Stewart Slocum
commited on
Commit
·
6589db3
1
Parent(s):
36bf1d8
Add fine-tuned model
Browse files- README.md +7 -0
- adapter_config.json +39 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +17 -0
- tokenizer.json +3 -0
- tokenizer_config.json +2065 -0
- trainer_state.json +3472 -0
README.md
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference
|
3 |
+
library_name: peft
|
4 |
+
---
|
5 |
+
### Framework versions
|
6 |
+
|
7 |
+
- PEFT 0.15.1
|
adapter_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "togethercomputer/Meta-Llama-3.3-70B-Instruct-Reference",
|
5 |
+
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
+
"fan_in_fan_out": false,
|
10 |
+
"inference_mode": true,
|
11 |
+
"init_lora_weights": true,
|
12 |
+
"layer_replication": null,
|
13 |
+
"layers_pattern": null,
|
14 |
+
"layers_to_transform": null,
|
15 |
+
"loftq_config": {},
|
16 |
+
"lora_alpha": 128,
|
17 |
+
"lora_bias": false,
|
18 |
+
"lora_dropout": 0.0,
|
19 |
+
"megatron_config": null,
|
20 |
+
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
22 |
+
"peft_type": "LORA",
|
23 |
+
"r": 64,
|
24 |
+
"rank_pattern": {},
|
25 |
+
"revision": null,
|
26 |
+
"target_modules": [
|
27 |
+
"down_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"o_proj",
|
30 |
+
"q_proj",
|
31 |
+
"v_proj",
|
32 |
+
"up_proj",
|
33 |
+
"k_proj"
|
34 |
+
],
|
35 |
+
"task_type": "CAUSAL_LM",
|
36 |
+
"trainable_token_indices": null,
|
37 |
+
"use_dora": false,
|
38 |
+
"use_rslora": false
|
39 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc0c1b6c5d63d6da84ba12739c748373828d8f3a77a42ef83f3bc9039d1d785a
|
3 |
+
size 1656903768
|
special_tokens_map.json
ADDED
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin_of_text|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<|eot_id|>"
|
17 |
+
}
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79e3e522635f3171300913bb421464a87de6222182a0570b9b2ccba2a964b2b4
|
3 |
+
size 9085657
|
tokenizer_config.json
ADDED
@@ -0,0 +1,2065 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"128000": {
|
4 |
+
"content": "<|begin_of_text|>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"128001": {
|
12 |
+
"content": "<|end_of_text|>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"128002": {
|
20 |
+
"content": "<|reserved_special_token_0|>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"128003": {
|
28 |
+
"content": "<|reserved_special_token_1|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"128004": {
|
36 |
+
"content": "<|finetune_right_pad_id|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"128005": {
|
44 |
+
"content": "<|reserved_special_token_2|>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"128006": {
|
52 |
+
"content": "<|start_header_id|>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"128007": {
|
60 |
+
"content": "<|end_header_id|>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"128008": {
|
68 |
+
"content": "<|eom_id|>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"128009": {
|
76 |
+
"content": "<|eot_id|>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"128010": {
|
84 |
+
"content": "<|python_tag|>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"128011": {
|
92 |
+
"content": "<|reserved_special_token_3|>",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"128012": {
|
100 |
+
"content": "<|reserved_special_token_4|>",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"128013": {
|
108 |
+
"content": "<|reserved_special_token_5|>",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"128014": {
|
116 |
+
"content": "<|reserved_special_token_6|>",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"128015": {
|
124 |
+
"content": "<|reserved_special_token_7|>",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"128016": {
|
132 |
+
"content": "<|reserved_special_token_8|>",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"128017": {
|
140 |
+
"content": "<|reserved_special_token_9|>",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"128018": {
|
148 |
+
"content": "<|reserved_special_token_10|>",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"128019": {
|
156 |
+
"content": "<|reserved_special_token_11|>",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"128020": {
|
164 |
+
"content": "<|reserved_special_token_12|>",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"128021": {
|
172 |
+
"content": "<|reserved_special_token_13|>",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"128022": {
|
180 |
+
"content": "<|reserved_special_token_14|>",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
},
|
187 |
+
"128023": {
|
188 |
+
"content": "<|reserved_special_token_15|>",
|
189 |
+
"lstrip": false,
|
190 |
+
"normalized": false,
|
191 |
+
"rstrip": false,
|
192 |
+
"single_word": false,
|
193 |
+
"special": true
|
194 |
+
},
|
195 |
+
"128024": {
|
196 |
+
"content": "<|reserved_special_token_16|>",
|
197 |
+
"lstrip": false,
|
198 |
+
"normalized": false,
|
199 |
+
"rstrip": false,
|
200 |
+
"single_word": false,
|
201 |
+
"special": true
|
202 |
+
},
|
203 |
+
"128025": {
|
204 |
+
"content": "<|reserved_special_token_17|>",
|
205 |
+
"lstrip": false,
|
206 |
+
"normalized": false,
|
207 |
+
"rstrip": false,
|
208 |
+
"single_word": false,
|
209 |
+
"special": true
|
210 |
+
},
|
211 |
+
"128026": {
|
212 |
+
"content": "<|reserved_special_token_18|>",
|
213 |
+
"lstrip": false,
|
214 |
+
"normalized": false,
|
215 |
+
"rstrip": false,
|
216 |
+
"single_word": false,
|
217 |
+
"special": true
|
218 |
+
},
|
219 |
+
"128027": {
|
220 |
+
"content": "<|reserved_special_token_19|>",
|
221 |
+
"lstrip": false,
|
222 |
+
"normalized": false,
|
223 |
+
"rstrip": false,
|
224 |
+
"single_word": false,
|
225 |
+
"special": true
|
226 |
+
},
|
227 |
+
"128028": {
|
228 |
+
"content": "<|reserved_special_token_20|>",
|
229 |
+
"lstrip": false,
|
230 |
+
"normalized": false,
|
231 |
+
"rstrip": false,
|
232 |
+
"single_word": false,
|
233 |
+
"special": true
|
234 |
+
},
|
235 |
+
"128029": {
|
236 |
+
"content": "<|reserved_special_token_21|>",
|
237 |
+
"lstrip": false,
|
238 |
+
"normalized": false,
|
239 |
+
"rstrip": false,
|
240 |
+
"single_word": false,
|
241 |
+
"special": true
|
242 |
+
},
|
243 |
+
"128030": {
|
244 |
+
"content": "<|reserved_special_token_22|>",
|
245 |
+
"lstrip": false,
|
246 |
+
"normalized": false,
|
247 |
+
"rstrip": false,
|
248 |
+
"single_word": false,
|
249 |
+
"special": true
|
250 |
+
},
|
251 |
+
"128031": {
|
252 |
+
"content": "<|reserved_special_token_23|>",
|
253 |
+
"lstrip": false,
|
254 |
+
"normalized": false,
|
255 |
+
"rstrip": false,
|
256 |
+
"single_word": false,
|
257 |
+
"special": true
|
258 |
+
},
|
259 |
+
"128032": {
|
260 |
+
"content": "<|reserved_special_token_24|>",
|
261 |
+
"lstrip": false,
|
262 |
+
"normalized": false,
|
263 |
+
"rstrip": false,
|
264 |
+
"single_word": false,
|
265 |
+
"special": true
|
266 |
+
},
|
267 |
+
"128033": {
|
268 |
+
"content": "<|reserved_special_token_25|>",
|
269 |
+
"lstrip": false,
|
270 |
+
"normalized": false,
|
271 |
+
"rstrip": false,
|
272 |
+
"single_word": false,
|
273 |
+
"special": true
|
274 |
+
},
|
275 |
+
"128034": {
|
276 |
+
"content": "<|reserved_special_token_26|>",
|
277 |
+
"lstrip": false,
|
278 |
+
"normalized": false,
|
279 |
+
"rstrip": false,
|
280 |
+
"single_word": false,
|
281 |
+
"special": true
|
282 |
+
},
|
283 |
+
"128035": {
|
284 |
+
"content": "<|reserved_special_token_27|>",
|
285 |
+
"lstrip": false,
|
286 |
+
"normalized": false,
|
287 |
+
"rstrip": false,
|
288 |
+
"single_word": false,
|
289 |
+
"special": true
|
290 |
+
},
|
291 |
+
"128036": {
|
292 |
+
"content": "<|reserved_special_token_28|>",
|
293 |
+
"lstrip": false,
|
294 |
+
"normalized": false,
|
295 |
+
"rstrip": false,
|
296 |
+
"single_word": false,
|
297 |
+
"special": true
|
298 |
+
},
|
299 |
+
"128037": {
|
300 |
+
"content": "<|reserved_special_token_29|>",
|
301 |
+
"lstrip": false,
|
302 |
+
"normalized": false,
|
303 |
+
"rstrip": false,
|
304 |
+
"single_word": false,
|
305 |
+
"special": true
|
306 |
+
},
|
307 |
+
"128038": {
|
308 |
+
"content": "<|reserved_special_token_30|>",
|
309 |
+
"lstrip": false,
|
310 |
+
"normalized": false,
|
311 |
+
"rstrip": false,
|
312 |
+
"single_word": false,
|
313 |
+
"special": true
|
314 |
+
},
|
315 |
+
"128039": {
|
316 |
+
"content": "<|reserved_special_token_31|>",
|
317 |
+
"lstrip": false,
|
318 |
+
"normalized": false,
|
319 |
+
"rstrip": false,
|
320 |
+
"single_word": false,
|
321 |
+
"special": true
|
322 |
+
},
|
323 |
+
"128040": {
|
324 |
+
"content": "<|reserved_special_token_32|>",
|
325 |
+
"lstrip": false,
|
326 |
+
"normalized": false,
|
327 |
+
"rstrip": false,
|
328 |
+
"single_word": false,
|
329 |
+
"special": true
|
330 |
+
},
|
331 |
+
"128041": {
|
332 |
+
"content": "<|reserved_special_token_33|>",
|
333 |
+
"lstrip": false,
|
334 |
+
"normalized": false,
|
335 |
+
"rstrip": false,
|
336 |
+
"single_word": false,
|
337 |
+
"special": true
|
338 |
+
},
|
339 |
+
"128042": {
|
340 |
+
"content": "<|reserved_special_token_34|>",
|
341 |
+
"lstrip": false,
|
342 |
+
"normalized": false,
|
343 |
+
"rstrip": false,
|
344 |
+
"single_word": false,
|
345 |
+
"special": true
|
346 |
+
},
|
347 |
+
"128043": {
|
348 |
+
"content": "<|reserved_special_token_35|>",
|
349 |
+
"lstrip": false,
|
350 |
+
"normalized": false,
|
351 |
+
"rstrip": false,
|
352 |
+
"single_word": false,
|
353 |
+
"special": true
|
354 |
+
},
|
355 |
+
"128044": {
|
356 |
+
"content": "<|reserved_special_token_36|>",
|
357 |
+
"lstrip": false,
|
358 |
+
"normalized": false,
|
359 |
+
"rstrip": false,
|
360 |
+
"single_word": false,
|
361 |
+
"special": true
|
362 |
+
},
|
363 |
+
"128045": {
|
364 |
+
"content": "<|reserved_special_token_37|>",
|
365 |
+
"lstrip": false,
|
366 |
+
"normalized": false,
|
367 |
+
"rstrip": false,
|
368 |
+
"single_word": false,
|
369 |
+
"special": true
|
370 |
+
},
|
371 |
+
"128046": {
|
372 |
+
"content": "<|reserved_special_token_38|>",
|
373 |
+
"lstrip": false,
|
374 |
+
"normalized": false,
|
375 |
+
"rstrip": false,
|
376 |
+
"single_word": false,
|
377 |
+
"special": true
|
378 |
+
},
|
379 |
+
"128047": {
|
380 |
+
"content": "<|reserved_special_token_39|>",
|
381 |
+
"lstrip": false,
|
382 |
+
"normalized": false,
|
383 |
+
"rstrip": false,
|
384 |
+
"single_word": false,
|
385 |
+
"special": true
|
386 |
+
},
|
387 |
+
"128048": {
|
388 |
+
"content": "<|reserved_special_token_40|>",
|
389 |
+
"lstrip": false,
|
390 |
+
"normalized": false,
|
391 |
+
"rstrip": false,
|
392 |
+
"single_word": false,
|
393 |
+
"special": true
|
394 |
+
},
|
395 |
+
"128049": {
|
396 |
+
"content": "<|reserved_special_token_41|>",
|
397 |
+
"lstrip": false,
|
398 |
+
"normalized": false,
|
399 |
+
"rstrip": false,
|
400 |
+
"single_word": false,
|
401 |
+
"special": true
|
402 |
+
},
|
403 |
+
"128050": {
|
404 |
+
"content": "<|reserved_special_token_42|>",
|
405 |
+
"lstrip": false,
|
406 |
+
"normalized": false,
|
407 |
+
"rstrip": false,
|
408 |
+
"single_word": false,
|
409 |
+
"special": true
|
410 |
+
},
|
411 |
+
"128051": {
|
412 |
+
"content": "<|reserved_special_token_43|>",
|
413 |
+
"lstrip": false,
|
414 |
+
"normalized": false,
|
415 |
+
"rstrip": false,
|
416 |
+
"single_word": false,
|
417 |
+
"special": true
|
418 |
+
},
|
419 |
+
"128052": {
|
420 |
+
"content": "<|reserved_special_token_44|>",
|
421 |
+
"lstrip": false,
|
422 |
+
"normalized": false,
|
423 |
+
"rstrip": false,
|
424 |
+
"single_word": false,
|
425 |
+
"special": true
|
426 |
+
},
|
427 |
+
"128053": {
|
428 |
+
"content": "<|reserved_special_token_45|>",
|
429 |
+
"lstrip": false,
|
430 |
+
"normalized": false,
|
431 |
+
"rstrip": false,
|
432 |
+
"single_word": false,
|
433 |
+
"special": true
|
434 |
+
},
|
435 |
+
"128054": {
|
436 |
+
"content": "<|reserved_special_token_46|>",
|
437 |
+
"lstrip": false,
|
438 |
+
"normalized": false,
|
439 |
+
"rstrip": false,
|
440 |
+
"single_word": false,
|
441 |
+
"special": true
|
442 |
+
},
|
443 |
+
"128055": {
|
444 |
+
"content": "<|reserved_special_token_47|>",
|
445 |
+
"lstrip": false,
|
446 |
+
"normalized": false,
|
447 |
+
"rstrip": false,
|
448 |
+
"single_word": false,
|
449 |
+
"special": true
|
450 |
+
},
|
451 |
+
"128056": {
|
452 |
+
"content": "<|reserved_special_token_48|>",
|
453 |
+
"lstrip": false,
|
454 |
+
"normalized": false,
|
455 |
+
"rstrip": false,
|
456 |
+
"single_word": false,
|
457 |
+
"special": true
|
458 |
+
},
|
459 |
+
"128057": {
|
460 |
+
"content": "<|reserved_special_token_49|>",
|
461 |
+
"lstrip": false,
|
462 |
+
"normalized": false,
|
463 |
+
"rstrip": false,
|
464 |
+
"single_word": false,
|
465 |
+
"special": true
|
466 |
+
},
|
467 |
+
"128058": {
|
468 |
+
"content": "<|reserved_special_token_50|>",
|
469 |
+
"lstrip": false,
|
470 |
+
"normalized": false,
|
471 |
+
"rstrip": false,
|
472 |
+
"single_word": false,
|
473 |
+
"special": true
|
474 |
+
},
|
475 |
+
"128059": {
|
476 |
+
"content": "<|reserved_special_token_51|>",
|
477 |
+
"lstrip": false,
|
478 |
+
"normalized": false,
|
479 |
+
"rstrip": false,
|
480 |
+
"single_word": false,
|
481 |
+
"special": true
|
482 |
+
},
|
483 |
+
"128060": {
|
484 |
+
"content": "<|reserved_special_token_52|>",
|
485 |
+
"lstrip": false,
|
486 |
+
"normalized": false,
|
487 |
+
"rstrip": false,
|
488 |
+
"single_word": false,
|
489 |
+
"special": true
|
490 |
+
},
|
491 |
+
"128061": {
|
492 |
+
"content": "<|reserved_special_token_53|>",
|
493 |
+
"lstrip": false,
|
494 |
+
"normalized": false,
|
495 |
+
"rstrip": false,
|
496 |
+
"single_word": false,
|
497 |
+
"special": true
|
498 |
+
},
|
499 |
+
"128062": {
|
500 |
+
"content": "<|reserved_special_token_54|>",
|
501 |
+
"lstrip": false,
|
502 |
+
"normalized": false,
|
503 |
+
"rstrip": false,
|
504 |
+
"single_word": false,
|
505 |
+
"special": true
|
506 |
+
},
|
507 |
+
"128063": {
|
508 |
+
"content": "<|reserved_special_token_55|>",
|
509 |
+
"lstrip": false,
|
510 |
+
"normalized": false,
|
511 |
+
"rstrip": false,
|
512 |
+
"single_word": false,
|
513 |
+
"special": true
|
514 |
+
},
|
515 |
+
"128064": {
|
516 |
+
"content": "<|reserved_special_token_56|>",
|
517 |
+
"lstrip": false,
|
518 |
+
"normalized": false,
|
519 |
+
"rstrip": false,
|
520 |
+
"single_word": false,
|
521 |
+
"special": true
|
522 |
+
},
|
523 |
+
"128065": {
|
524 |
+
"content": "<|reserved_special_token_57|>",
|
525 |
+
"lstrip": false,
|
526 |
+
"normalized": false,
|
527 |
+
"rstrip": false,
|
528 |
+
"single_word": false,
|
529 |
+
"special": true
|
530 |
+
},
|
531 |
+
"128066": {
|
532 |
+
"content": "<|reserved_special_token_58|>",
|
533 |
+
"lstrip": false,
|
534 |
+
"normalized": false,
|
535 |
+
"rstrip": false,
|
536 |
+
"single_word": false,
|
537 |
+
"special": true
|
538 |
+
},
|
539 |
+
"128067": {
|
540 |
+
"content": "<|reserved_special_token_59|>",
|
541 |
+
"lstrip": false,
|
542 |
+
"normalized": false,
|
543 |
+
"rstrip": false,
|
544 |
+
"single_word": false,
|
545 |
+
"special": true
|
546 |
+
},
|
547 |
+
"128068": {
|
548 |
+
"content": "<|reserved_special_token_60|>",
|
549 |
+
"lstrip": false,
|
550 |
+
"normalized": false,
|
551 |
+
"rstrip": false,
|
552 |
+
"single_word": false,
|
553 |
+
"special": true
|
554 |
+
},
|
555 |
+
"128069": {
|
556 |
+
"content": "<|reserved_special_token_61|>",
|
557 |
+
"lstrip": false,
|
558 |
+
"normalized": false,
|
559 |
+
"rstrip": false,
|
560 |
+
"single_word": false,
|
561 |
+
"special": true
|
562 |
+
},
|
563 |
+
"128070": {
|
564 |
+
"content": "<|reserved_special_token_62|>",
|
565 |
+
"lstrip": false,
|
566 |
+
"normalized": false,
|
567 |
+
"rstrip": false,
|
568 |
+
"single_word": false,
|
569 |
+
"special": true
|
570 |
+
},
|
571 |
+
"128071": {
|
572 |
+
"content": "<|reserved_special_token_63|>",
|
573 |
+
"lstrip": false,
|
574 |
+
"normalized": false,
|
575 |
+
"rstrip": false,
|
576 |
+
"single_word": false,
|
577 |
+
"special": true
|
578 |
+
},
|
579 |
+
"128072": {
|
580 |
+
"content": "<|reserved_special_token_64|>",
|
581 |
+
"lstrip": false,
|
582 |
+
"normalized": false,
|
583 |
+
"rstrip": false,
|
584 |
+
"single_word": false,
|
585 |
+
"special": true
|
586 |
+
},
|
587 |
+
"128073": {
|
588 |
+
"content": "<|reserved_special_token_65|>",
|
589 |
+
"lstrip": false,
|
590 |
+
"normalized": false,
|
591 |
+
"rstrip": false,
|
592 |
+
"single_word": false,
|
593 |
+
"special": true
|
594 |
+
},
|
595 |
+
"128074": {
|
596 |
+
"content": "<|reserved_special_token_66|>",
|
597 |
+
"lstrip": false,
|
598 |
+
"normalized": false,
|
599 |
+
"rstrip": false,
|
600 |
+
"single_word": false,
|
601 |
+
"special": true
|
602 |
+
},
|
603 |
+
"128075": {
|
604 |
+
"content": "<|reserved_special_token_67|>",
|
605 |
+
"lstrip": false,
|
606 |
+
"normalized": false,
|
607 |
+
"rstrip": false,
|
608 |
+
"single_word": false,
|
609 |
+
"special": true
|
610 |
+
},
|
611 |
+
"128076": {
|
612 |
+
"content": "<|reserved_special_token_68|>",
|
613 |
+
"lstrip": false,
|
614 |
+
"normalized": false,
|
615 |
+
"rstrip": false,
|
616 |
+
"single_word": false,
|
617 |
+
"special": true
|
618 |
+
},
|
619 |
+
"128077": {
|
620 |
+
"content": "<|reserved_special_token_69|>",
|
621 |
+
"lstrip": false,
|
622 |
+
"normalized": false,
|
623 |
+
"rstrip": false,
|
624 |
+
"single_word": false,
|
625 |
+
"special": true
|
626 |
+
},
|
627 |
+
"128078": {
|
628 |
+
"content": "<|reserved_special_token_70|>",
|
629 |
+
"lstrip": false,
|
630 |
+
"normalized": false,
|
631 |
+
"rstrip": false,
|
632 |
+
"single_word": false,
|
633 |
+
"special": true
|
634 |
+
},
|
635 |
+
"128079": {
|
636 |
+
"content": "<|reserved_special_token_71|>",
|
637 |
+
"lstrip": false,
|
638 |
+
"normalized": false,
|
639 |
+
"rstrip": false,
|
640 |
+
"single_word": false,
|
641 |
+
"special": true
|
642 |
+
},
|
643 |
+
"128080": {
|
644 |
+
"content": "<|reserved_special_token_72|>",
|
645 |
+
"lstrip": false,
|
646 |
+
"normalized": false,
|
647 |
+
"rstrip": false,
|
648 |
+
"single_word": false,
|
649 |
+
"special": true
|
650 |
+
},
|
651 |
+
"128081": {
|
652 |
+
"content": "<|reserved_special_token_73|>",
|
653 |
+
"lstrip": false,
|
654 |
+
"normalized": false,
|
655 |
+
"rstrip": false,
|
656 |
+
"single_word": false,
|
657 |
+
"special": true
|
658 |
+
},
|
659 |
+
"128082": {
|
660 |
+
"content": "<|reserved_special_token_74|>",
|
661 |
+
"lstrip": false,
|
662 |
+
"normalized": false,
|
663 |
+
"rstrip": false,
|
664 |
+
"single_word": false,
|
665 |
+
"special": true
|
666 |
+
},
|
667 |
+
"128083": {
|
668 |
+
"content": "<|reserved_special_token_75|>",
|
669 |
+
"lstrip": false,
|
670 |
+
"normalized": false,
|
671 |
+
"rstrip": false,
|
672 |
+
"single_word": false,
|
673 |
+
"special": true
|
674 |
+
},
|
675 |
+
"128084": {
|
676 |
+
"content": "<|reserved_special_token_76|>",
|
677 |
+
"lstrip": false,
|
678 |
+
"normalized": false,
|
679 |
+
"rstrip": false,
|
680 |
+
"single_word": false,
|
681 |
+
"special": true
|
682 |
+
},
|
683 |
+
"128085": {
|
684 |
+
"content": "<|reserved_special_token_77|>",
|
685 |
+
"lstrip": false,
|
686 |
+
"normalized": false,
|
687 |
+
"rstrip": false,
|
688 |
+
"single_word": false,
|
689 |
+
"special": true
|
690 |
+
},
|
691 |
+
"128086": {
|
692 |
+
"content": "<|reserved_special_token_78|>",
|
693 |
+
"lstrip": false,
|
694 |
+
"normalized": false,
|
695 |
+
"rstrip": false,
|
696 |
+
"single_word": false,
|
697 |
+
"special": true
|
698 |
+
},
|
699 |
+
"128087": {
|
700 |
+
"content": "<|reserved_special_token_79|>",
|
701 |
+
"lstrip": false,
|
702 |
+
"normalized": false,
|
703 |
+
"rstrip": false,
|
704 |
+
"single_word": false,
|
705 |
+
"special": true
|
706 |
+
},
|
707 |
+
"128088": {
|
708 |
+
"content": "<|reserved_special_token_80|>",
|
709 |
+
"lstrip": false,
|
710 |
+
"normalized": false,
|
711 |
+
"rstrip": false,
|
712 |
+
"single_word": false,
|
713 |
+
"special": true
|
714 |
+
},
|
715 |
+
"128089": {
|
716 |
+
"content": "<|reserved_special_token_81|>",
|
717 |
+
"lstrip": false,
|
718 |
+
"normalized": false,
|
719 |
+
"rstrip": false,
|
720 |
+
"single_word": false,
|
721 |
+
"special": true
|
722 |
+
},
|
723 |
+
"128090": {
|
724 |
+
"content": "<|reserved_special_token_82|>",
|
725 |
+
"lstrip": false,
|
726 |
+
"normalized": false,
|
727 |
+
"rstrip": false,
|
728 |
+
"single_word": false,
|
729 |
+
"special": true
|
730 |
+
},
|
731 |
+
"128091": {
|
732 |
+
"content": "<|reserved_special_token_83|>",
|
733 |
+
"lstrip": false,
|
734 |
+
"normalized": false,
|
735 |
+
"rstrip": false,
|
736 |
+
"single_word": false,
|
737 |
+
"special": true
|
738 |
+
},
|
739 |
+
"128092": {
|
740 |
+
"content": "<|reserved_special_token_84|>",
|
741 |
+
"lstrip": false,
|
742 |
+
"normalized": false,
|
743 |
+
"rstrip": false,
|
744 |
+
"single_word": false,
|
745 |
+
"special": true
|
746 |
+
},
|
747 |
+
"128093": {
|
748 |
+
"content": "<|reserved_special_token_85|>",
|
749 |
+
"lstrip": false,
|
750 |
+
"normalized": false,
|
751 |
+
"rstrip": false,
|
752 |
+
"single_word": false,
|
753 |
+
"special": true
|
754 |
+
},
|
755 |
+
"128094": {
|
756 |
+
"content": "<|reserved_special_token_86|>",
|
757 |
+
"lstrip": false,
|
758 |
+
"normalized": false,
|
759 |
+
"rstrip": false,
|
760 |
+
"single_word": false,
|
761 |
+
"special": true
|
762 |
+
},
|
763 |
+
"128095": {
|
764 |
+
"content": "<|reserved_special_token_87|>",
|
765 |
+
"lstrip": false,
|
766 |
+
"normalized": false,
|
767 |
+
"rstrip": false,
|
768 |
+
"single_word": false,
|
769 |
+
"special": true
|
770 |
+
},
|
771 |
+
"128096": {
|
772 |
+
"content": "<|reserved_special_token_88|>",
|
773 |
+
"lstrip": false,
|
774 |
+
"normalized": false,
|
775 |
+
"rstrip": false,
|
776 |
+
"single_word": false,
|
777 |
+
"special": true
|
778 |
+
},
|
779 |
+
"128097": {
|
780 |
+
"content": "<|reserved_special_token_89|>",
|
781 |
+
"lstrip": false,
|
782 |
+
"normalized": false,
|
783 |
+
"rstrip": false,
|
784 |
+
"single_word": false,
|
785 |
+
"special": true
|
786 |
+
},
|
787 |
+
"128098": {
|
788 |
+
"content": "<|reserved_special_token_90|>",
|
789 |
+
"lstrip": false,
|
790 |
+
"normalized": false,
|
791 |
+
"rstrip": false,
|
792 |
+
"single_word": false,
|
793 |
+
"special": true
|
794 |
+
},
|
795 |
+
"128099": {
|
796 |
+
"content": "<|reserved_special_token_91|>",
|
797 |
+
"lstrip": false,
|
798 |
+
"normalized": false,
|
799 |
+
"rstrip": false,
|
800 |
+
"single_word": false,
|
801 |
+
"special": true
|
802 |
+
},
|
803 |
+
"128100": {
|
804 |
+
"content": "<|reserved_special_token_92|>",
|
805 |
+
"lstrip": false,
|
806 |
+
"normalized": false,
|
807 |
+
"rstrip": false,
|
808 |
+
"single_word": false,
|
809 |
+
"special": true
|
810 |
+
},
|
811 |
+
"128101": {
|
812 |
+
"content": "<|reserved_special_token_93|>",
|
813 |
+
"lstrip": false,
|
814 |
+
"normalized": false,
|
815 |
+
"rstrip": false,
|
816 |
+
"single_word": false,
|
817 |
+
"special": true
|
818 |
+
},
|
819 |
+
"128102": {
|
820 |
+
"content": "<|reserved_special_token_94|>",
|
821 |
+
"lstrip": false,
|
822 |
+
"normalized": false,
|
823 |
+
"rstrip": false,
|
824 |
+
"single_word": false,
|
825 |
+
"special": true
|
826 |
+
},
|
827 |
+
"128103": {
|
828 |
+
"content": "<|reserved_special_token_95|>",
|
829 |
+
"lstrip": false,
|
830 |
+
"normalized": false,
|
831 |
+
"rstrip": false,
|
832 |
+
"single_word": false,
|
833 |
+
"special": true
|
834 |
+
},
|
835 |
+
"128104": {
|
836 |
+
"content": "<|reserved_special_token_96|>",
|
837 |
+
"lstrip": false,
|
838 |
+
"normalized": false,
|
839 |
+
"rstrip": false,
|
840 |
+
"single_word": false,
|
841 |
+
"special": true
|
842 |
+
},
|
843 |
+
"128105": {
|
844 |
+
"content": "<|reserved_special_token_97|>",
|
845 |
+
"lstrip": false,
|
846 |
+
"normalized": false,
|
847 |
+
"rstrip": false,
|
848 |
+
"single_word": false,
|
849 |
+
"special": true
|
850 |
+
},
|
851 |
+
"128106": {
|
852 |
+
"content": "<|reserved_special_token_98|>",
|
853 |
+
"lstrip": false,
|
854 |
+
"normalized": false,
|
855 |
+
"rstrip": false,
|
856 |
+
"single_word": false,
|
857 |
+
"special": true
|
858 |
+
},
|
859 |
+
"128107": {
|
860 |
+
"content": "<|reserved_special_token_99|>",
|
861 |
+
"lstrip": false,
|
862 |
+
"normalized": false,
|
863 |
+
"rstrip": false,
|
864 |
+
"single_word": false,
|
865 |
+
"special": true
|
866 |
+
},
|
867 |
+
"128108": {
|
868 |
+
"content": "<|reserved_special_token_100|>",
|
869 |
+
"lstrip": false,
|
870 |
+
"normalized": false,
|
871 |
+
"rstrip": false,
|
872 |
+
"single_word": false,
|
873 |
+
"special": true
|
874 |
+
},
|
875 |
+
"128109": {
|
876 |
+
"content": "<|reserved_special_token_101|>",
|
877 |
+
"lstrip": false,
|
878 |
+
"normalized": false,
|
879 |
+
"rstrip": false,
|
880 |
+
"single_word": false,
|
881 |
+
"special": true
|
882 |
+
},
|
883 |
+
"128110": {
|
884 |
+
"content": "<|reserved_special_token_102|>",
|
885 |
+
"lstrip": false,
|
886 |
+
"normalized": false,
|
887 |
+
"rstrip": false,
|
888 |
+
"single_word": false,
|
889 |
+
"special": true
|
890 |
+
},
|
891 |
+
"128111": {
|
892 |
+
"content": "<|reserved_special_token_103|>",
|
893 |
+
"lstrip": false,
|
894 |
+
"normalized": false,
|
895 |
+
"rstrip": false,
|
896 |
+
"single_word": false,
|
897 |
+
"special": true
|
898 |
+
},
|
899 |
+
"128112": {
|
900 |
+
"content": "<|reserved_special_token_104|>",
|
901 |
+
"lstrip": false,
|
902 |
+
"normalized": false,
|
903 |
+
"rstrip": false,
|
904 |
+
"single_word": false,
|
905 |
+
"special": true
|
906 |
+
},
|
907 |
+
"128113": {
|
908 |
+
"content": "<|reserved_special_token_105|>",
|
909 |
+
"lstrip": false,
|
910 |
+
"normalized": false,
|
911 |
+
"rstrip": false,
|
912 |
+
"single_word": false,
|
913 |
+
"special": true
|
914 |
+
},
|
915 |
+
"128114": {
|
916 |
+
"content": "<|reserved_special_token_106|>",
|
917 |
+
"lstrip": false,
|
918 |
+
"normalized": false,
|
919 |
+
"rstrip": false,
|
920 |
+
"single_word": false,
|
921 |
+
"special": true
|
922 |
+
},
|
923 |
+
"128115": {
|
924 |
+
"content": "<|reserved_special_token_107|>",
|
925 |
+
"lstrip": false,
|
926 |
+
"normalized": false,
|
927 |
+
"rstrip": false,
|
928 |
+
"single_word": false,
|
929 |
+
"special": true
|
930 |
+
},
|
931 |
+
"128116": {
|
932 |
+
"content": "<|reserved_special_token_108|>",
|
933 |
+
"lstrip": false,
|
934 |
+
"normalized": false,
|
935 |
+
"rstrip": false,
|
936 |
+
"single_word": false,
|
937 |
+
"special": true
|
938 |
+
},
|
939 |
+
"128117": {
|
940 |
+
"content": "<|reserved_special_token_109|>",
|
941 |
+
"lstrip": false,
|
942 |
+
"normalized": false,
|
943 |
+
"rstrip": false,
|
944 |
+
"single_word": false,
|
945 |
+
"special": true
|
946 |
+
},
|
947 |
+
"128118": {
|
948 |
+
"content": "<|reserved_special_token_110|>",
|
949 |
+
"lstrip": false,
|
950 |
+
"normalized": false,
|
951 |
+
"rstrip": false,
|
952 |
+
"single_word": false,
|
953 |
+
"special": true
|
954 |
+
},
|
955 |
+
"128119": {
|
956 |
+
"content": "<|reserved_special_token_111|>",
|
957 |
+
"lstrip": false,
|
958 |
+
"normalized": false,
|
959 |
+
"rstrip": false,
|
960 |
+
"single_word": false,
|
961 |
+
"special": true
|
962 |
+
},
|
963 |
+
"128120": {
|
964 |
+
"content": "<|reserved_special_token_112|>",
|
965 |
+
"lstrip": false,
|
966 |
+
"normalized": false,
|
967 |
+
"rstrip": false,
|
968 |
+
"single_word": false,
|
969 |
+
"special": true
|
970 |
+
},
|
971 |
+
"128121": {
|
972 |
+
"content": "<|reserved_special_token_113|>",
|
973 |
+
"lstrip": false,
|
974 |
+
"normalized": false,
|
975 |
+
"rstrip": false,
|
976 |
+
"single_word": false,
|
977 |
+
"special": true
|
978 |
+
},
|
979 |
+
"128122": {
|
980 |
+
"content": "<|reserved_special_token_114|>",
|
981 |
+
"lstrip": false,
|
982 |
+
"normalized": false,
|
983 |
+
"rstrip": false,
|
984 |
+
"single_word": false,
|
985 |
+
"special": true
|
986 |
+
},
|
987 |
+
"128123": {
|
988 |
+
"content": "<|reserved_special_token_115|>",
|
989 |
+
"lstrip": false,
|
990 |
+
"normalized": false,
|
991 |
+
"rstrip": false,
|
992 |
+
"single_word": false,
|
993 |
+
"special": true
|
994 |
+
},
|
995 |
+
"128124": {
|
996 |
+
"content": "<|reserved_special_token_116|>",
|
997 |
+
"lstrip": false,
|
998 |
+
"normalized": false,
|
999 |
+
"rstrip": false,
|
1000 |
+
"single_word": false,
|
1001 |
+
"special": true
|
1002 |
+
},
|
1003 |
+
"128125": {
|
1004 |
+
"content": "<|reserved_special_token_117|>",
|
1005 |
+
"lstrip": false,
|
1006 |
+
"normalized": false,
|
1007 |
+
"rstrip": false,
|
1008 |
+
"single_word": false,
|
1009 |
+
"special": true
|
1010 |
+
},
|
1011 |
+
"128126": {
|
1012 |
+
"content": "<|reserved_special_token_118|>",
|
1013 |
+
"lstrip": false,
|
1014 |
+
"normalized": false,
|
1015 |
+
"rstrip": false,
|
1016 |
+
"single_word": false,
|
1017 |
+
"special": true
|
1018 |
+
},
|
1019 |
+
"128127": {
|
1020 |
+
"content": "<|reserved_special_token_119|>",
|
1021 |
+
"lstrip": false,
|
1022 |
+
"normalized": false,
|
1023 |
+
"rstrip": false,
|
1024 |
+
"single_word": false,
|
1025 |
+
"special": true
|
1026 |
+
},
|
1027 |
+
"128128": {
|
1028 |
+
"content": "<|reserved_special_token_120|>",
|
1029 |
+
"lstrip": false,
|
1030 |
+
"normalized": false,
|
1031 |
+
"rstrip": false,
|
1032 |
+
"single_word": false,
|
1033 |
+
"special": true
|
1034 |
+
},
|
1035 |
+
"128129": {
|
1036 |
+
"content": "<|reserved_special_token_121|>",
|
1037 |
+
"lstrip": false,
|
1038 |
+
"normalized": false,
|
1039 |
+
"rstrip": false,
|
1040 |
+
"single_word": false,
|
1041 |
+
"special": true
|
1042 |
+
},
|
1043 |
+
"128130": {
|
1044 |
+
"content": "<|reserved_special_token_122|>",
|
1045 |
+
"lstrip": false,
|
1046 |
+
"normalized": false,
|
1047 |
+
"rstrip": false,
|
1048 |
+
"single_word": false,
|
1049 |
+
"special": true
|
1050 |
+
},
|
1051 |
+
"128131": {
|
1052 |
+
"content": "<|reserved_special_token_123|>",
|
1053 |
+
"lstrip": false,
|
1054 |
+
"normalized": false,
|
1055 |
+
"rstrip": false,
|
1056 |
+
"single_word": false,
|
1057 |
+
"special": true
|
1058 |
+
},
|
1059 |
+
"128132": {
|
1060 |
+
"content": "<|reserved_special_token_124|>",
|
1061 |
+
"lstrip": false,
|
1062 |
+
"normalized": false,
|
1063 |
+
"rstrip": false,
|
1064 |
+
"single_word": false,
|
1065 |
+
"special": true
|
1066 |
+
},
|
1067 |
+
"128133": {
|
1068 |
+
"content": "<|reserved_special_token_125|>",
|
1069 |
+
"lstrip": false,
|
1070 |
+
"normalized": false,
|
1071 |
+
"rstrip": false,
|
1072 |
+
"single_word": false,
|
1073 |
+
"special": true
|
1074 |
+
},
|
1075 |
+
"128134": {
|
1076 |
+
"content": "<|reserved_special_token_126|>",
|
1077 |
+
"lstrip": false,
|
1078 |
+
"normalized": false,
|
1079 |
+
"rstrip": false,
|
1080 |
+
"single_word": false,
|
1081 |
+
"special": true
|
1082 |
+
},
|
1083 |
+
"128135": {
|
1084 |
+
"content": "<|reserved_special_token_127|>",
|
1085 |
+
"lstrip": false,
|
1086 |
+
"normalized": false,
|
1087 |
+
"rstrip": false,
|
1088 |
+
"single_word": false,
|
1089 |
+
"special": true
|
1090 |
+
},
|
1091 |
+
"128136": {
|
1092 |
+
"content": "<|reserved_special_token_128|>",
|
1093 |
+
"lstrip": false,
|
1094 |
+
"normalized": false,
|
1095 |
+
"rstrip": false,
|
1096 |
+
"single_word": false,
|
1097 |
+
"special": true
|
1098 |
+
},
|
1099 |
+
"128137": {
|
1100 |
+
"content": "<|reserved_special_token_129|>",
|
1101 |
+
"lstrip": false,
|
1102 |
+
"normalized": false,
|
1103 |
+
"rstrip": false,
|
1104 |
+
"single_word": false,
|
1105 |
+
"special": true
|
1106 |
+
},
|
1107 |
+
"128138": {
|
1108 |
+
"content": "<|reserved_special_token_130|>",
|
1109 |
+
"lstrip": false,
|
1110 |
+
"normalized": false,
|
1111 |
+
"rstrip": false,
|
1112 |
+
"single_word": false,
|
1113 |
+
"special": true
|
1114 |
+
},
|
1115 |
+
"128139": {
|
1116 |
+
"content": "<|reserved_special_token_131|>",
|
1117 |
+
"lstrip": false,
|
1118 |
+
"normalized": false,
|
1119 |
+
"rstrip": false,
|
1120 |
+
"single_word": false,
|
1121 |
+
"special": true
|
1122 |
+
},
|
1123 |
+
"128140": {
|
1124 |
+
"content": "<|reserved_special_token_132|>",
|
1125 |
+
"lstrip": false,
|
1126 |
+
"normalized": false,
|
1127 |
+
"rstrip": false,
|
1128 |
+
"single_word": false,
|
1129 |
+
"special": true
|
1130 |
+
},
|
1131 |
+
"128141": {
|
1132 |
+
"content": "<|reserved_special_token_133|>",
|
1133 |
+
"lstrip": false,
|
1134 |
+
"normalized": false,
|
1135 |
+
"rstrip": false,
|
1136 |
+
"single_word": false,
|
1137 |
+
"special": true
|
1138 |
+
},
|
1139 |
+
"128142": {
|
1140 |
+
"content": "<|reserved_special_token_134|>",
|
1141 |
+
"lstrip": false,
|
1142 |
+
"normalized": false,
|
1143 |
+
"rstrip": false,
|
1144 |
+
"single_word": false,
|
1145 |
+
"special": true
|
1146 |
+
},
|
1147 |
+
"128143": {
|
1148 |
+
"content": "<|reserved_special_token_135|>",
|
1149 |
+
"lstrip": false,
|
1150 |
+
"normalized": false,
|
1151 |
+
"rstrip": false,
|
1152 |
+
"single_word": false,
|
1153 |
+
"special": true
|
1154 |
+
},
|
1155 |
+
"128144": {
|
1156 |
+
"content": "<|reserved_special_token_136|>",
|
1157 |
+
"lstrip": false,
|
1158 |
+
"normalized": false,
|
1159 |
+
"rstrip": false,
|
1160 |
+
"single_word": false,
|
1161 |
+
"special": true
|
1162 |
+
},
|
1163 |
+
"128145": {
|
1164 |
+
"content": "<|reserved_special_token_137|>",
|
1165 |
+
"lstrip": false,
|
1166 |
+
"normalized": false,
|
1167 |
+
"rstrip": false,
|
1168 |
+
"single_word": false,
|
1169 |
+
"special": true
|
1170 |
+
},
|
1171 |
+
"128146": {
|
1172 |
+
"content": "<|reserved_special_token_138|>",
|
1173 |
+
"lstrip": false,
|
1174 |
+
"normalized": false,
|
1175 |
+
"rstrip": false,
|
1176 |
+
"single_word": false,
|
1177 |
+
"special": true
|
1178 |
+
},
|
1179 |
+
"128147": {
|
1180 |
+
"content": "<|reserved_special_token_139|>",
|
1181 |
+
"lstrip": false,
|
1182 |
+
"normalized": false,
|
1183 |
+
"rstrip": false,
|
1184 |
+
"single_word": false,
|
1185 |
+
"special": true
|
1186 |
+
},
|
1187 |
+
"128148": {
|
1188 |
+
"content": "<|reserved_special_token_140|>",
|
1189 |
+
"lstrip": false,
|
1190 |
+
"normalized": false,
|
1191 |
+
"rstrip": false,
|
1192 |
+
"single_word": false,
|
1193 |
+
"special": true
|
1194 |
+
},
|
1195 |
+
"128149": {
|
1196 |
+
"content": "<|reserved_special_token_141|>",
|
1197 |
+
"lstrip": false,
|
1198 |
+
"normalized": false,
|
1199 |
+
"rstrip": false,
|
1200 |
+
"single_word": false,
|
1201 |
+
"special": true
|
1202 |
+
},
|
1203 |
+
"128150": {
|
1204 |
+
"content": "<|reserved_special_token_142|>",
|
1205 |
+
"lstrip": false,
|
1206 |
+
"normalized": false,
|
1207 |
+
"rstrip": false,
|
1208 |
+
"single_word": false,
|
1209 |
+
"special": true
|
1210 |
+
},
|
1211 |
+
"128151": {
|
1212 |
+
"content": "<|reserved_special_token_143|>",
|
1213 |
+
"lstrip": false,
|
1214 |
+
"normalized": false,
|
1215 |
+
"rstrip": false,
|
1216 |
+
"single_word": false,
|
1217 |
+
"special": true
|
1218 |
+
},
|
1219 |
+
"128152": {
|
1220 |
+
"content": "<|reserved_special_token_144|>",
|
1221 |
+
"lstrip": false,
|
1222 |
+
"normalized": false,
|
1223 |
+
"rstrip": false,
|
1224 |
+
"single_word": false,
|
1225 |
+
"special": true
|
1226 |
+
},
|
1227 |
+
"128153": {
|
1228 |
+
"content": "<|reserved_special_token_145|>",
|
1229 |
+
"lstrip": false,
|
1230 |
+
"normalized": false,
|
1231 |
+
"rstrip": false,
|
1232 |
+
"single_word": false,
|
1233 |
+
"special": true
|
1234 |
+
},
|
1235 |
+
"128154": {
|
1236 |
+
"content": "<|reserved_special_token_146|>",
|
1237 |
+
"lstrip": false,
|
1238 |
+
"normalized": false,
|
1239 |
+
"rstrip": false,
|
1240 |
+
"single_word": false,
|
1241 |
+
"special": true
|
1242 |
+
},
|
1243 |
+
"128155": {
|
1244 |
+
"content": "<|reserved_special_token_147|>",
|
1245 |
+
"lstrip": false,
|
1246 |
+
"normalized": false,
|
1247 |
+
"rstrip": false,
|
1248 |
+
"single_word": false,
|
1249 |
+
"special": true
|
1250 |
+
},
|
1251 |
+
"128156": {
|
1252 |
+
"content": "<|reserved_special_token_148|>",
|
1253 |
+
"lstrip": false,
|
1254 |
+
"normalized": false,
|
1255 |
+
"rstrip": false,
|
1256 |
+
"single_word": false,
|
1257 |
+
"special": true
|
1258 |
+
},
|
1259 |
+
"128157": {
|
1260 |
+
"content": "<|reserved_special_token_149|>",
|
1261 |
+
"lstrip": false,
|
1262 |
+
"normalized": false,
|
1263 |
+
"rstrip": false,
|
1264 |
+
"single_word": false,
|
1265 |
+
"special": true
|
1266 |
+
},
|
1267 |
+
"128158": {
|
1268 |
+
"content": "<|reserved_special_token_150|>",
|
1269 |
+
"lstrip": false,
|
1270 |
+
"normalized": false,
|
1271 |
+
"rstrip": false,
|
1272 |
+
"single_word": false,
|
1273 |
+
"special": true
|
1274 |
+
},
|
1275 |
+
"128159": {
|
1276 |
+
"content": "<|reserved_special_token_151|>",
|
1277 |
+
"lstrip": false,
|
1278 |
+
"normalized": false,
|
1279 |
+
"rstrip": false,
|
1280 |
+
"single_word": false,
|
1281 |
+
"special": true
|
1282 |
+
},
|
1283 |
+
"128160": {
|
1284 |
+
"content": "<|reserved_special_token_152|>",
|
1285 |
+
"lstrip": false,
|
1286 |
+
"normalized": false,
|
1287 |
+
"rstrip": false,
|
1288 |
+
"single_word": false,
|
1289 |
+
"special": true
|
1290 |
+
},
|
1291 |
+
"128161": {
|
1292 |
+
"content": "<|reserved_special_token_153|>",
|
1293 |
+
"lstrip": false,
|
1294 |
+
"normalized": false,
|
1295 |
+
"rstrip": false,
|
1296 |
+
"single_word": false,
|
1297 |
+
"special": true
|
1298 |
+
},
|
1299 |
+
"128162": {
|
1300 |
+
"content": "<|reserved_special_token_154|>",
|
1301 |
+
"lstrip": false,
|
1302 |
+
"normalized": false,
|
1303 |
+
"rstrip": false,
|
1304 |
+
"single_word": false,
|
1305 |
+
"special": true
|
1306 |
+
},
|
1307 |
+
"128163": {
|
1308 |
+
"content": "<|reserved_special_token_155|>",
|
1309 |
+
"lstrip": false,
|
1310 |
+
"normalized": false,
|
1311 |
+
"rstrip": false,
|
1312 |
+
"single_word": false,
|
1313 |
+
"special": true
|
1314 |
+
},
|
1315 |
+
"128164": {
|
1316 |
+
"content": "<|reserved_special_token_156|>",
|
1317 |
+
"lstrip": false,
|
1318 |
+
"normalized": false,
|
1319 |
+
"rstrip": false,
|
1320 |
+
"single_word": false,
|
1321 |
+
"special": true
|
1322 |
+
},
|
1323 |
+
"128165": {
|
1324 |
+
"content": "<|reserved_special_token_157|>",
|
1325 |
+
"lstrip": false,
|
1326 |
+
"normalized": false,
|
1327 |
+
"rstrip": false,
|
1328 |
+
"single_word": false,
|
1329 |
+
"special": true
|
1330 |
+
},
|
1331 |
+
"128166": {
|
1332 |
+
"content": "<|reserved_special_token_158|>",
|
1333 |
+
"lstrip": false,
|
1334 |
+
"normalized": false,
|
1335 |
+
"rstrip": false,
|
1336 |
+
"single_word": false,
|
1337 |
+
"special": true
|
1338 |
+
},
|
1339 |
+
"128167": {
|
1340 |
+
"content": "<|reserved_special_token_159|>",
|
1341 |
+
"lstrip": false,
|
1342 |
+
"normalized": false,
|
1343 |
+
"rstrip": false,
|
1344 |
+
"single_word": false,
|
1345 |
+
"special": true
|
1346 |
+
},
|
1347 |
+
"128168": {
|
1348 |
+
"content": "<|reserved_special_token_160|>",
|
1349 |
+
"lstrip": false,
|
1350 |
+
"normalized": false,
|
1351 |
+
"rstrip": false,
|
1352 |
+
"single_word": false,
|
1353 |
+
"special": true
|
1354 |
+
},
|
1355 |
+
"128169": {
|
1356 |
+
"content": "<|reserved_special_token_161|>",
|
1357 |
+
"lstrip": false,
|
1358 |
+
"normalized": false,
|
1359 |
+
"rstrip": false,
|
1360 |
+
"single_word": false,
|
1361 |
+
"special": true
|
1362 |
+
},
|
1363 |
+
"128170": {
|
1364 |
+
"content": "<|reserved_special_token_162|>",
|
1365 |
+
"lstrip": false,
|
1366 |
+
"normalized": false,
|
1367 |
+
"rstrip": false,
|
1368 |
+
"single_word": false,
|
1369 |
+
"special": true
|
1370 |
+
},
|
1371 |
+
"128171": {
|
1372 |
+
"content": "<|reserved_special_token_163|>",
|
1373 |
+
"lstrip": false,
|
1374 |
+
"normalized": false,
|
1375 |
+
"rstrip": false,
|
1376 |
+
"single_word": false,
|
1377 |
+
"special": true
|
1378 |
+
},
|
1379 |
+
"128172": {
|
1380 |
+
"content": "<|reserved_special_token_164|>",
|
1381 |
+
"lstrip": false,
|
1382 |
+
"normalized": false,
|
1383 |
+
"rstrip": false,
|
1384 |
+
"single_word": false,
|
1385 |
+
"special": true
|
1386 |
+
},
|
1387 |
+
"128173": {
|
1388 |
+
"content": "<|reserved_special_token_165|>",
|
1389 |
+
"lstrip": false,
|
1390 |
+
"normalized": false,
|
1391 |
+
"rstrip": false,
|
1392 |
+
"single_word": false,
|
1393 |
+
"special": true
|
1394 |
+
},
|
1395 |
+
"128174": {
|
1396 |
+
"content": "<|reserved_special_token_166|>",
|
1397 |
+
"lstrip": false,
|
1398 |
+
"normalized": false,
|
1399 |
+
"rstrip": false,
|
1400 |
+
"single_word": false,
|
1401 |
+
"special": true
|
1402 |
+
},
|
1403 |
+
"128175": {
|
1404 |
+
"content": "<|reserved_special_token_167|>",
|
1405 |
+
"lstrip": false,
|
1406 |
+
"normalized": false,
|
1407 |
+
"rstrip": false,
|
1408 |
+
"single_word": false,
|
1409 |
+
"special": true
|
1410 |
+
},
|
1411 |
+
"128176": {
|
1412 |
+
"content": "<|reserved_special_token_168|>",
|
1413 |
+
"lstrip": false,
|
1414 |
+
"normalized": false,
|
1415 |
+
"rstrip": false,
|
1416 |
+
"single_word": false,
|
1417 |
+
"special": true
|
1418 |
+
},
|
1419 |
+
"128177": {
|
1420 |
+
"content": "<|reserved_special_token_169|>",
|
1421 |
+
"lstrip": false,
|
1422 |
+
"normalized": false,
|
1423 |
+
"rstrip": false,
|
1424 |
+
"single_word": false,
|
1425 |
+
"special": true
|
1426 |
+
},
|
1427 |
+
"128178": {
|
1428 |
+
"content": "<|reserved_special_token_170|>",
|
1429 |
+
"lstrip": false,
|
1430 |
+
"normalized": false,
|
1431 |
+
"rstrip": false,
|
1432 |
+
"single_word": false,
|
1433 |
+
"special": true
|
1434 |
+
},
|
1435 |
+
"128179": {
|
1436 |
+
"content": "<|reserved_special_token_171|>",
|
1437 |
+
"lstrip": false,
|
1438 |
+
"normalized": false,
|
1439 |
+
"rstrip": false,
|
1440 |
+
"single_word": false,
|
1441 |
+
"special": true
|
1442 |
+
},
|
1443 |
+
"128180": {
|
1444 |
+
"content": "<|reserved_special_token_172|>",
|
1445 |
+
"lstrip": false,
|
1446 |
+
"normalized": false,
|
1447 |
+
"rstrip": false,
|
1448 |
+
"single_word": false,
|
1449 |
+
"special": true
|
1450 |
+
},
|
1451 |
+
"128181": {
|
1452 |
+
"content": "<|reserved_special_token_173|>",
|
1453 |
+
"lstrip": false,
|
1454 |
+
"normalized": false,
|
1455 |
+
"rstrip": false,
|
1456 |
+
"single_word": false,
|
1457 |
+
"special": true
|
1458 |
+
},
|
1459 |
+
"128182": {
|
1460 |
+
"content": "<|reserved_special_token_174|>",
|
1461 |
+
"lstrip": false,
|
1462 |
+
"normalized": false,
|
1463 |
+
"rstrip": false,
|
1464 |
+
"single_word": false,
|
1465 |
+
"special": true
|
1466 |
+
},
|
1467 |
+
"128183": {
|
1468 |
+
"content": "<|reserved_special_token_175|>",
|
1469 |
+
"lstrip": false,
|
1470 |
+
"normalized": false,
|
1471 |
+
"rstrip": false,
|
1472 |
+
"single_word": false,
|
1473 |
+
"special": true
|
1474 |
+
},
|
1475 |
+
"128184": {
|
1476 |
+
"content": "<|reserved_special_token_176|>",
|
1477 |
+
"lstrip": false,
|
1478 |
+
"normalized": false,
|
1479 |
+
"rstrip": false,
|
1480 |
+
"single_word": false,
|
1481 |
+
"special": true
|
1482 |
+
},
|
1483 |
+
"128185": {
|
1484 |
+
"content": "<|reserved_special_token_177|>",
|
1485 |
+
"lstrip": false,
|
1486 |
+
"normalized": false,
|
1487 |
+
"rstrip": false,
|
1488 |
+
"single_word": false,
|
1489 |
+
"special": true
|
1490 |
+
},
|
1491 |
+
"128186": {
|
1492 |
+
"content": "<|reserved_special_token_178|>",
|
1493 |
+
"lstrip": false,
|
1494 |
+
"normalized": false,
|
1495 |
+
"rstrip": false,
|
1496 |
+
"single_word": false,
|
1497 |
+
"special": true
|
1498 |
+
},
|
1499 |
+
"128187": {
|
1500 |
+
"content": "<|reserved_special_token_179|>",
|
1501 |
+
"lstrip": false,
|
1502 |
+
"normalized": false,
|
1503 |
+
"rstrip": false,
|
1504 |
+
"single_word": false,
|
1505 |
+
"special": true
|
1506 |
+
},
|
1507 |
+
"128188": {
|
1508 |
+
"content": "<|reserved_special_token_180|>",
|
1509 |
+
"lstrip": false,
|
1510 |
+
"normalized": false,
|
1511 |
+
"rstrip": false,
|
1512 |
+
"single_word": false,
|
1513 |
+
"special": true
|
1514 |
+
},
|
1515 |
+
"128189": {
|
1516 |
+
"content": "<|reserved_special_token_181|>",
|
1517 |
+
"lstrip": false,
|
1518 |
+
"normalized": false,
|
1519 |
+
"rstrip": false,
|
1520 |
+
"single_word": false,
|
1521 |
+
"special": true
|
1522 |
+
},
|
1523 |
+
"128190": {
|
1524 |
+
"content": "<|reserved_special_token_182|>",
|
1525 |
+
"lstrip": false,
|
1526 |
+
"normalized": false,
|
1527 |
+
"rstrip": false,
|
1528 |
+
"single_word": false,
|
1529 |
+
"special": true
|
1530 |
+
},
|
1531 |
+
"128191": {
|
1532 |
+
"content": "<|reserved_special_token_183|>",
|
1533 |
+
"lstrip": false,
|
1534 |
+
"normalized": false,
|
1535 |
+
"rstrip": false,
|
1536 |
+
"single_word": false,
|
1537 |
+
"special": true
|
1538 |
+
},
|
1539 |
+
"128192": {
|
1540 |
+
"content": "<|reserved_special_token_184|>",
|
1541 |
+
"lstrip": false,
|
1542 |
+
"normalized": false,
|
1543 |
+
"rstrip": false,
|
1544 |
+
"single_word": false,
|
1545 |
+
"special": true
|
1546 |
+
},
|
1547 |
+
"128193": {
|
1548 |
+
"content": "<|reserved_special_token_185|>",
|
1549 |
+
"lstrip": false,
|
1550 |
+
"normalized": false,
|
1551 |
+
"rstrip": false,
|
1552 |
+
"single_word": false,
|
1553 |
+
"special": true
|
1554 |
+
},
|
1555 |
+
"128194": {
|
1556 |
+
"content": "<|reserved_special_token_186|>",
|
1557 |
+
"lstrip": false,
|
1558 |
+
"normalized": false,
|
1559 |
+
"rstrip": false,
|
1560 |
+
"single_word": false,
|
1561 |
+
"special": true
|
1562 |
+
},
|
1563 |
+
"128195": {
|
1564 |
+
"content": "<|reserved_special_token_187|>",
|
1565 |
+
"lstrip": false,
|
1566 |
+
"normalized": false,
|
1567 |
+
"rstrip": false,
|
1568 |
+
"single_word": false,
|
1569 |
+
"special": true
|
1570 |
+
},
|
1571 |
+
"128196": {
|
1572 |
+
"content": "<|reserved_special_token_188|>",
|
1573 |
+
"lstrip": false,
|
1574 |
+
"normalized": false,
|
1575 |
+
"rstrip": false,
|
1576 |
+
"single_word": false,
|
1577 |
+
"special": true
|
1578 |
+
},
|
1579 |
+
"128197": {
|
1580 |
+
"content": "<|reserved_special_token_189|>",
|
1581 |
+
"lstrip": false,
|
1582 |
+
"normalized": false,
|
1583 |
+
"rstrip": false,
|
1584 |
+
"single_word": false,
|
1585 |
+
"special": true
|
1586 |
+
},
|
1587 |
+
"128198": {
|
1588 |
+
"content": "<|reserved_special_token_190|>",
|
1589 |
+
"lstrip": false,
|
1590 |
+
"normalized": false,
|
1591 |
+
"rstrip": false,
|
1592 |
+
"single_word": false,
|
1593 |
+
"special": true
|
1594 |
+
},
|
1595 |
+
"128199": {
|
1596 |
+
"content": "<|reserved_special_token_191|>",
|
1597 |
+
"lstrip": false,
|
1598 |
+
"normalized": false,
|
1599 |
+
"rstrip": false,
|
1600 |
+
"single_word": false,
|
1601 |
+
"special": true
|
1602 |
+
},
|
1603 |
+
"128200": {
|
1604 |
+
"content": "<|reserved_special_token_192|>",
|
1605 |
+
"lstrip": false,
|
1606 |
+
"normalized": false,
|
1607 |
+
"rstrip": false,
|
1608 |
+
"single_word": false,
|
1609 |
+
"special": true
|
1610 |
+
},
|
1611 |
+
"128201": {
|
1612 |
+
"content": "<|reserved_special_token_193|>",
|
1613 |
+
"lstrip": false,
|
1614 |
+
"normalized": false,
|
1615 |
+
"rstrip": false,
|
1616 |
+
"single_word": false,
|
1617 |
+
"special": true
|
1618 |
+
},
|
1619 |
+
"128202": {
|
1620 |
+
"content": "<|reserved_special_token_194|>",
|
1621 |
+
"lstrip": false,
|
1622 |
+
"normalized": false,
|
1623 |
+
"rstrip": false,
|
1624 |
+
"single_word": false,
|
1625 |
+
"special": true
|
1626 |
+
},
|
1627 |
+
"128203": {
|
1628 |
+
"content": "<|reserved_special_token_195|>",
|
1629 |
+
"lstrip": false,
|
1630 |
+
"normalized": false,
|
1631 |
+
"rstrip": false,
|
1632 |
+
"single_word": false,
|
1633 |
+
"special": true
|
1634 |
+
},
|
1635 |
+
"128204": {
|
1636 |
+
"content": "<|reserved_special_token_196|>",
|
1637 |
+
"lstrip": false,
|
1638 |
+
"normalized": false,
|
1639 |
+
"rstrip": false,
|
1640 |
+
"single_word": false,
|
1641 |
+
"special": true
|
1642 |
+
},
|
1643 |
+
"128205": {
|
1644 |
+
"content": "<|reserved_special_token_197|>",
|
1645 |
+
"lstrip": false,
|
1646 |
+
"normalized": false,
|
1647 |
+
"rstrip": false,
|
1648 |
+
"single_word": false,
|
1649 |
+
"special": true
|
1650 |
+
},
|
1651 |
+
"128206": {
|
1652 |
+
"content": "<|reserved_special_token_198|>",
|
1653 |
+
"lstrip": false,
|
1654 |
+
"normalized": false,
|
1655 |
+
"rstrip": false,
|
1656 |
+
"single_word": false,
|
1657 |
+
"special": true
|
1658 |
+
},
|
1659 |
+
"128207": {
|
1660 |
+
"content": "<|reserved_special_token_199|>",
|
1661 |
+
"lstrip": false,
|
1662 |
+
"normalized": false,
|
1663 |
+
"rstrip": false,
|
1664 |
+
"single_word": false,
|
1665 |
+
"special": true
|
1666 |
+
},
|
1667 |
+
"128208": {
|
1668 |
+
"content": "<|reserved_special_token_200|>",
|
1669 |
+
"lstrip": false,
|
1670 |
+
"normalized": false,
|
1671 |
+
"rstrip": false,
|
1672 |
+
"single_word": false,
|
1673 |
+
"special": true
|
1674 |
+
},
|
1675 |
+
"128209": {
|
1676 |
+
"content": "<|reserved_special_token_201|>",
|
1677 |
+
"lstrip": false,
|
1678 |
+
"normalized": false,
|
1679 |
+
"rstrip": false,
|
1680 |
+
"single_word": false,
|
1681 |
+
"special": true
|
1682 |
+
},
|
1683 |
+
"128210": {
|
1684 |
+
"content": "<|reserved_special_token_202|>",
|
1685 |
+
"lstrip": false,
|
1686 |
+
"normalized": false,
|
1687 |
+
"rstrip": false,
|
1688 |
+
"single_word": false,
|
1689 |
+
"special": true
|
1690 |
+
},
|
1691 |
+
"128211": {
|
1692 |
+
"content": "<|reserved_special_token_203|>",
|
1693 |
+
"lstrip": false,
|
1694 |
+
"normalized": false,
|
1695 |
+
"rstrip": false,
|
1696 |
+
"single_word": false,
|
1697 |
+
"special": true
|
1698 |
+
},
|
1699 |
+
"128212": {
|
1700 |
+
"content": "<|reserved_special_token_204|>",
|
1701 |
+
"lstrip": false,
|
1702 |
+
"normalized": false,
|
1703 |
+
"rstrip": false,
|
1704 |
+
"single_word": false,
|
1705 |
+
"special": true
|
1706 |
+
},
|
1707 |
+
"128213": {
|
1708 |
+
"content": "<|reserved_special_token_205|>",
|
1709 |
+
"lstrip": false,
|
1710 |
+
"normalized": false,
|
1711 |
+
"rstrip": false,
|
1712 |
+
"single_word": false,
|
1713 |
+
"special": true
|
1714 |
+
},
|
1715 |
+
"128214": {
|
1716 |
+
"content": "<|reserved_special_token_206|>",
|
1717 |
+
"lstrip": false,
|
1718 |
+
"normalized": false,
|
1719 |
+
"rstrip": false,
|
1720 |
+
"single_word": false,
|
1721 |
+
"special": true
|
1722 |
+
},
|
1723 |
+
"128215": {
|
1724 |
+
"content": "<|reserved_special_token_207|>",
|
1725 |
+
"lstrip": false,
|
1726 |
+
"normalized": false,
|
1727 |
+
"rstrip": false,
|
1728 |
+
"single_word": false,
|
1729 |
+
"special": true
|
1730 |
+
},
|
1731 |
+
"128216": {
|
1732 |
+
"content": "<|reserved_special_token_208|>",
|
1733 |
+
"lstrip": false,
|
1734 |
+
"normalized": false,
|
1735 |
+
"rstrip": false,
|
1736 |
+
"single_word": false,
|
1737 |
+
"special": true
|
1738 |
+
},
|
1739 |
+
"128217": {
|
1740 |
+
"content": "<|reserved_special_token_209|>",
|
1741 |
+
"lstrip": false,
|
1742 |
+
"normalized": false,
|
1743 |
+
"rstrip": false,
|
1744 |
+
"single_word": false,
|
1745 |
+
"special": true
|
1746 |
+
},
|
1747 |
+
"128218": {
|
1748 |
+
"content": "<|reserved_special_token_210|>",
|
1749 |
+
"lstrip": false,
|
1750 |
+
"normalized": false,
|
1751 |
+
"rstrip": false,
|
1752 |
+
"single_word": false,
|
1753 |
+
"special": true
|
1754 |
+
},
|
1755 |
+
"128219": {
|
1756 |
+
"content": "<|reserved_special_token_211|>",
|
1757 |
+
"lstrip": false,
|
1758 |
+
"normalized": false,
|
1759 |
+
"rstrip": false,
|
1760 |
+
"single_word": false,
|
1761 |
+
"special": true
|
1762 |
+
},
|
1763 |
+
"128220": {
|
1764 |
+
"content": "<|reserved_special_token_212|>",
|
1765 |
+
"lstrip": false,
|
1766 |
+
"normalized": false,
|
1767 |
+
"rstrip": false,
|
1768 |
+
"single_word": false,
|
1769 |
+
"special": true
|
1770 |
+
},
|
1771 |
+
"128221": {
|
1772 |
+
"content": "<|reserved_special_token_213|>",
|
1773 |
+
"lstrip": false,
|
1774 |
+
"normalized": false,
|
1775 |
+
"rstrip": false,
|
1776 |
+
"single_word": false,
|
1777 |
+
"special": true
|
1778 |
+
},
|
1779 |
+
"128222": {
|
1780 |
+
"content": "<|reserved_special_token_214|>",
|
1781 |
+
"lstrip": false,
|
1782 |
+
"normalized": false,
|
1783 |
+
"rstrip": false,
|
1784 |
+
"single_word": false,
|
1785 |
+
"special": true
|
1786 |
+
},
|
1787 |
+
"128223": {
|
1788 |
+
"content": "<|reserved_special_token_215|>",
|
1789 |
+
"lstrip": false,
|
1790 |
+
"normalized": false,
|
1791 |
+
"rstrip": false,
|
1792 |
+
"single_word": false,
|
1793 |
+
"special": true
|
1794 |
+
},
|
1795 |
+
"128224": {
|
1796 |
+
"content": "<|reserved_special_token_216|>",
|
1797 |
+
"lstrip": false,
|
1798 |
+
"normalized": false,
|
1799 |
+
"rstrip": false,
|
1800 |
+
"single_word": false,
|
1801 |
+
"special": true
|
1802 |
+
},
|
1803 |
+
"128225": {
|
1804 |
+
"content": "<|reserved_special_token_217|>",
|
1805 |
+
"lstrip": false,
|
1806 |
+
"normalized": false,
|
1807 |
+
"rstrip": false,
|
1808 |
+
"single_word": false,
|
1809 |
+
"special": true
|
1810 |
+
},
|
1811 |
+
"128226": {
|
1812 |
+
"content": "<|reserved_special_token_218|>",
|
1813 |
+
"lstrip": false,
|
1814 |
+
"normalized": false,
|
1815 |
+
"rstrip": false,
|
1816 |
+
"single_word": false,
|
1817 |
+
"special": true
|
1818 |
+
},
|
1819 |
+
"128227": {
|
1820 |
+
"content": "<|reserved_special_token_219|>",
|
1821 |
+
"lstrip": false,
|
1822 |
+
"normalized": false,
|
1823 |
+
"rstrip": false,
|
1824 |
+
"single_word": false,
|
1825 |
+
"special": true
|
1826 |
+
},
|
1827 |
+
"128228": {
|
1828 |
+
"content": "<|reserved_special_token_220|>",
|
1829 |
+
"lstrip": false,
|
1830 |
+
"normalized": false,
|
1831 |
+
"rstrip": false,
|
1832 |
+
"single_word": false,
|
1833 |
+
"special": true
|
1834 |
+
},
|
1835 |
+
"128229": {
|
1836 |
+
"content": "<|reserved_special_token_221|>",
|
1837 |
+
"lstrip": false,
|
1838 |
+
"normalized": false,
|
1839 |
+
"rstrip": false,
|
1840 |
+
"single_word": false,
|
1841 |
+
"special": true
|
1842 |
+
},
|
1843 |
+
"128230": {
|
1844 |
+
"content": "<|reserved_special_token_222|>",
|
1845 |
+
"lstrip": false,
|
1846 |
+
"normalized": false,
|
1847 |
+
"rstrip": false,
|
1848 |
+
"single_word": false,
|
1849 |
+
"special": true
|
1850 |
+
},
|
1851 |
+
"128231": {
|
1852 |
+
"content": "<|reserved_special_token_223|>",
|
1853 |
+
"lstrip": false,
|
1854 |
+
"normalized": false,
|
1855 |
+
"rstrip": false,
|
1856 |
+
"single_word": false,
|
1857 |
+
"special": true
|
1858 |
+
},
|
1859 |
+
"128232": {
|
1860 |
+
"content": "<|reserved_special_token_224|>",
|
1861 |
+
"lstrip": false,
|
1862 |
+
"normalized": false,
|
1863 |
+
"rstrip": false,
|
1864 |
+
"single_word": false,
|
1865 |
+
"special": true
|
1866 |
+
},
|
1867 |
+
"128233": {
|
1868 |
+
"content": "<|reserved_special_token_225|>",
|
1869 |
+
"lstrip": false,
|
1870 |
+
"normalized": false,
|
1871 |
+
"rstrip": false,
|
1872 |
+
"single_word": false,
|
1873 |
+
"special": true
|
1874 |
+
},
|
1875 |
+
"128234": {
|
1876 |
+
"content": "<|reserved_special_token_226|>",
|
1877 |
+
"lstrip": false,
|
1878 |
+
"normalized": false,
|
1879 |
+
"rstrip": false,
|
1880 |
+
"single_word": false,
|
1881 |
+
"special": true
|
1882 |
+
},
|
1883 |
+
"128235": {
|
1884 |
+
"content": "<|reserved_special_token_227|>",
|
1885 |
+
"lstrip": false,
|
1886 |
+
"normalized": false,
|
1887 |
+
"rstrip": false,
|
1888 |
+
"single_word": false,
|
1889 |
+
"special": true
|
1890 |
+
},
|
1891 |
+
"128236": {
|
1892 |
+
"content": "<|reserved_special_token_228|>",
|
1893 |
+
"lstrip": false,
|
1894 |
+
"normalized": false,
|
1895 |
+
"rstrip": false,
|
1896 |
+
"single_word": false,
|
1897 |
+
"special": true
|
1898 |
+
},
|
1899 |
+
"128237": {
|
1900 |
+
"content": "<|reserved_special_token_229|>",
|
1901 |
+
"lstrip": false,
|
1902 |
+
"normalized": false,
|
1903 |
+
"rstrip": false,
|
1904 |
+
"single_word": false,
|
1905 |
+
"special": true
|
1906 |
+
},
|
1907 |
+
"128238": {
|
1908 |
+
"content": "<|reserved_special_token_230|>",
|
1909 |
+
"lstrip": false,
|
1910 |
+
"normalized": false,
|
1911 |
+
"rstrip": false,
|
1912 |
+
"single_word": false,
|
1913 |
+
"special": true
|
1914 |
+
},
|
1915 |
+
"128239": {
|
1916 |
+
"content": "<|reserved_special_token_231|>",
|
1917 |
+
"lstrip": false,
|
1918 |
+
"normalized": false,
|
1919 |
+
"rstrip": false,
|
1920 |
+
"single_word": false,
|
1921 |
+
"special": true
|
1922 |
+
},
|
1923 |
+
"128240": {
|
1924 |
+
"content": "<|reserved_special_token_232|>",
|
1925 |
+
"lstrip": false,
|
1926 |
+
"normalized": false,
|
1927 |
+
"rstrip": false,
|
1928 |
+
"single_word": false,
|
1929 |
+
"special": true
|
1930 |
+
},
|
1931 |
+
"128241": {
|
1932 |
+
"content": "<|reserved_special_token_233|>",
|
1933 |
+
"lstrip": false,
|
1934 |
+
"normalized": false,
|
1935 |
+
"rstrip": false,
|
1936 |
+
"single_word": false,
|
1937 |
+
"special": true
|
1938 |
+
},
|
1939 |
+
"128242": {
|
1940 |
+
"content": "<|reserved_special_token_234|>",
|
1941 |
+
"lstrip": false,
|
1942 |
+
"normalized": false,
|
1943 |
+
"rstrip": false,
|
1944 |
+
"single_word": false,
|
1945 |
+
"special": true
|
1946 |
+
},
|
1947 |
+
"128243": {
|
1948 |
+
"content": "<|reserved_special_token_235|>",
|
1949 |
+
"lstrip": false,
|
1950 |
+
"normalized": false,
|
1951 |
+
"rstrip": false,
|
1952 |
+
"single_word": false,
|
1953 |
+
"special": true
|
1954 |
+
},
|
1955 |
+
"128244": {
|
1956 |
+
"content": "<|reserved_special_token_236|>",
|
1957 |
+
"lstrip": false,
|
1958 |
+
"normalized": false,
|
1959 |
+
"rstrip": false,
|
1960 |
+
"single_word": false,
|
1961 |
+
"special": true
|
1962 |
+
},
|
1963 |
+
"128245": {
|
1964 |
+
"content": "<|reserved_special_token_237|>",
|
1965 |
+
"lstrip": false,
|
1966 |
+
"normalized": false,
|
1967 |
+
"rstrip": false,
|
1968 |
+
"single_word": false,
|
1969 |
+
"special": true
|
1970 |
+
},
|
1971 |
+
"128246": {
|
1972 |
+
"content": "<|reserved_special_token_238|>",
|
1973 |
+
"lstrip": false,
|
1974 |
+
"normalized": false,
|
1975 |
+
"rstrip": false,
|
1976 |
+
"single_word": false,
|
1977 |
+
"special": true
|
1978 |
+
},
|
1979 |
+
"128247": {
|
1980 |
+
"content": "<|reserved_special_token_239|>",
|
1981 |
+
"lstrip": false,
|
1982 |
+
"normalized": false,
|
1983 |
+
"rstrip": false,
|
1984 |
+
"single_word": false,
|
1985 |
+
"special": true
|
1986 |
+
},
|
1987 |
+
"128248": {
|
1988 |
+
"content": "<|reserved_special_token_240|>",
|
1989 |
+
"lstrip": false,
|
1990 |
+
"normalized": false,
|
1991 |
+
"rstrip": false,
|
1992 |
+
"single_word": false,
|
1993 |
+
"special": true
|
1994 |
+
},
|
1995 |
+
"128249": {
|
1996 |
+
"content": "<|reserved_special_token_241|>",
|
1997 |
+
"lstrip": false,
|
1998 |
+
"normalized": false,
|
1999 |
+
"rstrip": false,
|
2000 |
+
"single_word": false,
|
2001 |
+
"special": true
|
2002 |
+
},
|
2003 |
+
"128250": {
|
2004 |
+
"content": "<|reserved_special_token_242|>",
|
2005 |
+
"lstrip": false,
|
2006 |
+
"normalized": false,
|
2007 |
+
"rstrip": false,
|
2008 |
+
"single_word": false,
|
2009 |
+
"special": true
|
2010 |
+
},
|
2011 |
+
"128251": {
|
2012 |
+
"content": "<|reserved_special_token_243|>",
|
2013 |
+
"lstrip": false,
|
2014 |
+
"normalized": false,
|
2015 |
+
"rstrip": false,
|
2016 |
+
"single_word": false,
|
2017 |
+
"special": true
|
2018 |
+
},
|
2019 |
+
"128252": {
|
2020 |
+
"content": "<|reserved_special_token_244|>",
|
2021 |
+
"lstrip": false,
|
2022 |
+
"normalized": false,
|
2023 |
+
"rstrip": false,
|
2024 |
+
"single_word": false,
|
2025 |
+
"special": true
|
2026 |
+
},
|
2027 |
+
"128253": {
|
2028 |
+
"content": "<|reserved_special_token_245|>",
|
2029 |
+
"lstrip": false,
|
2030 |
+
"normalized": false,
|
2031 |
+
"rstrip": false,
|
2032 |
+
"single_word": false,
|
2033 |
+
"special": true
|
2034 |
+
},
|
2035 |
+
"128254": {
|
2036 |
+
"content": "<|reserved_special_token_246|>",
|
2037 |
+
"lstrip": false,
|
2038 |
+
"normalized": false,
|
2039 |
+
"rstrip": false,
|
2040 |
+
"single_word": false,
|
2041 |
+
"special": true
|
2042 |
+
},
|
2043 |
+
"128255": {
|
2044 |
+
"content": "<|reserved_special_token_247|>",
|
2045 |
+
"lstrip": false,
|
2046 |
+
"normalized": false,
|
2047 |
+
"rstrip": false,
|
2048 |
+
"single_word": false,
|
2049 |
+
"special": true
|
2050 |
+
}
|
2051 |
+
},
|
2052 |
+
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
+
"extra_special_tokens": {},
|
2057 |
+
"model_input_names": [
|
2058 |
+
"input_ids",
|
2059 |
+
"attention_mask"
|
2060 |
+
],
|
2061 |
+
"model_max_length": 131072,
|
2062 |
+
"pad_token": "<|eot_id|>",
|
2063 |
+
"padding_side": "right",
|
2064 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
2065 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,3472 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": null,
|
3 |
+
"best_metric": null,
|
4 |
+
"best_model_checkpoint": null,
|
5 |
+
"epoch": 1.0,
|
6 |
+
"eval_steps": 490,
|
7 |
+
"global_step": 490,
|
8 |
+
"is_hyper_param_search": false,
|
9 |
+
"is_local_process_zero": true,
|
10 |
+
"is_world_process_zero": true,
|
11 |
+
"log_history": [
|
12 |
+
{
|
13 |
+
"epoch": 0.0020408163265306124,
|
14 |
+
"grad_norm": 1.5,
|
15 |
+
"learning_rate": 1e-05,
|
16 |
+
"loss": 2.6494,
|
17 |
+
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.004081632653061225,
|
21 |
+
"grad_norm": 1.4453125,
|
22 |
+
"learning_rate": 9.979591836734694e-06,
|
23 |
+
"loss": 2.6178,
|
24 |
+
"step": 2
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.006122448979591836,
|
28 |
+
"grad_norm": 1.3359375,
|
29 |
+
"learning_rate": 9.959183673469387e-06,
|
30 |
+
"loss": 2.5754,
|
31 |
+
"step": 3
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.00816326530612245,
|
35 |
+
"grad_norm": 1.265625,
|
36 |
+
"learning_rate": 9.938775510204082e-06,
|
37 |
+
"loss": 2.5329,
|
38 |
+
"step": 4
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.01020408163265306,
|
42 |
+
"grad_norm": 1.1328125,
|
43 |
+
"learning_rate": 9.918367346938776e-06,
|
44 |
+
"loss": 2.4144,
|
45 |
+
"step": 5
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.012244897959183673,
|
49 |
+
"grad_norm": 1.0546875,
|
50 |
+
"learning_rate": 9.89795918367347e-06,
|
51 |
+
"loss": 2.3706,
|
52 |
+
"step": 6
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 0.014285714285714285,
|
56 |
+
"grad_norm": 0.9921875,
|
57 |
+
"learning_rate": 9.877551020408164e-06,
|
58 |
+
"loss": 2.3567,
|
59 |
+
"step": 7
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.0163265306122449,
|
63 |
+
"grad_norm": 0.953125,
|
64 |
+
"learning_rate": 9.857142857142859e-06,
|
65 |
+
"loss": 2.3129,
|
66 |
+
"step": 8
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.018367346938775512,
|
70 |
+
"grad_norm": 0.87890625,
|
71 |
+
"learning_rate": 9.836734693877552e-06,
|
72 |
+
"loss": 2.2201,
|
73 |
+
"step": 9
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 0.02040816326530612,
|
77 |
+
"grad_norm": 0.8515625,
|
78 |
+
"learning_rate": 9.816326530612245e-06,
|
79 |
+
"loss": 2.1547,
|
80 |
+
"step": 10
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.022448979591836733,
|
84 |
+
"grad_norm": 0.84375,
|
85 |
+
"learning_rate": 9.795918367346939e-06,
|
86 |
+
"loss": 2.1029,
|
87 |
+
"step": 11
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.024489795918367346,
|
91 |
+
"grad_norm": 0.83984375,
|
92 |
+
"learning_rate": 9.775510204081634e-06,
|
93 |
+
"loss": 2.0033,
|
94 |
+
"step": 12
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 0.026530612244897958,
|
98 |
+
"grad_norm": 0.8984375,
|
99 |
+
"learning_rate": 9.755102040816327e-06,
|
100 |
+
"loss": 1.9678,
|
101 |
+
"step": 13
|
102 |
+
},
|
103 |
+
{
|
104 |
+
"epoch": 0.02857142857142857,
|
105 |
+
"grad_norm": 0.91015625,
|
106 |
+
"learning_rate": 9.734693877551022e-06,
|
107 |
+
"loss": 1.9049,
|
108 |
+
"step": 14
|
109 |
+
},
|
110 |
+
{
|
111 |
+
"epoch": 0.030612244897959183,
|
112 |
+
"grad_norm": 0.90234375,
|
113 |
+
"learning_rate": 9.714285714285715e-06,
|
114 |
+
"loss": 1.8092,
|
115 |
+
"step": 15
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 0.0326530612244898,
|
119 |
+
"grad_norm": 0.890625,
|
120 |
+
"learning_rate": 9.693877551020408e-06,
|
121 |
+
"loss": 1.7489,
|
122 |
+
"step": 16
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.03469387755102041,
|
126 |
+
"grad_norm": 1.0078125,
|
127 |
+
"learning_rate": 9.673469387755103e-06,
|
128 |
+
"loss": 1.6506,
|
129 |
+
"step": 17
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.036734693877551024,
|
133 |
+
"grad_norm": 1.0859375,
|
134 |
+
"learning_rate": 9.653061224489797e-06,
|
135 |
+
"loss": 1.5929,
|
136 |
+
"step": 18
|
137 |
+
},
|
138 |
+
{
|
139 |
+
"epoch": 0.03877551020408163,
|
140 |
+
"grad_norm": 1.015625,
|
141 |
+
"learning_rate": 9.63265306122449e-06,
|
142 |
+
"loss": 1.5118,
|
143 |
+
"step": 19
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.04081632653061224,
|
147 |
+
"grad_norm": 1.0625,
|
148 |
+
"learning_rate": 9.612244897959185e-06,
|
149 |
+
"loss": 1.4574,
|
150 |
+
"step": 20
|
151 |
+
},
|
152 |
+
{
|
153 |
+
"epoch": 0.04285714285714286,
|
154 |
+
"grad_norm": 1.4921875,
|
155 |
+
"learning_rate": 9.591836734693878e-06,
|
156 |
+
"loss": 1.3716,
|
157 |
+
"step": 21
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.044897959183673466,
|
161 |
+
"grad_norm": 0.98828125,
|
162 |
+
"learning_rate": 9.571428571428573e-06,
|
163 |
+
"loss": 1.312,
|
164 |
+
"step": 22
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.04693877551020408,
|
168 |
+
"grad_norm": 1.0703125,
|
169 |
+
"learning_rate": 9.551020408163266e-06,
|
170 |
+
"loss": 1.2485,
|
171 |
+
"step": 23
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.04897959183673469,
|
175 |
+
"grad_norm": 1.140625,
|
176 |
+
"learning_rate": 9.53061224489796e-06,
|
177 |
+
"loss": 1.1937,
|
178 |
+
"step": 24
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.05102040816326531,
|
182 |
+
"grad_norm": 0.96875,
|
183 |
+
"learning_rate": 9.510204081632653e-06,
|
184 |
+
"loss": 1.1141,
|
185 |
+
"step": 25
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.053061224489795916,
|
189 |
+
"grad_norm": 0.9140625,
|
190 |
+
"learning_rate": 9.489795918367348e-06,
|
191 |
+
"loss": 1.0344,
|
192 |
+
"step": 26
|
193 |
+
},
|
194 |
+
{
|
195 |
+
"epoch": 0.05510204081632653,
|
196 |
+
"grad_norm": 0.91796875,
|
197 |
+
"learning_rate": 9.469387755102041e-06,
|
198 |
+
"loss": 0.9953,
|
199 |
+
"step": 27
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 0.05714285714285714,
|
203 |
+
"grad_norm": 0.796875,
|
204 |
+
"learning_rate": 9.448979591836736e-06,
|
205 |
+
"loss": 0.9416,
|
206 |
+
"step": 28
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.05918367346938776,
|
210 |
+
"grad_norm": 0.71484375,
|
211 |
+
"learning_rate": 9.42857142857143e-06,
|
212 |
+
"loss": 0.8887,
|
213 |
+
"step": 29
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.061224489795918366,
|
217 |
+
"grad_norm": 0.640625,
|
218 |
+
"learning_rate": 9.408163265306123e-06,
|
219 |
+
"loss": 0.8538,
|
220 |
+
"step": 30
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.06326530612244897,
|
224 |
+
"grad_norm": 0.55078125,
|
225 |
+
"learning_rate": 9.387755102040818e-06,
|
226 |
+
"loss": 0.8325,
|
227 |
+
"step": 31
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.0653061224489796,
|
231 |
+
"grad_norm": 0.4453125,
|
232 |
+
"learning_rate": 9.367346938775511e-06,
|
233 |
+
"loss": 0.8091,
|
234 |
+
"step": 32
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.0673469387755102,
|
238 |
+
"grad_norm": 0.37890625,
|
239 |
+
"learning_rate": 9.346938775510204e-06,
|
240 |
+
"loss": 0.7762,
|
241 |
+
"step": 33
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.06938775510204082,
|
245 |
+
"grad_norm": 0.353515625,
|
246 |
+
"learning_rate": 9.326530612244898e-06,
|
247 |
+
"loss": 0.7914,
|
248 |
+
"step": 34
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.07142857142857142,
|
252 |
+
"grad_norm": 0.328125,
|
253 |
+
"learning_rate": 9.306122448979593e-06,
|
254 |
+
"loss": 0.771,
|
255 |
+
"step": 35
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.07346938775510205,
|
259 |
+
"grad_norm": 0.275390625,
|
260 |
+
"learning_rate": 9.285714285714288e-06,
|
261 |
+
"loss": 0.7532,
|
262 |
+
"step": 36
|
263 |
+
},
|
264 |
+
{
|
265 |
+
"epoch": 0.07551020408163266,
|
266 |
+
"grad_norm": 0.2373046875,
|
267 |
+
"learning_rate": 9.26530612244898e-06,
|
268 |
+
"loss": 0.7528,
|
269 |
+
"step": 37
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 0.07755102040816327,
|
273 |
+
"grad_norm": 0.228515625,
|
274 |
+
"learning_rate": 9.244897959183674e-06,
|
275 |
+
"loss": 0.7559,
|
276 |
+
"step": 38
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 0.07959183673469387,
|
280 |
+
"grad_norm": 0.2197265625,
|
281 |
+
"learning_rate": 9.224489795918367e-06,
|
282 |
+
"loss": 0.7516,
|
283 |
+
"step": 39
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.08163265306122448,
|
287 |
+
"grad_norm": 0.2109375,
|
288 |
+
"learning_rate": 9.204081632653062e-06,
|
289 |
+
"loss": 0.7577,
|
290 |
+
"step": 40
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.0836734693877551,
|
294 |
+
"grad_norm": 0.2099609375,
|
295 |
+
"learning_rate": 9.183673469387756e-06,
|
296 |
+
"loss": 0.7302,
|
297 |
+
"step": 41
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.08571428571428572,
|
301 |
+
"grad_norm": 0.2177734375,
|
302 |
+
"learning_rate": 9.163265306122449e-06,
|
303 |
+
"loss": 0.7402,
|
304 |
+
"step": 42
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.08775510204081632,
|
308 |
+
"grad_norm": 0.208984375,
|
309 |
+
"learning_rate": 9.142857142857144e-06,
|
310 |
+
"loss": 0.747,
|
311 |
+
"step": 43
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.08979591836734693,
|
315 |
+
"grad_norm": 0.2099609375,
|
316 |
+
"learning_rate": 9.122448979591837e-06,
|
317 |
+
"loss": 0.7224,
|
318 |
+
"step": 44
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 0.09183673469387756,
|
322 |
+
"grad_norm": 0.2119140625,
|
323 |
+
"learning_rate": 9.102040816326532e-06,
|
324 |
+
"loss": 0.708,
|
325 |
+
"step": 45
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.09387755102040816,
|
329 |
+
"grad_norm": 0.2138671875,
|
330 |
+
"learning_rate": 9.081632653061225e-06,
|
331 |
+
"loss": 0.7086,
|
332 |
+
"step": 46
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 0.09591836734693877,
|
336 |
+
"grad_norm": 0.2080078125,
|
337 |
+
"learning_rate": 9.061224489795919e-06,
|
338 |
+
"loss": 0.708,
|
339 |
+
"step": 47
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.09795918367346938,
|
343 |
+
"grad_norm": 0.2001953125,
|
344 |
+
"learning_rate": 9.040816326530612e-06,
|
345 |
+
"loss": 0.7164,
|
346 |
+
"step": 48
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.1,
|
350 |
+
"grad_norm": 0.1953125,
|
351 |
+
"learning_rate": 9.020408163265307e-06,
|
352 |
+
"loss": 0.687,
|
353 |
+
"step": 49
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 0.10204081632653061,
|
357 |
+
"grad_norm": 0.181640625,
|
358 |
+
"learning_rate": 9e-06,
|
359 |
+
"loss": 0.6805,
|
360 |
+
"step": 50
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 0.10408163265306122,
|
364 |
+
"grad_norm": 0.1767578125,
|
365 |
+
"learning_rate": 8.979591836734695e-06,
|
366 |
+
"loss": 0.7123,
|
367 |
+
"step": 51
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.10612244897959183,
|
371 |
+
"grad_norm": 0.169921875,
|
372 |
+
"learning_rate": 8.959183673469388e-06,
|
373 |
+
"loss": 0.6835,
|
374 |
+
"step": 52
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 0.10816326530612246,
|
378 |
+
"grad_norm": 0.1728515625,
|
379 |
+
"learning_rate": 8.938775510204082e-06,
|
380 |
+
"loss": 0.6827,
|
381 |
+
"step": 53
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.11020408163265306,
|
385 |
+
"grad_norm": 0.166015625,
|
386 |
+
"learning_rate": 8.918367346938777e-06,
|
387 |
+
"loss": 0.6785,
|
388 |
+
"step": 54
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 0.11224489795918367,
|
392 |
+
"grad_norm": 0.1689453125,
|
393 |
+
"learning_rate": 8.89795918367347e-06,
|
394 |
+
"loss": 0.6458,
|
395 |
+
"step": 55
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 0.11428571428571428,
|
399 |
+
"grad_norm": 0.1689453125,
|
400 |
+
"learning_rate": 8.877551020408163e-06,
|
401 |
+
"loss": 0.6576,
|
402 |
+
"step": 56
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.11632653061224489,
|
406 |
+
"grad_norm": 0.1806640625,
|
407 |
+
"learning_rate": 8.857142857142858e-06,
|
408 |
+
"loss": 0.683,
|
409 |
+
"step": 57
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 0.11836734693877551,
|
413 |
+
"grad_norm": 0.1572265625,
|
414 |
+
"learning_rate": 8.836734693877552e-06,
|
415 |
+
"loss": 0.6673,
|
416 |
+
"step": 58
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 0.12040816326530612,
|
420 |
+
"grad_norm": 0.1572265625,
|
421 |
+
"learning_rate": 8.816326530612247e-06,
|
422 |
+
"loss": 0.6625,
|
423 |
+
"step": 59
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.12244897959183673,
|
427 |
+
"grad_norm": 0.1591796875,
|
428 |
+
"learning_rate": 8.79591836734694e-06,
|
429 |
+
"loss": 0.6855,
|
430 |
+
"step": 60
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 0.12448979591836734,
|
434 |
+
"grad_norm": 0.158203125,
|
435 |
+
"learning_rate": 8.775510204081633e-06,
|
436 |
+
"loss": 0.6549,
|
437 |
+
"step": 61
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 0.12653061224489795,
|
441 |
+
"grad_norm": 0.15234375,
|
442 |
+
"learning_rate": 8.755102040816326e-06,
|
443 |
+
"loss": 0.6641,
|
444 |
+
"step": 62
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 0.12857142857142856,
|
448 |
+
"grad_norm": 0.1552734375,
|
449 |
+
"learning_rate": 8.734693877551021e-06,
|
450 |
+
"loss": 0.6467,
|
451 |
+
"step": 63
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 0.1306122448979592,
|
455 |
+
"grad_norm": 0.1494140625,
|
456 |
+
"learning_rate": 8.714285714285715e-06,
|
457 |
+
"loss": 0.6862,
|
458 |
+
"step": 64
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.1326530612244898,
|
462 |
+
"grad_norm": 0.1484375,
|
463 |
+
"learning_rate": 8.69387755102041e-06,
|
464 |
+
"loss": 0.6346,
|
465 |
+
"step": 65
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.1346938775510204,
|
469 |
+
"grad_norm": 0.1484375,
|
470 |
+
"learning_rate": 8.673469387755103e-06,
|
471 |
+
"loss": 0.6471,
|
472 |
+
"step": 66
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 0.13673469387755102,
|
476 |
+
"grad_norm": 0.1455078125,
|
477 |
+
"learning_rate": 8.653061224489798e-06,
|
478 |
+
"loss": 0.6432,
|
479 |
+
"step": 67
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 0.13877551020408163,
|
483 |
+
"grad_norm": 0.14453125,
|
484 |
+
"learning_rate": 8.632653061224491e-06,
|
485 |
+
"loss": 0.6388,
|
486 |
+
"step": 68
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 0.14081632653061224,
|
490 |
+
"grad_norm": 0.171875,
|
491 |
+
"learning_rate": 8.612244897959184e-06,
|
492 |
+
"loss": 0.6304,
|
493 |
+
"step": 69
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 0.14285714285714285,
|
497 |
+
"grad_norm": 0.14453125,
|
498 |
+
"learning_rate": 8.591836734693878e-06,
|
499 |
+
"loss": 0.6387,
|
500 |
+
"step": 70
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 0.14489795918367346,
|
504 |
+
"grad_norm": 0.1669921875,
|
505 |
+
"learning_rate": 8.571428571428571e-06,
|
506 |
+
"loss": 0.619,
|
507 |
+
"step": 71
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.1469387755102041,
|
511 |
+
"grad_norm": 0.1435546875,
|
512 |
+
"learning_rate": 8.551020408163266e-06,
|
513 |
+
"loss": 0.632,
|
514 |
+
"step": 72
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.1489795918367347,
|
518 |
+
"grad_norm": 0.13671875,
|
519 |
+
"learning_rate": 8.530612244897961e-06,
|
520 |
+
"loss": 0.639,
|
521 |
+
"step": 73
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.1510204081632653,
|
525 |
+
"grad_norm": 0.1455078125,
|
526 |
+
"learning_rate": 8.510204081632654e-06,
|
527 |
+
"loss": 0.6303,
|
528 |
+
"step": 74
|
529 |
+
},
|
530 |
+
{
|
531 |
+
"epoch": 0.15306122448979592,
|
532 |
+
"grad_norm": 0.1396484375,
|
533 |
+
"learning_rate": 8.489795918367347e-06,
|
534 |
+
"loss": 0.6089,
|
535 |
+
"step": 75
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 0.15510204081632653,
|
539 |
+
"grad_norm": 0.1328125,
|
540 |
+
"learning_rate": 8.469387755102042e-06,
|
541 |
+
"loss": 0.632,
|
542 |
+
"step": 76
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 0.15714285714285714,
|
546 |
+
"grad_norm": 0.1650390625,
|
547 |
+
"learning_rate": 8.448979591836736e-06,
|
548 |
+
"loss": 0.6173,
|
549 |
+
"step": 77
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.15918367346938775,
|
553 |
+
"grad_norm": 0.13671875,
|
554 |
+
"learning_rate": 8.428571428571429e-06,
|
555 |
+
"loss": 0.6216,
|
556 |
+
"step": 78
|
557 |
+
},
|
558 |
+
{
|
559 |
+
"epoch": 0.16122448979591836,
|
560 |
+
"grad_norm": 0.1435546875,
|
561 |
+
"learning_rate": 8.408163265306122e-06,
|
562 |
+
"loss": 0.6084,
|
563 |
+
"step": 79
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.16326530612244897,
|
567 |
+
"grad_norm": 0.1376953125,
|
568 |
+
"learning_rate": 8.387755102040817e-06,
|
569 |
+
"loss": 0.6393,
|
570 |
+
"step": 80
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.1653061224489796,
|
574 |
+
"grad_norm": 0.154296875,
|
575 |
+
"learning_rate": 8.36734693877551e-06,
|
576 |
+
"loss": 0.6229,
|
577 |
+
"step": 81
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 0.1673469387755102,
|
581 |
+
"grad_norm": 0.13671875,
|
582 |
+
"learning_rate": 8.346938775510205e-06,
|
583 |
+
"loss": 0.5973,
|
584 |
+
"step": 82
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 0.16938775510204082,
|
588 |
+
"grad_norm": 0.138671875,
|
589 |
+
"learning_rate": 8.326530612244899e-06,
|
590 |
+
"loss": 0.603,
|
591 |
+
"step": 83
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.17142857142857143,
|
595 |
+
"grad_norm": 0.134765625,
|
596 |
+
"learning_rate": 8.306122448979592e-06,
|
597 |
+
"loss": 0.5991,
|
598 |
+
"step": 84
|
599 |
+
},
|
600 |
+
{
|
601 |
+
"epoch": 0.17346938775510204,
|
602 |
+
"grad_norm": 0.1376953125,
|
603 |
+
"learning_rate": 8.285714285714287e-06,
|
604 |
+
"loss": 0.6006,
|
605 |
+
"step": 85
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.17551020408163265,
|
609 |
+
"grad_norm": 0.134765625,
|
610 |
+
"learning_rate": 8.26530612244898e-06,
|
611 |
+
"loss": 0.5926,
|
612 |
+
"step": 86
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.17755102040816326,
|
616 |
+
"grad_norm": 0.134765625,
|
617 |
+
"learning_rate": 8.244897959183674e-06,
|
618 |
+
"loss": 0.6015,
|
619 |
+
"step": 87
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.17959183673469387,
|
623 |
+
"grad_norm": 0.1318359375,
|
624 |
+
"learning_rate": 8.224489795918369e-06,
|
625 |
+
"loss": 0.6046,
|
626 |
+
"step": 88
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.1816326530612245,
|
630 |
+
"grad_norm": 0.1416015625,
|
631 |
+
"learning_rate": 8.204081632653062e-06,
|
632 |
+
"loss": 0.5818,
|
633 |
+
"step": 89
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.1836734693877551,
|
637 |
+
"grad_norm": 0.1455078125,
|
638 |
+
"learning_rate": 8.183673469387757e-06,
|
639 |
+
"loss": 0.596,
|
640 |
+
"step": 90
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.18571428571428572,
|
644 |
+
"grad_norm": 0.150390625,
|
645 |
+
"learning_rate": 8.16326530612245e-06,
|
646 |
+
"loss": 0.5836,
|
647 |
+
"step": 91
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.18775510204081633,
|
651 |
+
"grad_norm": 0.1708984375,
|
652 |
+
"learning_rate": 8.142857142857143e-06,
|
653 |
+
"loss": 0.5922,
|
654 |
+
"step": 92
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.18979591836734694,
|
658 |
+
"grad_norm": 0.15625,
|
659 |
+
"learning_rate": 8.122448979591837e-06,
|
660 |
+
"loss": 0.5953,
|
661 |
+
"step": 93
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.19183673469387755,
|
665 |
+
"grad_norm": 0.193359375,
|
666 |
+
"learning_rate": 8.102040816326532e-06,
|
667 |
+
"loss": 0.5834,
|
668 |
+
"step": 94
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.19387755102040816,
|
672 |
+
"grad_norm": 0.1376953125,
|
673 |
+
"learning_rate": 8.081632653061225e-06,
|
674 |
+
"loss": 0.5851,
|
675 |
+
"step": 95
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.19591836734693877,
|
679 |
+
"grad_norm": 0.150390625,
|
680 |
+
"learning_rate": 8.06122448979592e-06,
|
681 |
+
"loss": 0.5788,
|
682 |
+
"step": 96
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.19795918367346937,
|
686 |
+
"grad_norm": 0.1298828125,
|
687 |
+
"learning_rate": 8.040816326530613e-06,
|
688 |
+
"loss": 0.5934,
|
689 |
+
"step": 97
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.2,
|
693 |
+
"grad_norm": 0.1396484375,
|
694 |
+
"learning_rate": 8.020408163265306e-06,
|
695 |
+
"loss": 0.5877,
|
696 |
+
"step": 98
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.20204081632653062,
|
700 |
+
"grad_norm": 0.140625,
|
701 |
+
"learning_rate": 8.000000000000001e-06,
|
702 |
+
"loss": 0.584,
|
703 |
+
"step": 99
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.20408163265306123,
|
707 |
+
"grad_norm": 0.150390625,
|
708 |
+
"learning_rate": 7.979591836734695e-06,
|
709 |
+
"loss": 0.5865,
|
710 |
+
"step": 100
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.20612244897959184,
|
714 |
+
"grad_norm": 0.1259765625,
|
715 |
+
"learning_rate": 7.959183673469388e-06,
|
716 |
+
"loss": 0.5707,
|
717 |
+
"step": 101
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.20816326530612245,
|
721 |
+
"grad_norm": 0.146484375,
|
722 |
+
"learning_rate": 7.938775510204081e-06,
|
723 |
+
"loss": 0.5673,
|
724 |
+
"step": 102
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.21020408163265306,
|
728 |
+
"grad_norm": 0.1572265625,
|
729 |
+
"learning_rate": 7.918367346938776e-06,
|
730 |
+
"loss": 0.5679,
|
731 |
+
"step": 103
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.21224489795918366,
|
735 |
+
"grad_norm": 0.1220703125,
|
736 |
+
"learning_rate": 7.897959183673471e-06,
|
737 |
+
"loss": 0.5694,
|
738 |
+
"step": 104
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.21428571428571427,
|
742 |
+
"grad_norm": 0.1533203125,
|
743 |
+
"learning_rate": 7.877551020408164e-06,
|
744 |
+
"loss": 0.5688,
|
745 |
+
"step": 105
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.2163265306122449,
|
749 |
+
"grad_norm": 0.1650390625,
|
750 |
+
"learning_rate": 7.857142857142858e-06,
|
751 |
+
"loss": 0.5776,
|
752 |
+
"step": 106
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 0.21836734693877552,
|
756 |
+
"grad_norm": 0.146484375,
|
757 |
+
"learning_rate": 7.836734693877551e-06,
|
758 |
+
"loss": 0.5485,
|
759 |
+
"step": 107
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.22040816326530613,
|
763 |
+
"grad_norm": 0.146484375,
|
764 |
+
"learning_rate": 7.816326530612246e-06,
|
765 |
+
"loss": 0.5635,
|
766 |
+
"step": 108
|
767 |
+
},
|
768 |
+
{
|
769 |
+
"epoch": 0.22244897959183674,
|
770 |
+
"grad_norm": 0.16796875,
|
771 |
+
"learning_rate": 7.79591836734694e-06,
|
772 |
+
"loss": 0.5786,
|
773 |
+
"step": 109
|
774 |
+
},
|
775 |
+
{
|
776 |
+
"epoch": 0.22448979591836735,
|
777 |
+
"grad_norm": 0.177734375,
|
778 |
+
"learning_rate": 7.775510204081632e-06,
|
779 |
+
"loss": 0.5715,
|
780 |
+
"step": 110
|
781 |
+
},
|
782 |
+
{
|
783 |
+
"epoch": 0.22653061224489796,
|
784 |
+
"grad_norm": 0.11865234375,
|
785 |
+
"learning_rate": 7.755102040816327e-06,
|
786 |
+
"loss": 0.5604,
|
787 |
+
"step": 111
|
788 |
+
},
|
789 |
+
{
|
790 |
+
"epoch": 0.22857142857142856,
|
791 |
+
"grad_norm": 0.1650390625,
|
792 |
+
"learning_rate": 7.73469387755102e-06,
|
793 |
+
"loss": 0.5651,
|
794 |
+
"step": 112
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.23061224489795917,
|
798 |
+
"grad_norm": 0.1494140625,
|
799 |
+
"learning_rate": 7.714285714285716e-06,
|
800 |
+
"loss": 0.561,
|
801 |
+
"step": 113
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.23265306122448978,
|
805 |
+
"grad_norm": 0.203125,
|
806 |
+
"learning_rate": 7.693877551020409e-06,
|
807 |
+
"loss": 0.5447,
|
808 |
+
"step": 114
|
809 |
+
},
|
810 |
+
{
|
811 |
+
"epoch": 0.23469387755102042,
|
812 |
+
"grad_norm": 0.126953125,
|
813 |
+
"learning_rate": 7.673469387755102e-06,
|
814 |
+
"loss": 0.5747,
|
815 |
+
"step": 115
|
816 |
+
},
|
817 |
+
{
|
818 |
+
"epoch": 0.23673469387755103,
|
819 |
+
"grad_norm": 0.1455078125,
|
820 |
+
"learning_rate": 7.653061224489796e-06,
|
821 |
+
"loss": 0.5602,
|
822 |
+
"step": 116
|
823 |
+
},
|
824 |
+
{
|
825 |
+
"epoch": 0.23877551020408164,
|
826 |
+
"grad_norm": 0.13671875,
|
827 |
+
"learning_rate": 7.63265306122449e-06,
|
828 |
+
"loss": 0.5597,
|
829 |
+
"step": 117
|
830 |
+
},
|
831 |
+
{
|
832 |
+
"epoch": 0.24081632653061225,
|
833 |
+
"grad_norm": 0.1435546875,
|
834 |
+
"learning_rate": 7.612244897959185e-06,
|
835 |
+
"loss": 0.558,
|
836 |
+
"step": 118
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 0.24285714285714285,
|
840 |
+
"grad_norm": 0.1220703125,
|
841 |
+
"learning_rate": 7.591836734693878e-06,
|
842 |
+
"loss": 0.5376,
|
843 |
+
"step": 119
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.24489795918367346,
|
847 |
+
"grad_norm": 0.1279296875,
|
848 |
+
"learning_rate": 7.571428571428572e-06,
|
849 |
+
"loss": 0.5456,
|
850 |
+
"step": 120
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.24693877551020407,
|
854 |
+
"grad_norm": 0.1279296875,
|
855 |
+
"learning_rate": 7.551020408163265e-06,
|
856 |
+
"loss": 0.5565,
|
857 |
+
"step": 121
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 0.24897959183673468,
|
861 |
+
"grad_norm": 0.1552734375,
|
862 |
+
"learning_rate": 7.53061224489796e-06,
|
863 |
+
"loss": 0.5443,
|
864 |
+
"step": 122
|
865 |
+
},
|
866 |
+
{
|
867 |
+
"epoch": 0.2510204081632653,
|
868 |
+
"grad_norm": 0.1474609375,
|
869 |
+
"learning_rate": 7.5102040816326536e-06,
|
870 |
+
"loss": 0.5448,
|
871 |
+
"step": 123
|
872 |
+
},
|
873 |
+
{
|
874 |
+
"epoch": 0.2530612244897959,
|
875 |
+
"grad_norm": 0.1416015625,
|
876 |
+
"learning_rate": 7.489795918367348e-06,
|
877 |
+
"loss": 0.5319,
|
878 |
+
"step": 124
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 0.25510204081632654,
|
882 |
+
"grad_norm": 0.1513671875,
|
883 |
+
"learning_rate": 7.469387755102041e-06,
|
884 |
+
"loss": 0.5518,
|
885 |
+
"step": 125
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.2571428571428571,
|
889 |
+
"grad_norm": 0.1328125,
|
890 |
+
"learning_rate": 7.448979591836736e-06,
|
891 |
+
"loss": 0.5682,
|
892 |
+
"step": 126
|
893 |
+
},
|
894 |
+
{
|
895 |
+
"epoch": 0.25918367346938775,
|
896 |
+
"grad_norm": 0.1279296875,
|
897 |
+
"learning_rate": 7.428571428571429e-06,
|
898 |
+
"loss": 0.5433,
|
899 |
+
"step": 127
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 0.2612244897959184,
|
903 |
+
"grad_norm": 0.12255859375,
|
904 |
+
"learning_rate": 7.408163265306123e-06,
|
905 |
+
"loss": 0.5391,
|
906 |
+
"step": 128
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.26326530612244897,
|
910 |
+
"grad_norm": 0.130859375,
|
911 |
+
"learning_rate": 7.387755102040817e-06,
|
912 |
+
"loss": 0.5539,
|
913 |
+
"step": 129
|
914 |
+
},
|
915 |
+
{
|
916 |
+
"epoch": 0.2653061224489796,
|
917 |
+
"grad_norm": 0.130859375,
|
918 |
+
"learning_rate": 7.367346938775511e-06,
|
919 |
+
"loss": 0.5608,
|
920 |
+
"step": 130
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 0.2673469387755102,
|
924 |
+
"grad_norm": 0.126953125,
|
925 |
+
"learning_rate": 7.346938775510205e-06,
|
926 |
+
"loss": 0.5342,
|
927 |
+
"step": 131
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.2693877551020408,
|
931 |
+
"grad_norm": 0.1630859375,
|
932 |
+
"learning_rate": 7.326530612244899e-06,
|
933 |
+
"loss": 0.5549,
|
934 |
+
"step": 132
|
935 |
+
},
|
936 |
+
{
|
937 |
+
"epoch": 0.2714285714285714,
|
938 |
+
"grad_norm": 0.1904296875,
|
939 |
+
"learning_rate": 7.306122448979592e-06,
|
940 |
+
"loss": 0.5522,
|
941 |
+
"step": 133
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.27346938775510204,
|
945 |
+
"grad_norm": 0.1240234375,
|
946 |
+
"learning_rate": 7.285714285714286e-06,
|
947 |
+
"loss": 0.5492,
|
948 |
+
"step": 134
|
949 |
+
},
|
950 |
+
{
|
951 |
+
"epoch": 0.2755102040816326,
|
952 |
+
"grad_norm": 0.1337890625,
|
953 |
+
"learning_rate": 7.2653061224489805e-06,
|
954 |
+
"loss": 0.5331,
|
955 |
+
"step": 135
|
956 |
+
},
|
957 |
+
{
|
958 |
+
"epoch": 0.27755102040816326,
|
959 |
+
"grad_norm": 0.1689453125,
|
960 |
+
"learning_rate": 7.244897959183675e-06,
|
961 |
+
"loss": 0.5545,
|
962 |
+
"step": 136
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.2795918367346939,
|
966 |
+
"grad_norm": 0.150390625,
|
967 |
+
"learning_rate": 7.224489795918368e-06,
|
968 |
+
"loss": 0.5441,
|
969 |
+
"step": 137
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.2816326530612245,
|
973 |
+
"grad_norm": 0.1494140625,
|
974 |
+
"learning_rate": 7.204081632653061e-06,
|
975 |
+
"loss": 0.5591,
|
976 |
+
"step": 138
|
977 |
+
},
|
978 |
+
{
|
979 |
+
"epoch": 0.2836734693877551,
|
980 |
+
"grad_norm": 0.130859375,
|
981 |
+
"learning_rate": 7.183673469387755e-06,
|
982 |
+
"loss": 0.5441,
|
983 |
+
"step": 139
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.2857142857142857,
|
987 |
+
"grad_norm": 0.1669921875,
|
988 |
+
"learning_rate": 7.16326530612245e-06,
|
989 |
+
"loss": 0.5392,
|
990 |
+
"step": 140
|
991 |
+
},
|
992 |
+
{
|
993 |
+
"epoch": 0.28775510204081634,
|
994 |
+
"grad_norm": 0.22265625,
|
995 |
+
"learning_rate": 7.1428571428571436e-06,
|
996 |
+
"loss": 0.537,
|
997 |
+
"step": 141
|
998 |
+
},
|
999 |
+
{
|
1000 |
+
"epoch": 0.2897959183673469,
|
1001 |
+
"grad_norm": 0.140625,
|
1002 |
+
"learning_rate": 7.122448979591837e-06,
|
1003 |
+
"loss": 0.5486,
|
1004 |
+
"step": 142
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 0.29183673469387755,
|
1008 |
+
"grad_norm": 0.1474609375,
|
1009 |
+
"learning_rate": 7.102040816326531e-06,
|
1010 |
+
"loss": 0.5418,
|
1011 |
+
"step": 143
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.2938775510204082,
|
1015 |
+
"grad_norm": 0.1484375,
|
1016 |
+
"learning_rate": 7.081632653061226e-06,
|
1017 |
+
"loss": 0.5288,
|
1018 |
+
"step": 144
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.29591836734693877,
|
1022 |
+
"grad_norm": 0.201171875,
|
1023 |
+
"learning_rate": 7.061224489795919e-06,
|
1024 |
+
"loss": 0.5165,
|
1025 |
+
"step": 145
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 0.2979591836734694,
|
1029 |
+
"grad_norm": 0.1318359375,
|
1030 |
+
"learning_rate": 7.0408163265306125e-06,
|
1031 |
+
"loss": 0.5285,
|
1032 |
+
"step": 146
|
1033 |
+
},
|
1034 |
+
{
|
1035 |
+
"epoch": 0.3,
|
1036 |
+
"grad_norm": 0.1806640625,
|
1037 |
+
"learning_rate": 7.020408163265307e-06,
|
1038 |
+
"loss": 0.5404,
|
1039 |
+
"step": 147
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 0.3020408163265306,
|
1043 |
+
"grad_norm": 0.146484375,
|
1044 |
+
"learning_rate": 7e-06,
|
1045 |
+
"loss": 0.5444,
|
1046 |
+
"step": 148
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 0.3040816326530612,
|
1050 |
+
"grad_norm": 0.177734375,
|
1051 |
+
"learning_rate": 6.979591836734695e-06,
|
1052 |
+
"loss": 0.5192,
|
1053 |
+
"step": 149
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.30612244897959184,
|
1057 |
+
"grad_norm": 0.1484375,
|
1058 |
+
"learning_rate": 6.959183673469388e-06,
|
1059 |
+
"loss": 0.5332,
|
1060 |
+
"step": 150
|
1061 |
+
},
|
1062 |
+
{
|
1063 |
+
"epoch": 0.3081632653061224,
|
1064 |
+
"grad_norm": 0.1591796875,
|
1065 |
+
"learning_rate": 6.938775510204082e-06,
|
1066 |
+
"loss": 0.5137,
|
1067 |
+
"step": 151
|
1068 |
+
},
|
1069 |
+
{
|
1070 |
+
"epoch": 0.31020408163265306,
|
1071 |
+
"grad_norm": 0.142578125,
|
1072 |
+
"learning_rate": 6.9183673469387755e-06,
|
1073 |
+
"loss": 0.5418,
|
1074 |
+
"step": 152
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.3122448979591837,
|
1078 |
+
"grad_norm": 0.158203125,
|
1079 |
+
"learning_rate": 6.8979591836734705e-06,
|
1080 |
+
"loss": 0.5262,
|
1081 |
+
"step": 153
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 0.3142857142857143,
|
1085 |
+
"grad_norm": 0.197265625,
|
1086 |
+
"learning_rate": 6.877551020408164e-06,
|
1087 |
+
"loss": 0.5324,
|
1088 |
+
"step": 154
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 0.3163265306122449,
|
1092 |
+
"grad_norm": 0.1591796875,
|
1093 |
+
"learning_rate": 6.857142857142858e-06,
|
1094 |
+
"loss": 0.5259,
|
1095 |
+
"step": 155
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.3183673469387755,
|
1099 |
+
"grad_norm": 0.279296875,
|
1100 |
+
"learning_rate": 6.836734693877551e-06,
|
1101 |
+
"loss": 0.5354,
|
1102 |
+
"step": 156
|
1103 |
+
},
|
1104 |
+
{
|
1105 |
+
"epoch": 0.32040816326530613,
|
1106 |
+
"grad_norm": 0.15234375,
|
1107 |
+
"learning_rate": 6.816326530612245e-06,
|
1108 |
+
"loss": 0.5283,
|
1109 |
+
"step": 157
|
1110 |
+
},
|
1111 |
+
{
|
1112 |
+
"epoch": 0.3224489795918367,
|
1113 |
+
"grad_norm": 0.1640625,
|
1114 |
+
"learning_rate": 6.7959183673469394e-06,
|
1115 |
+
"loss": 0.5269,
|
1116 |
+
"step": 158
|
1117 |
+
},
|
1118 |
+
{
|
1119 |
+
"epoch": 0.32448979591836735,
|
1120 |
+
"grad_norm": 0.1962890625,
|
1121 |
+
"learning_rate": 6.7755102040816336e-06,
|
1122 |
+
"loss": 0.5233,
|
1123 |
+
"step": 159
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 0.32653061224489793,
|
1127 |
+
"grad_norm": 0.15234375,
|
1128 |
+
"learning_rate": 6.755102040816327e-06,
|
1129 |
+
"loss": 0.5427,
|
1130 |
+
"step": 160
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.32857142857142857,
|
1134 |
+
"grad_norm": 0.1591796875,
|
1135 |
+
"learning_rate": 6.734693877551021e-06,
|
1136 |
+
"loss": 0.5468,
|
1137 |
+
"step": 161
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.3306122448979592,
|
1141 |
+
"grad_norm": 0.1474609375,
|
1142 |
+
"learning_rate": 6.714285714285714e-06,
|
1143 |
+
"loss": 0.5435,
|
1144 |
+
"step": 162
|
1145 |
+
},
|
1146 |
+
{
|
1147 |
+
"epoch": 0.3326530612244898,
|
1148 |
+
"grad_norm": 0.1611328125,
|
1149 |
+
"learning_rate": 6.693877551020409e-06,
|
1150 |
+
"loss": 0.5364,
|
1151 |
+
"step": 163
|
1152 |
+
},
|
1153 |
+
{
|
1154 |
+
"epoch": 0.3346938775510204,
|
1155 |
+
"grad_norm": 0.1455078125,
|
1156 |
+
"learning_rate": 6.6734693877551025e-06,
|
1157 |
+
"loss": 0.5338,
|
1158 |
+
"step": 164
|
1159 |
+
},
|
1160 |
+
{
|
1161 |
+
"epoch": 0.336734693877551,
|
1162 |
+
"grad_norm": 0.1396484375,
|
1163 |
+
"learning_rate": 6.653061224489797e-06,
|
1164 |
+
"loss": 0.521,
|
1165 |
+
"step": 165
|
1166 |
+
},
|
1167 |
+
{
|
1168 |
+
"epoch": 0.33877551020408164,
|
1169 |
+
"grad_norm": 0.1533203125,
|
1170 |
+
"learning_rate": 6.63265306122449e-06,
|
1171 |
+
"loss": 0.516,
|
1172 |
+
"step": 166
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 0.3408163265306122,
|
1176 |
+
"grad_norm": 0.166015625,
|
1177 |
+
"learning_rate": 6.612244897959185e-06,
|
1178 |
+
"loss": 0.5252,
|
1179 |
+
"step": 167
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.34285714285714286,
|
1183 |
+
"grad_norm": 0.1484375,
|
1184 |
+
"learning_rate": 6.591836734693878e-06,
|
1185 |
+
"loss": 0.5253,
|
1186 |
+
"step": 168
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.3448979591836735,
|
1190 |
+
"grad_norm": 0.1689453125,
|
1191 |
+
"learning_rate": 6.571428571428572e-06,
|
1192 |
+
"loss": 0.5281,
|
1193 |
+
"step": 169
|
1194 |
+
},
|
1195 |
+
{
|
1196 |
+
"epoch": 0.3469387755102041,
|
1197 |
+
"grad_norm": 0.16015625,
|
1198 |
+
"learning_rate": 6.5510204081632656e-06,
|
1199 |
+
"loss": 0.5296,
|
1200 |
+
"step": 170
|
1201 |
+
},
|
1202 |
+
{
|
1203 |
+
"epoch": 0.3489795918367347,
|
1204 |
+
"grad_norm": 0.1611328125,
|
1205 |
+
"learning_rate": 6.530612244897959e-06,
|
1206 |
+
"loss": 0.5179,
|
1207 |
+
"step": 171
|
1208 |
+
},
|
1209 |
+
{
|
1210 |
+
"epoch": 0.3510204081632653,
|
1211 |
+
"grad_norm": 0.19140625,
|
1212 |
+
"learning_rate": 6.510204081632654e-06,
|
1213 |
+
"loss": 0.5256,
|
1214 |
+
"step": 172
|
1215 |
+
},
|
1216 |
+
{
|
1217 |
+
"epoch": 0.35306122448979593,
|
1218 |
+
"grad_norm": 0.1943359375,
|
1219 |
+
"learning_rate": 6.489795918367348e-06,
|
1220 |
+
"loss": 0.5358,
|
1221 |
+
"step": 173
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.3551020408163265,
|
1225 |
+
"grad_norm": 0.1591796875,
|
1226 |
+
"learning_rate": 6.469387755102041e-06,
|
1227 |
+
"loss": 0.523,
|
1228 |
+
"step": 174
|
1229 |
+
},
|
1230 |
+
{
|
1231 |
+
"epoch": 0.35714285714285715,
|
1232 |
+
"grad_norm": 0.1533203125,
|
1233 |
+
"learning_rate": 6.4489795918367345e-06,
|
1234 |
+
"loss": 0.5238,
|
1235 |
+
"step": 175
|
1236 |
+
},
|
1237 |
+
{
|
1238 |
+
"epoch": 0.35918367346938773,
|
1239 |
+
"grad_norm": 0.150390625,
|
1240 |
+
"learning_rate": 6.4285714285714295e-06,
|
1241 |
+
"loss": 0.528,
|
1242 |
+
"step": 176
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.36122448979591837,
|
1246 |
+
"grad_norm": 0.158203125,
|
1247 |
+
"learning_rate": 6.408163265306124e-06,
|
1248 |
+
"loss": 0.5415,
|
1249 |
+
"step": 177
|
1250 |
+
},
|
1251 |
+
{
|
1252 |
+
"epoch": 0.363265306122449,
|
1253 |
+
"grad_norm": 0.1552734375,
|
1254 |
+
"learning_rate": 6.387755102040817e-06,
|
1255 |
+
"loss": 0.5293,
|
1256 |
+
"step": 178
|
1257 |
+
},
|
1258 |
+
{
|
1259 |
+
"epoch": 0.3653061224489796,
|
1260 |
+
"grad_norm": 0.17578125,
|
1261 |
+
"learning_rate": 6.36734693877551e-06,
|
1262 |
+
"loss": 0.5157,
|
1263 |
+
"step": 179
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.3673469387755102,
|
1267 |
+
"grad_norm": 0.189453125,
|
1268 |
+
"learning_rate": 6.346938775510204e-06,
|
1269 |
+
"loss": 0.5146,
|
1270 |
+
"step": 180
|
1271 |
+
},
|
1272 |
+
{
|
1273 |
+
"epoch": 0.3693877551020408,
|
1274 |
+
"grad_norm": 0.1591796875,
|
1275 |
+
"learning_rate": 6.326530612244899e-06,
|
1276 |
+
"loss": 0.5117,
|
1277 |
+
"step": 181
|
1278 |
+
},
|
1279 |
+
{
|
1280 |
+
"epoch": 0.37142857142857144,
|
1281 |
+
"grad_norm": 0.16015625,
|
1282 |
+
"learning_rate": 6.3061224489795925e-06,
|
1283 |
+
"loss": 0.5088,
|
1284 |
+
"step": 182
|
1285 |
+
},
|
1286 |
+
{
|
1287 |
+
"epoch": 0.373469387755102,
|
1288 |
+
"grad_norm": 0.216796875,
|
1289 |
+
"learning_rate": 6.285714285714286e-06,
|
1290 |
+
"loss": 0.4939,
|
1291 |
+
"step": 183
|
1292 |
+
},
|
1293 |
+
{
|
1294 |
+
"epoch": 0.37551020408163266,
|
1295 |
+
"grad_norm": 0.1865234375,
|
1296 |
+
"learning_rate": 6.26530612244898e-06,
|
1297 |
+
"loss": 0.5215,
|
1298 |
+
"step": 184
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.37755102040816324,
|
1302 |
+
"grad_norm": 0.171875,
|
1303 |
+
"learning_rate": 6.244897959183675e-06,
|
1304 |
+
"loss": 0.5192,
|
1305 |
+
"step": 185
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.3795918367346939,
|
1309 |
+
"grad_norm": 0.162109375,
|
1310 |
+
"learning_rate": 6.224489795918368e-06,
|
1311 |
+
"loss": 0.5144,
|
1312 |
+
"step": 186
|
1313 |
+
},
|
1314 |
+
{
|
1315 |
+
"epoch": 0.3816326530612245,
|
1316 |
+
"grad_norm": 0.1962890625,
|
1317 |
+
"learning_rate": 6.2040816326530614e-06,
|
1318 |
+
"loss": 0.5037,
|
1319 |
+
"step": 187
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 0.3836734693877551,
|
1323 |
+
"grad_norm": 0.177734375,
|
1324 |
+
"learning_rate": 6.1836734693877556e-06,
|
1325 |
+
"loss": 0.5133,
|
1326 |
+
"step": 188
|
1327 |
+
},
|
1328 |
+
{
|
1329 |
+
"epoch": 0.38571428571428573,
|
1330 |
+
"grad_norm": 0.18359375,
|
1331 |
+
"learning_rate": 6.163265306122449e-06,
|
1332 |
+
"loss": 0.5179,
|
1333 |
+
"step": 189
|
1334 |
+
},
|
1335 |
+
{
|
1336 |
+
"epoch": 0.3877551020408163,
|
1337 |
+
"grad_norm": 0.2001953125,
|
1338 |
+
"learning_rate": 6.142857142857144e-06,
|
1339 |
+
"loss": 0.521,
|
1340 |
+
"step": 190
|
1341 |
+
},
|
1342 |
+
{
|
1343 |
+
"epoch": 0.38979591836734695,
|
1344 |
+
"grad_norm": 0.1572265625,
|
1345 |
+
"learning_rate": 6.122448979591837e-06,
|
1346 |
+
"loss": 0.5148,
|
1347 |
+
"step": 191
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.39183673469387753,
|
1351 |
+
"grad_norm": 0.1669921875,
|
1352 |
+
"learning_rate": 6.102040816326531e-06,
|
1353 |
+
"loss": 0.5336,
|
1354 |
+
"step": 192
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.39387755102040817,
|
1358 |
+
"grad_norm": 0.2041015625,
|
1359 |
+
"learning_rate": 6.0816326530612245e-06,
|
1360 |
+
"loss": 0.5312,
|
1361 |
+
"step": 193
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 0.39591836734693875,
|
1365 |
+
"grad_norm": 0.181640625,
|
1366 |
+
"learning_rate": 6.0612244897959195e-06,
|
1367 |
+
"loss": 0.516,
|
1368 |
+
"step": 194
|
1369 |
+
},
|
1370 |
+
{
|
1371 |
+
"epoch": 0.3979591836734694,
|
1372 |
+
"grad_norm": 0.1591796875,
|
1373 |
+
"learning_rate": 6.040816326530613e-06,
|
1374 |
+
"loss": 0.5157,
|
1375 |
+
"step": 195
|
1376 |
+
},
|
1377 |
+
{
|
1378 |
+
"epoch": 0.4,
|
1379 |
+
"grad_norm": 0.138671875,
|
1380 |
+
"learning_rate": 6.020408163265307e-06,
|
1381 |
+
"loss": 0.5093,
|
1382 |
+
"step": 196
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 0.4020408163265306,
|
1386 |
+
"grad_norm": 0.1669921875,
|
1387 |
+
"learning_rate": 6e-06,
|
1388 |
+
"loss": 0.5135,
|
1389 |
+
"step": 197
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.40408163265306124,
|
1393 |
+
"grad_norm": 0.1484375,
|
1394 |
+
"learning_rate": 5.979591836734694e-06,
|
1395 |
+
"loss": 0.5079,
|
1396 |
+
"step": 198
|
1397 |
+
},
|
1398 |
+
{
|
1399 |
+
"epoch": 0.4061224489795918,
|
1400 |
+
"grad_norm": 0.2265625,
|
1401 |
+
"learning_rate": 5.959183673469388e-06,
|
1402 |
+
"loss": 0.5114,
|
1403 |
+
"step": 199
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 0.40816326530612246,
|
1407 |
+
"grad_norm": 0.1982421875,
|
1408 |
+
"learning_rate": 5.9387755102040825e-06,
|
1409 |
+
"loss": 0.5142,
|
1410 |
+
"step": 200
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.41020408163265304,
|
1414 |
+
"grad_norm": 0.173828125,
|
1415 |
+
"learning_rate": 5.918367346938776e-06,
|
1416 |
+
"loss": 0.5295,
|
1417 |
+
"step": 201
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 0.4122448979591837,
|
1421 |
+
"grad_norm": 0.1884765625,
|
1422 |
+
"learning_rate": 5.89795918367347e-06,
|
1423 |
+
"loss": 0.5196,
|
1424 |
+
"step": 202
|
1425 |
+
},
|
1426 |
+
{
|
1427 |
+
"epoch": 0.4142857142857143,
|
1428 |
+
"grad_norm": 0.169921875,
|
1429 |
+
"learning_rate": 5.877551020408164e-06,
|
1430 |
+
"loss": 0.5118,
|
1431 |
+
"step": 203
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.4163265306122449,
|
1435 |
+
"grad_norm": 0.166015625,
|
1436 |
+
"learning_rate": 5.857142857142858e-06,
|
1437 |
+
"loss": 0.5065,
|
1438 |
+
"step": 204
|
1439 |
+
},
|
1440 |
+
{
|
1441 |
+
"epoch": 0.41836734693877553,
|
1442 |
+
"grad_norm": 0.189453125,
|
1443 |
+
"learning_rate": 5.8367346938775515e-06,
|
1444 |
+
"loss": 0.5082,
|
1445 |
+
"step": 205
|
1446 |
+
},
|
1447 |
+
{
|
1448 |
+
"epoch": 0.4204081632653061,
|
1449 |
+
"grad_norm": 0.2099609375,
|
1450 |
+
"learning_rate": 5.816326530612246e-06,
|
1451 |
+
"loss": 0.5056,
|
1452 |
+
"step": 206
|
1453 |
+
},
|
1454 |
+
{
|
1455 |
+
"epoch": 0.42244897959183675,
|
1456 |
+
"grad_norm": 0.1572265625,
|
1457 |
+
"learning_rate": 5.795918367346939e-06,
|
1458 |
+
"loss": 0.5127,
|
1459 |
+
"step": 207
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 0.42448979591836733,
|
1463 |
+
"grad_norm": 0.1875,
|
1464 |
+
"learning_rate": 5.775510204081634e-06,
|
1465 |
+
"loss": 0.4988,
|
1466 |
+
"step": 208
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 0.42653061224489797,
|
1470 |
+
"grad_norm": 0.169921875,
|
1471 |
+
"learning_rate": 5.755102040816327e-06,
|
1472 |
+
"loss": 0.501,
|
1473 |
+
"step": 209
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.42857142857142855,
|
1477 |
+
"grad_norm": 0.1865234375,
|
1478 |
+
"learning_rate": 5.73469387755102e-06,
|
1479 |
+
"loss": 0.526,
|
1480 |
+
"step": 210
|
1481 |
+
},
|
1482 |
+
{
|
1483 |
+
"epoch": 0.4306122448979592,
|
1484 |
+
"grad_norm": 0.1640625,
|
1485 |
+
"learning_rate": 5.7142857142857145e-06,
|
1486 |
+
"loss": 0.5079,
|
1487 |
+
"step": 211
|
1488 |
+
},
|
1489 |
+
{
|
1490 |
+
"epoch": 0.4326530612244898,
|
1491 |
+
"grad_norm": 0.2001953125,
|
1492 |
+
"learning_rate": 5.6938775510204095e-06,
|
1493 |
+
"loss": 0.5059,
|
1494 |
+
"step": 212
|
1495 |
+
},
|
1496 |
+
{
|
1497 |
+
"epoch": 0.4346938775510204,
|
1498 |
+
"grad_norm": 0.181640625,
|
1499 |
+
"learning_rate": 5.673469387755103e-06,
|
1500 |
+
"loss": 0.5138,
|
1501 |
+
"step": 213
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 0.43673469387755104,
|
1505 |
+
"grad_norm": 0.1728515625,
|
1506 |
+
"learning_rate": 5.653061224489796e-06,
|
1507 |
+
"loss": 0.4999,
|
1508 |
+
"step": 214
|
1509 |
+
},
|
1510 |
+
{
|
1511 |
+
"epoch": 0.4387755102040816,
|
1512 |
+
"grad_norm": 0.1943359375,
|
1513 |
+
"learning_rate": 5.63265306122449e-06,
|
1514 |
+
"loss": 0.5155,
|
1515 |
+
"step": 215
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.44081632653061226,
|
1519 |
+
"grad_norm": 0.1865234375,
|
1520 |
+
"learning_rate": 5.6122448979591834e-06,
|
1521 |
+
"loss": 0.5005,
|
1522 |
+
"step": 216
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 0.44285714285714284,
|
1526 |
+
"grad_norm": 0.171875,
|
1527 |
+
"learning_rate": 5.591836734693878e-06,
|
1528 |
+
"loss": 0.5026,
|
1529 |
+
"step": 217
|
1530 |
+
},
|
1531 |
+
{
|
1532 |
+
"epoch": 0.4448979591836735,
|
1533 |
+
"grad_norm": 0.1806640625,
|
1534 |
+
"learning_rate": 5.571428571428572e-06,
|
1535 |
+
"loss": 0.4997,
|
1536 |
+
"step": 218
|
1537 |
+
},
|
1538 |
+
{
|
1539 |
+
"epoch": 0.44693877551020406,
|
1540 |
+
"grad_norm": 0.1630859375,
|
1541 |
+
"learning_rate": 5.551020408163266e-06,
|
1542 |
+
"loss": 0.5055,
|
1543 |
+
"step": 219
|
1544 |
+
},
|
1545 |
+
{
|
1546 |
+
"epoch": 0.4489795918367347,
|
1547 |
+
"grad_norm": 0.18359375,
|
1548 |
+
"learning_rate": 5.530612244897959e-06,
|
1549 |
+
"loss": 0.5036,
|
1550 |
+
"step": 220
|
1551 |
+
},
|
1552 |
+
{
|
1553 |
+
"epoch": 0.45102040816326533,
|
1554 |
+
"grad_norm": 0.171875,
|
1555 |
+
"learning_rate": 5.510204081632653e-06,
|
1556 |
+
"loss": 0.5184,
|
1557 |
+
"step": 221
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.4530612244897959,
|
1561 |
+
"grad_norm": 0.1826171875,
|
1562 |
+
"learning_rate": 5.489795918367347e-06,
|
1563 |
+
"loss": 0.4992,
|
1564 |
+
"step": 222
|
1565 |
+
},
|
1566 |
+
{
|
1567 |
+
"epoch": 0.45510204081632655,
|
1568 |
+
"grad_norm": 0.2421875,
|
1569 |
+
"learning_rate": 5.4693877551020415e-06,
|
1570 |
+
"loss": 0.5114,
|
1571 |
+
"step": 223
|
1572 |
+
},
|
1573 |
+
{
|
1574 |
+
"epoch": 0.45714285714285713,
|
1575 |
+
"grad_norm": 0.1845703125,
|
1576 |
+
"learning_rate": 5.448979591836735e-06,
|
1577 |
+
"loss": 0.5069,
|
1578 |
+
"step": 224
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 0.45918367346938777,
|
1582 |
+
"grad_norm": 0.177734375,
|
1583 |
+
"learning_rate": 5.428571428571429e-06,
|
1584 |
+
"loss": 0.4927,
|
1585 |
+
"step": 225
|
1586 |
+
},
|
1587 |
+
{
|
1588 |
+
"epoch": 0.46122448979591835,
|
1589 |
+
"grad_norm": 0.150390625,
|
1590 |
+
"learning_rate": 5.408163265306123e-06,
|
1591 |
+
"loss": 0.5002,
|
1592 |
+
"step": 226
|
1593 |
+
},
|
1594 |
+
{
|
1595 |
+
"epoch": 0.463265306122449,
|
1596 |
+
"grad_norm": 0.189453125,
|
1597 |
+
"learning_rate": 5.387755102040817e-06,
|
1598 |
+
"loss": 0.5106,
|
1599 |
+
"step": 227
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.46530612244897956,
|
1603 |
+
"grad_norm": 0.1689453125,
|
1604 |
+
"learning_rate": 5.36734693877551e-06,
|
1605 |
+
"loss": 0.5203,
|
1606 |
+
"step": 228
|
1607 |
+
},
|
1608 |
+
{
|
1609 |
+
"epoch": 0.4673469387755102,
|
1610 |
+
"grad_norm": 0.1669921875,
|
1611 |
+
"learning_rate": 5.3469387755102045e-06,
|
1612 |
+
"loss": 0.4991,
|
1613 |
+
"step": 229
|
1614 |
+
},
|
1615 |
+
{
|
1616 |
+
"epoch": 0.46938775510204084,
|
1617 |
+
"grad_norm": 0.1845703125,
|
1618 |
+
"learning_rate": 5.326530612244898e-06,
|
1619 |
+
"loss": 0.4836,
|
1620 |
+
"step": 230
|
1621 |
+
},
|
1622 |
+
{
|
1623 |
+
"epoch": 0.4714285714285714,
|
1624 |
+
"grad_norm": 0.150390625,
|
1625 |
+
"learning_rate": 5.306122448979593e-06,
|
1626 |
+
"loss": 0.5134,
|
1627 |
+
"step": 231
|
1628 |
+
},
|
1629 |
+
{
|
1630 |
+
"epoch": 0.47346938775510206,
|
1631 |
+
"grad_norm": 0.177734375,
|
1632 |
+
"learning_rate": 5.285714285714286e-06,
|
1633 |
+
"loss": 0.5014,
|
1634 |
+
"step": 232
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 0.47551020408163264,
|
1638 |
+
"grad_norm": 0.158203125,
|
1639 |
+
"learning_rate": 5.26530612244898e-06,
|
1640 |
+
"loss": 0.5033,
|
1641 |
+
"step": 233
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.4775510204081633,
|
1645 |
+
"grad_norm": 0.1796875,
|
1646 |
+
"learning_rate": 5.2448979591836735e-06,
|
1647 |
+
"loss": 0.5087,
|
1648 |
+
"step": 234
|
1649 |
+
},
|
1650 |
+
{
|
1651 |
+
"epoch": 0.47959183673469385,
|
1652 |
+
"grad_norm": 0.2119140625,
|
1653 |
+
"learning_rate": 5.2244897959183684e-06,
|
1654 |
+
"loss": 0.5068,
|
1655 |
+
"step": 235
|
1656 |
+
},
|
1657 |
+
{
|
1658 |
+
"epoch": 0.4816326530612245,
|
1659 |
+
"grad_norm": 0.166015625,
|
1660 |
+
"learning_rate": 5.204081632653062e-06,
|
1661 |
+
"loss": 0.516,
|
1662 |
+
"step": 236
|
1663 |
+
},
|
1664 |
+
{
|
1665 |
+
"epoch": 0.48367346938775513,
|
1666 |
+
"grad_norm": 0.16015625,
|
1667 |
+
"learning_rate": 5.183673469387756e-06,
|
1668 |
+
"loss": 0.5097,
|
1669 |
+
"step": 237
|
1670 |
+
},
|
1671 |
+
{
|
1672 |
+
"epoch": 0.4857142857142857,
|
1673 |
+
"grad_norm": 0.1650390625,
|
1674 |
+
"learning_rate": 5.163265306122449e-06,
|
1675 |
+
"loss": 0.5029,
|
1676 |
+
"step": 238
|
1677 |
+
},
|
1678 |
+
{
|
1679 |
+
"epoch": 0.48775510204081635,
|
1680 |
+
"grad_norm": 0.2216796875,
|
1681 |
+
"learning_rate": 5.142857142857142e-06,
|
1682 |
+
"loss": 0.5014,
|
1683 |
+
"step": 239
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.4897959183673469,
|
1687 |
+
"grad_norm": 0.189453125,
|
1688 |
+
"learning_rate": 5.122448979591837e-06,
|
1689 |
+
"loss": 0.4849,
|
1690 |
+
"step": 240
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 0.49183673469387756,
|
1694 |
+
"grad_norm": 0.1806640625,
|
1695 |
+
"learning_rate": 5.1020408163265315e-06,
|
1696 |
+
"loss": 0.5112,
|
1697 |
+
"step": 241
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 0.49387755102040815,
|
1701 |
+
"grad_norm": 0.1640625,
|
1702 |
+
"learning_rate": 5.081632653061225e-06,
|
1703 |
+
"loss": 0.5001,
|
1704 |
+
"step": 242
|
1705 |
+
},
|
1706 |
+
{
|
1707 |
+
"epoch": 0.4959183673469388,
|
1708 |
+
"grad_norm": 0.2138671875,
|
1709 |
+
"learning_rate": 5.061224489795918e-06,
|
1710 |
+
"loss": 0.5101,
|
1711 |
+
"step": 243
|
1712 |
+
},
|
1713 |
+
{
|
1714 |
+
"epoch": 0.49795918367346936,
|
1715 |
+
"grad_norm": 0.158203125,
|
1716 |
+
"learning_rate": 5.040816326530613e-06,
|
1717 |
+
"loss": 0.497,
|
1718 |
+
"step": 244
|
1719 |
+
},
|
1720 |
+
{
|
1721 |
+
"epoch": 0.5,
|
1722 |
+
"grad_norm": 0.1669921875,
|
1723 |
+
"learning_rate": 5.020408163265307e-06,
|
1724 |
+
"loss": 0.5118,
|
1725 |
+
"step": 245
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.5020408163265306,
|
1729 |
+
"grad_norm": 0.1611328125,
|
1730 |
+
"learning_rate": 5e-06,
|
1731 |
+
"loss": 0.5013,
|
1732 |
+
"step": 246
|
1733 |
+
},
|
1734 |
+
{
|
1735 |
+
"epoch": 0.5040816326530613,
|
1736 |
+
"grad_norm": 0.201171875,
|
1737 |
+
"learning_rate": 4.979591836734694e-06,
|
1738 |
+
"loss": 0.482,
|
1739 |
+
"step": 247
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 0.5061224489795918,
|
1743 |
+
"grad_norm": 0.177734375,
|
1744 |
+
"learning_rate": 4.959183673469388e-06,
|
1745 |
+
"loss": 0.4942,
|
1746 |
+
"step": 248
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 0.5081632653061224,
|
1750 |
+
"grad_norm": 0.1826171875,
|
1751 |
+
"learning_rate": 4.938775510204082e-06,
|
1752 |
+
"loss": 0.4896,
|
1753 |
+
"step": 249
|
1754 |
+
},
|
1755 |
+
{
|
1756 |
+
"epoch": 0.5102040816326531,
|
1757 |
+
"grad_norm": 0.1748046875,
|
1758 |
+
"learning_rate": 4.918367346938776e-06,
|
1759 |
+
"loss": 0.5108,
|
1760 |
+
"step": 250
|
1761 |
+
},
|
1762 |
+
{
|
1763 |
+
"epoch": 0.5122448979591837,
|
1764 |
+
"grad_norm": 0.1669921875,
|
1765 |
+
"learning_rate": 4.897959183673469e-06,
|
1766 |
+
"loss": 0.4907,
|
1767 |
+
"step": 251
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 0.5142857142857142,
|
1771 |
+
"grad_norm": 0.240234375,
|
1772 |
+
"learning_rate": 4.8775510204081635e-06,
|
1773 |
+
"loss": 0.5048,
|
1774 |
+
"step": 252
|
1775 |
+
},
|
1776 |
+
{
|
1777 |
+
"epoch": 0.5163265306122449,
|
1778 |
+
"grad_norm": 0.1767578125,
|
1779 |
+
"learning_rate": 4.857142857142858e-06,
|
1780 |
+
"loss": 0.5061,
|
1781 |
+
"step": 253
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 0.5183673469387755,
|
1785 |
+
"grad_norm": 0.228515625,
|
1786 |
+
"learning_rate": 4.836734693877552e-06,
|
1787 |
+
"loss": 0.5041,
|
1788 |
+
"step": 254
|
1789 |
+
},
|
1790 |
+
{
|
1791 |
+
"epoch": 0.5204081632653061,
|
1792 |
+
"grad_norm": 0.1533203125,
|
1793 |
+
"learning_rate": 4.816326530612245e-06,
|
1794 |
+
"loss": 0.5029,
|
1795 |
+
"step": 255
|
1796 |
+
},
|
1797 |
+
{
|
1798 |
+
"epoch": 0.5224489795918368,
|
1799 |
+
"grad_norm": 0.150390625,
|
1800 |
+
"learning_rate": 4.795918367346939e-06,
|
1801 |
+
"loss": 0.5057,
|
1802 |
+
"step": 256
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 0.5244897959183673,
|
1806 |
+
"grad_norm": 0.1630859375,
|
1807 |
+
"learning_rate": 4.775510204081633e-06,
|
1808 |
+
"loss": 0.4966,
|
1809 |
+
"step": 257
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.5265306122448979,
|
1813 |
+
"grad_norm": 0.181640625,
|
1814 |
+
"learning_rate": 4.7551020408163265e-06,
|
1815 |
+
"loss": 0.5008,
|
1816 |
+
"step": 258
|
1817 |
+
},
|
1818 |
+
{
|
1819 |
+
"epoch": 0.5285714285714286,
|
1820 |
+
"grad_norm": 0.1455078125,
|
1821 |
+
"learning_rate": 4.734693877551021e-06,
|
1822 |
+
"loss": 0.4972,
|
1823 |
+
"step": 259
|
1824 |
+
},
|
1825 |
+
{
|
1826 |
+
"epoch": 0.5306122448979592,
|
1827 |
+
"grad_norm": 0.189453125,
|
1828 |
+
"learning_rate": 4.714285714285715e-06,
|
1829 |
+
"loss": 0.4923,
|
1830 |
+
"step": 260
|
1831 |
+
},
|
1832 |
+
{
|
1833 |
+
"epoch": 0.5326530612244897,
|
1834 |
+
"grad_norm": 0.1787109375,
|
1835 |
+
"learning_rate": 4.693877551020409e-06,
|
1836 |
+
"loss": 0.495,
|
1837 |
+
"step": 261
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 0.5346938775510204,
|
1841 |
+
"grad_norm": 0.16015625,
|
1842 |
+
"learning_rate": 4.673469387755102e-06,
|
1843 |
+
"loss": 0.5016,
|
1844 |
+
"step": 262
|
1845 |
+
},
|
1846 |
+
{
|
1847 |
+
"epoch": 0.536734693877551,
|
1848 |
+
"grad_norm": 0.154296875,
|
1849 |
+
"learning_rate": 4.653061224489796e-06,
|
1850 |
+
"loss": 0.5099,
|
1851 |
+
"step": 263
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 0.5387755102040817,
|
1855 |
+
"grad_norm": 0.1923828125,
|
1856 |
+
"learning_rate": 4.63265306122449e-06,
|
1857 |
+
"loss": 0.5017,
|
1858 |
+
"step": 264
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 0.5408163265306123,
|
1862 |
+
"grad_norm": 0.1826171875,
|
1863 |
+
"learning_rate": 4.612244897959184e-06,
|
1864 |
+
"loss": 0.487,
|
1865 |
+
"step": 265
|
1866 |
+
},
|
1867 |
+
{
|
1868 |
+
"epoch": 0.5428571428571428,
|
1869 |
+
"grad_norm": 0.19140625,
|
1870 |
+
"learning_rate": 4.591836734693878e-06,
|
1871 |
+
"loss": 0.488,
|
1872 |
+
"step": 266
|
1873 |
+
},
|
1874 |
+
{
|
1875 |
+
"epoch": 0.5448979591836735,
|
1876 |
+
"grad_norm": 0.1875,
|
1877 |
+
"learning_rate": 4.571428571428572e-06,
|
1878 |
+
"loss": 0.4872,
|
1879 |
+
"step": 267
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 0.5469387755102041,
|
1883 |
+
"grad_norm": 0.19140625,
|
1884 |
+
"learning_rate": 4.551020408163266e-06,
|
1885 |
+
"loss": 0.4937,
|
1886 |
+
"step": 268
|
1887 |
+
},
|
1888 |
+
{
|
1889 |
+
"epoch": 0.5489795918367347,
|
1890 |
+
"grad_norm": 0.189453125,
|
1891 |
+
"learning_rate": 4.530612244897959e-06,
|
1892 |
+
"loss": 0.4985,
|
1893 |
+
"step": 269
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 0.5510204081632653,
|
1897 |
+
"grad_norm": 0.1689453125,
|
1898 |
+
"learning_rate": 4.5102040816326535e-06,
|
1899 |
+
"loss": 0.5172,
|
1900 |
+
"step": 270
|
1901 |
+
},
|
1902 |
+
{
|
1903 |
+
"epoch": 0.5530612244897959,
|
1904 |
+
"grad_norm": 0.1669921875,
|
1905 |
+
"learning_rate": 4.489795918367348e-06,
|
1906 |
+
"loss": 0.4946,
|
1907 |
+
"step": 271
|
1908 |
+
},
|
1909 |
+
{
|
1910 |
+
"epoch": 0.5551020408163265,
|
1911 |
+
"grad_norm": 0.25,
|
1912 |
+
"learning_rate": 4.469387755102041e-06,
|
1913 |
+
"loss": 0.501,
|
1914 |
+
"step": 272
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 0.5571428571428572,
|
1918 |
+
"grad_norm": 0.1796875,
|
1919 |
+
"learning_rate": 4.448979591836735e-06,
|
1920 |
+
"loss": 0.4943,
|
1921 |
+
"step": 273
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 0.5591836734693878,
|
1925 |
+
"grad_norm": 0.21875,
|
1926 |
+
"learning_rate": 4.428571428571429e-06,
|
1927 |
+
"loss": 0.4852,
|
1928 |
+
"step": 274
|
1929 |
+
},
|
1930 |
+
{
|
1931 |
+
"epoch": 0.5612244897959183,
|
1932 |
+
"grad_norm": 0.1904296875,
|
1933 |
+
"learning_rate": 4.408163265306123e-06,
|
1934 |
+
"loss": 0.4729,
|
1935 |
+
"step": 275
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 0.563265306122449,
|
1939 |
+
"grad_norm": 0.1826171875,
|
1940 |
+
"learning_rate": 4.3877551020408165e-06,
|
1941 |
+
"loss": 0.4969,
|
1942 |
+
"step": 276
|
1943 |
+
},
|
1944 |
+
{
|
1945 |
+
"epoch": 0.5653061224489796,
|
1946 |
+
"grad_norm": 0.2314453125,
|
1947 |
+
"learning_rate": 4.367346938775511e-06,
|
1948 |
+
"loss": 0.4959,
|
1949 |
+
"step": 277
|
1950 |
+
},
|
1951 |
+
{
|
1952 |
+
"epoch": 0.5673469387755102,
|
1953 |
+
"grad_norm": 0.2109375,
|
1954 |
+
"learning_rate": 4.346938775510205e-06,
|
1955 |
+
"loss": 0.5065,
|
1956 |
+
"step": 278
|
1957 |
+
},
|
1958 |
+
{
|
1959 |
+
"epoch": 0.5693877551020409,
|
1960 |
+
"grad_norm": 0.1611328125,
|
1961 |
+
"learning_rate": 4.326530612244899e-06,
|
1962 |
+
"loss": 0.4769,
|
1963 |
+
"step": 279
|
1964 |
+
},
|
1965 |
+
{
|
1966 |
+
"epoch": 0.5714285714285714,
|
1967 |
+
"grad_norm": 0.173828125,
|
1968 |
+
"learning_rate": 4.306122448979592e-06,
|
1969 |
+
"loss": 0.4895,
|
1970 |
+
"step": 280
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 0.573469387755102,
|
1974 |
+
"grad_norm": 0.1982421875,
|
1975 |
+
"learning_rate": 4.2857142857142855e-06,
|
1976 |
+
"loss": 0.485,
|
1977 |
+
"step": 281
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 0.5755102040816327,
|
1981 |
+
"grad_norm": 0.22265625,
|
1982 |
+
"learning_rate": 4.2653061224489804e-06,
|
1983 |
+
"loss": 0.4895,
|
1984 |
+
"step": 282
|
1985 |
+
},
|
1986 |
+
{
|
1987 |
+
"epoch": 0.5775510204081633,
|
1988 |
+
"grad_norm": 0.171875,
|
1989 |
+
"learning_rate": 4.244897959183674e-06,
|
1990 |
+
"loss": 0.4937,
|
1991 |
+
"step": 283
|
1992 |
+
},
|
1993 |
+
{
|
1994 |
+
"epoch": 0.5795918367346938,
|
1995 |
+
"grad_norm": 0.1611328125,
|
1996 |
+
"learning_rate": 4.224489795918368e-06,
|
1997 |
+
"loss": 0.4997,
|
1998 |
+
"step": 284
|
1999 |
+
},
|
2000 |
+
{
|
2001 |
+
"epoch": 0.5816326530612245,
|
2002 |
+
"grad_norm": 0.16796875,
|
2003 |
+
"learning_rate": 4.204081632653061e-06,
|
2004 |
+
"loss": 0.4885,
|
2005 |
+
"step": 285
|
2006 |
+
},
|
2007 |
+
{
|
2008 |
+
"epoch": 0.5836734693877551,
|
2009 |
+
"grad_norm": 0.1845703125,
|
2010 |
+
"learning_rate": 4.183673469387755e-06,
|
2011 |
+
"loss": 0.5069,
|
2012 |
+
"step": 286
|
2013 |
+
},
|
2014 |
+
{
|
2015 |
+
"epoch": 0.5857142857142857,
|
2016 |
+
"grad_norm": 0.171875,
|
2017 |
+
"learning_rate": 4.163265306122449e-06,
|
2018 |
+
"loss": 0.4867,
|
2019 |
+
"step": 287
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 0.5877551020408164,
|
2023 |
+
"grad_norm": 0.1767578125,
|
2024 |
+
"learning_rate": 4.1428571428571435e-06,
|
2025 |
+
"loss": 0.5128,
|
2026 |
+
"step": 288
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 0.5897959183673469,
|
2030 |
+
"grad_norm": 0.1767578125,
|
2031 |
+
"learning_rate": 4.122448979591837e-06,
|
2032 |
+
"loss": 0.5106,
|
2033 |
+
"step": 289
|
2034 |
+
},
|
2035 |
+
{
|
2036 |
+
"epoch": 0.5918367346938775,
|
2037 |
+
"grad_norm": 0.1708984375,
|
2038 |
+
"learning_rate": 4.102040816326531e-06,
|
2039 |
+
"loss": 0.4892,
|
2040 |
+
"step": 290
|
2041 |
+
},
|
2042 |
+
{
|
2043 |
+
"epoch": 0.5938775510204082,
|
2044 |
+
"grad_norm": 0.16015625,
|
2045 |
+
"learning_rate": 4.081632653061225e-06,
|
2046 |
+
"loss": 0.4883,
|
2047 |
+
"step": 291
|
2048 |
+
},
|
2049 |
+
{
|
2050 |
+
"epoch": 0.5959183673469388,
|
2051 |
+
"grad_norm": 0.2001953125,
|
2052 |
+
"learning_rate": 4.061224489795918e-06,
|
2053 |
+
"loss": 0.4828,
|
2054 |
+
"step": 292
|
2055 |
+
},
|
2056 |
+
{
|
2057 |
+
"epoch": 0.5979591836734693,
|
2058 |
+
"grad_norm": 0.2197265625,
|
2059 |
+
"learning_rate": 4.040816326530612e-06,
|
2060 |
+
"loss": 0.4872,
|
2061 |
+
"step": 293
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 0.6,
|
2065 |
+
"grad_norm": 0.16796875,
|
2066 |
+
"learning_rate": 4.0204081632653065e-06,
|
2067 |
+
"loss": 0.4812,
|
2068 |
+
"step": 294
|
2069 |
+
},
|
2070 |
+
{
|
2071 |
+
"epoch": 0.6020408163265306,
|
2072 |
+
"grad_norm": 0.1982421875,
|
2073 |
+
"learning_rate": 4.000000000000001e-06,
|
2074 |
+
"loss": 0.5009,
|
2075 |
+
"step": 295
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"epoch": 0.6040816326530613,
|
2079 |
+
"grad_norm": 0.189453125,
|
2080 |
+
"learning_rate": 3.979591836734694e-06,
|
2081 |
+
"loss": 0.4858,
|
2082 |
+
"step": 296
|
2083 |
+
},
|
2084 |
+
{
|
2085 |
+
"epoch": 0.6061224489795919,
|
2086 |
+
"grad_norm": 0.2080078125,
|
2087 |
+
"learning_rate": 3.959183673469388e-06,
|
2088 |
+
"loss": 0.5081,
|
2089 |
+
"step": 297
|
2090 |
+
},
|
2091 |
+
{
|
2092 |
+
"epoch": 0.6081632653061224,
|
2093 |
+
"grad_norm": 0.224609375,
|
2094 |
+
"learning_rate": 3.938775510204082e-06,
|
2095 |
+
"loss": 0.4935,
|
2096 |
+
"step": 298
|
2097 |
+
},
|
2098 |
+
{
|
2099 |
+
"epoch": 0.610204081632653,
|
2100 |
+
"grad_norm": 0.162109375,
|
2101 |
+
"learning_rate": 3.9183673469387755e-06,
|
2102 |
+
"loss": 0.4852,
|
2103 |
+
"step": 299
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 0.6122448979591837,
|
2107 |
+
"grad_norm": 0.16796875,
|
2108 |
+
"learning_rate": 3.89795918367347e-06,
|
2109 |
+
"loss": 0.4895,
|
2110 |
+
"step": 300
|
2111 |
+
},
|
2112 |
+
{
|
2113 |
+
"epoch": 0.6142857142857143,
|
2114 |
+
"grad_norm": 0.1806640625,
|
2115 |
+
"learning_rate": 3.877551020408164e-06,
|
2116 |
+
"loss": 0.4736,
|
2117 |
+
"step": 301
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 0.6163265306122448,
|
2121 |
+
"grad_norm": 0.154296875,
|
2122 |
+
"learning_rate": 3.857142857142858e-06,
|
2123 |
+
"loss": 0.4837,
|
2124 |
+
"step": 302
|
2125 |
+
},
|
2126 |
+
{
|
2127 |
+
"epoch": 0.6183673469387755,
|
2128 |
+
"grad_norm": 0.1572265625,
|
2129 |
+
"learning_rate": 3.836734693877551e-06,
|
2130 |
+
"loss": 0.4892,
|
2131 |
+
"step": 303
|
2132 |
+
},
|
2133 |
+
{
|
2134 |
+
"epoch": 0.6204081632653061,
|
2135 |
+
"grad_norm": 0.166015625,
|
2136 |
+
"learning_rate": 3.816326530612245e-06,
|
2137 |
+
"loss": 0.5028,
|
2138 |
+
"step": 304
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 0.6224489795918368,
|
2142 |
+
"grad_norm": 0.23046875,
|
2143 |
+
"learning_rate": 3.795918367346939e-06,
|
2144 |
+
"loss": 0.4965,
|
2145 |
+
"step": 305
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 0.6244897959183674,
|
2149 |
+
"grad_norm": 0.1640625,
|
2150 |
+
"learning_rate": 3.7755102040816327e-06,
|
2151 |
+
"loss": 0.4829,
|
2152 |
+
"step": 306
|
2153 |
+
},
|
2154 |
+
{
|
2155 |
+
"epoch": 0.6265306122448979,
|
2156 |
+
"grad_norm": 0.1982421875,
|
2157 |
+
"learning_rate": 3.7551020408163268e-06,
|
2158 |
+
"loss": 0.4934,
|
2159 |
+
"step": 307
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 0.6285714285714286,
|
2163 |
+
"grad_norm": 0.1728515625,
|
2164 |
+
"learning_rate": 3.7346938775510205e-06,
|
2165 |
+
"loss": 0.4848,
|
2166 |
+
"step": 308
|
2167 |
+
},
|
2168 |
+
{
|
2169 |
+
"epoch": 0.6306122448979592,
|
2170 |
+
"grad_norm": 0.1865234375,
|
2171 |
+
"learning_rate": 3.7142857142857146e-06,
|
2172 |
+
"loss": 0.4824,
|
2173 |
+
"step": 309
|
2174 |
+
},
|
2175 |
+
{
|
2176 |
+
"epoch": 0.6326530612244898,
|
2177 |
+
"grad_norm": 0.1630859375,
|
2178 |
+
"learning_rate": 3.6938775510204083e-06,
|
2179 |
+
"loss": 0.4836,
|
2180 |
+
"step": 310
|
2181 |
+
},
|
2182 |
+
{
|
2183 |
+
"epoch": 0.6346938775510204,
|
2184 |
+
"grad_norm": 0.1767578125,
|
2185 |
+
"learning_rate": 3.6734693877551024e-06,
|
2186 |
+
"loss": 0.4856,
|
2187 |
+
"step": 311
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 0.636734693877551,
|
2191 |
+
"grad_norm": 0.2177734375,
|
2192 |
+
"learning_rate": 3.653061224489796e-06,
|
2193 |
+
"loss": 0.5039,
|
2194 |
+
"step": 312
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 0.6387755102040816,
|
2198 |
+
"grad_norm": 0.1640625,
|
2199 |
+
"learning_rate": 3.6326530612244903e-06,
|
2200 |
+
"loss": 0.473,
|
2201 |
+
"step": 313
|
2202 |
+
},
|
2203 |
+
{
|
2204 |
+
"epoch": 0.6408163265306123,
|
2205 |
+
"grad_norm": 0.171875,
|
2206 |
+
"learning_rate": 3.612244897959184e-06,
|
2207 |
+
"loss": 0.4903,
|
2208 |
+
"step": 314
|
2209 |
+
},
|
2210 |
+
{
|
2211 |
+
"epoch": 0.6428571428571429,
|
2212 |
+
"grad_norm": 0.1689453125,
|
2213 |
+
"learning_rate": 3.5918367346938777e-06,
|
2214 |
+
"loss": 0.4831,
|
2215 |
+
"step": 315
|
2216 |
+
},
|
2217 |
+
{
|
2218 |
+
"epoch": 0.6448979591836734,
|
2219 |
+
"grad_norm": 0.17578125,
|
2220 |
+
"learning_rate": 3.5714285714285718e-06,
|
2221 |
+
"loss": 0.4859,
|
2222 |
+
"step": 316
|
2223 |
+
},
|
2224 |
+
{
|
2225 |
+
"epoch": 0.6469387755102041,
|
2226 |
+
"grad_norm": 0.1650390625,
|
2227 |
+
"learning_rate": 3.5510204081632655e-06,
|
2228 |
+
"loss": 0.5054,
|
2229 |
+
"step": 317
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 0.6489795918367347,
|
2233 |
+
"grad_norm": 0.1826171875,
|
2234 |
+
"learning_rate": 3.5306122448979596e-06,
|
2235 |
+
"loss": 0.4936,
|
2236 |
+
"step": 318
|
2237 |
+
},
|
2238 |
+
{
|
2239 |
+
"epoch": 0.6510204081632653,
|
2240 |
+
"grad_norm": 0.16015625,
|
2241 |
+
"learning_rate": 3.5102040816326533e-06,
|
2242 |
+
"loss": 0.5022,
|
2243 |
+
"step": 319
|
2244 |
+
},
|
2245 |
+
{
|
2246 |
+
"epoch": 0.6530612244897959,
|
2247 |
+
"grad_norm": 0.1767578125,
|
2248 |
+
"learning_rate": 3.4897959183673474e-06,
|
2249 |
+
"loss": 0.494,
|
2250 |
+
"step": 320
|
2251 |
+
},
|
2252 |
+
{
|
2253 |
+
"epoch": 0.6551020408163265,
|
2254 |
+
"grad_norm": 0.1806640625,
|
2255 |
+
"learning_rate": 3.469387755102041e-06,
|
2256 |
+
"loss": 0.4919,
|
2257 |
+
"step": 321
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 0.6571428571428571,
|
2261 |
+
"grad_norm": 0.1865234375,
|
2262 |
+
"learning_rate": 3.4489795918367353e-06,
|
2263 |
+
"loss": 0.4898,
|
2264 |
+
"step": 322
|
2265 |
+
},
|
2266 |
+
{
|
2267 |
+
"epoch": 0.6591836734693878,
|
2268 |
+
"grad_norm": 0.205078125,
|
2269 |
+
"learning_rate": 3.428571428571429e-06,
|
2270 |
+
"loss": 0.4987,
|
2271 |
+
"step": 323
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 0.6612244897959184,
|
2275 |
+
"grad_norm": 0.1826171875,
|
2276 |
+
"learning_rate": 3.4081632653061227e-06,
|
2277 |
+
"loss": 0.4831,
|
2278 |
+
"step": 324
|
2279 |
+
},
|
2280 |
+
{
|
2281 |
+
"epoch": 0.6632653061224489,
|
2282 |
+
"grad_norm": 0.158203125,
|
2283 |
+
"learning_rate": 3.3877551020408168e-06,
|
2284 |
+
"loss": 0.4944,
|
2285 |
+
"step": 325
|
2286 |
+
},
|
2287 |
+
{
|
2288 |
+
"epoch": 0.6653061224489796,
|
2289 |
+
"grad_norm": 0.1787109375,
|
2290 |
+
"learning_rate": 3.3673469387755105e-06,
|
2291 |
+
"loss": 0.4882,
|
2292 |
+
"step": 326
|
2293 |
+
},
|
2294 |
+
{
|
2295 |
+
"epoch": 0.6673469387755102,
|
2296 |
+
"grad_norm": 0.1787109375,
|
2297 |
+
"learning_rate": 3.3469387755102046e-06,
|
2298 |
+
"loss": 0.4915,
|
2299 |
+
"step": 327
|
2300 |
+
},
|
2301 |
+
{
|
2302 |
+
"epoch": 0.6693877551020408,
|
2303 |
+
"grad_norm": 0.1953125,
|
2304 |
+
"learning_rate": 3.3265306122448983e-06,
|
2305 |
+
"loss": 0.5001,
|
2306 |
+
"step": 328
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 0.6714285714285714,
|
2310 |
+
"grad_norm": 0.166015625,
|
2311 |
+
"learning_rate": 3.3061224489795924e-06,
|
2312 |
+
"loss": 0.4939,
|
2313 |
+
"step": 329
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 0.673469387755102,
|
2317 |
+
"grad_norm": 0.19140625,
|
2318 |
+
"learning_rate": 3.285714285714286e-06,
|
2319 |
+
"loss": 0.4834,
|
2320 |
+
"step": 330
|
2321 |
+
},
|
2322 |
+
{
|
2323 |
+
"epoch": 0.6755102040816326,
|
2324 |
+
"grad_norm": 0.2216796875,
|
2325 |
+
"learning_rate": 3.2653061224489794e-06,
|
2326 |
+
"loss": 0.5047,
|
2327 |
+
"step": 331
|
2328 |
+
},
|
2329 |
+
{
|
2330 |
+
"epoch": 0.6775510204081633,
|
2331 |
+
"grad_norm": 0.271484375,
|
2332 |
+
"learning_rate": 3.244897959183674e-06,
|
2333 |
+
"loss": 0.4859,
|
2334 |
+
"step": 332
|
2335 |
+
},
|
2336 |
+
{
|
2337 |
+
"epoch": 0.6795918367346939,
|
2338 |
+
"grad_norm": 0.1826171875,
|
2339 |
+
"learning_rate": 3.2244897959183672e-06,
|
2340 |
+
"loss": 0.4959,
|
2341 |
+
"step": 333
|
2342 |
+
},
|
2343 |
+
{
|
2344 |
+
"epoch": 0.6816326530612244,
|
2345 |
+
"grad_norm": 0.201171875,
|
2346 |
+
"learning_rate": 3.204081632653062e-06,
|
2347 |
+
"loss": 0.4912,
|
2348 |
+
"step": 334
|
2349 |
+
},
|
2350 |
+
{
|
2351 |
+
"epoch": 0.6836734693877551,
|
2352 |
+
"grad_norm": 0.20703125,
|
2353 |
+
"learning_rate": 3.183673469387755e-06,
|
2354 |
+
"loss": 0.4855,
|
2355 |
+
"step": 335
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 0.6857142857142857,
|
2359 |
+
"grad_norm": 0.2021484375,
|
2360 |
+
"learning_rate": 3.1632653061224496e-06,
|
2361 |
+
"loss": 0.4998,
|
2362 |
+
"step": 336
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 0.6877551020408164,
|
2366 |
+
"grad_norm": 0.1943359375,
|
2367 |
+
"learning_rate": 3.142857142857143e-06,
|
2368 |
+
"loss": 0.4906,
|
2369 |
+
"step": 337
|
2370 |
+
},
|
2371 |
+
{
|
2372 |
+
"epoch": 0.689795918367347,
|
2373 |
+
"grad_norm": 0.1943359375,
|
2374 |
+
"learning_rate": 3.1224489795918374e-06,
|
2375 |
+
"loss": 0.496,
|
2376 |
+
"step": 338
|
2377 |
+
},
|
2378 |
+
{
|
2379 |
+
"epoch": 0.6918367346938775,
|
2380 |
+
"grad_norm": 0.1845703125,
|
2381 |
+
"learning_rate": 3.1020408163265307e-06,
|
2382 |
+
"loss": 0.4864,
|
2383 |
+
"step": 339
|
2384 |
+
},
|
2385 |
+
{
|
2386 |
+
"epoch": 0.6938775510204082,
|
2387 |
+
"grad_norm": 0.1748046875,
|
2388 |
+
"learning_rate": 3.0816326530612244e-06,
|
2389 |
+
"loss": 0.4994,
|
2390 |
+
"step": 340
|
2391 |
+
},
|
2392 |
+
{
|
2393 |
+
"epoch": 0.6959183673469388,
|
2394 |
+
"grad_norm": 0.1884765625,
|
2395 |
+
"learning_rate": 3.0612244897959185e-06,
|
2396 |
+
"loss": 0.4915,
|
2397 |
+
"step": 341
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 0.6979591836734694,
|
2401 |
+
"grad_norm": 0.1787109375,
|
2402 |
+
"learning_rate": 3.0408163265306122e-06,
|
2403 |
+
"loss": 0.4864,
|
2404 |
+
"step": 342
|
2405 |
+
},
|
2406 |
+
{
|
2407 |
+
"epoch": 0.7,
|
2408 |
+
"grad_norm": 0.1962890625,
|
2409 |
+
"learning_rate": 3.0204081632653064e-06,
|
2410 |
+
"loss": 0.4896,
|
2411 |
+
"step": 343
|
2412 |
+
},
|
2413 |
+
{
|
2414 |
+
"epoch": 0.7020408163265306,
|
2415 |
+
"grad_norm": 0.173828125,
|
2416 |
+
"learning_rate": 3e-06,
|
2417 |
+
"loss": 0.4903,
|
2418 |
+
"step": 344
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 0.7040816326530612,
|
2422 |
+
"grad_norm": 0.197265625,
|
2423 |
+
"learning_rate": 2.979591836734694e-06,
|
2424 |
+
"loss": 0.4922,
|
2425 |
+
"step": 345
|
2426 |
+
},
|
2427 |
+
{
|
2428 |
+
"epoch": 0.7061224489795919,
|
2429 |
+
"grad_norm": 0.181640625,
|
2430 |
+
"learning_rate": 2.959183673469388e-06,
|
2431 |
+
"loss": 0.4945,
|
2432 |
+
"step": 346
|
2433 |
+
},
|
2434 |
+
{
|
2435 |
+
"epoch": 0.7081632653061225,
|
2436 |
+
"grad_norm": 0.16796875,
|
2437 |
+
"learning_rate": 2.938775510204082e-06,
|
2438 |
+
"loss": 0.4757,
|
2439 |
+
"step": 347
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 0.710204081632653,
|
2443 |
+
"grad_norm": 0.1748046875,
|
2444 |
+
"learning_rate": 2.9183673469387757e-06,
|
2445 |
+
"loss": 0.4942,
|
2446 |
+
"step": 348
|
2447 |
+
},
|
2448 |
+
{
|
2449 |
+
"epoch": 0.7122448979591837,
|
2450 |
+
"grad_norm": 0.2060546875,
|
2451 |
+
"learning_rate": 2.8979591836734694e-06,
|
2452 |
+
"loss": 0.4934,
|
2453 |
+
"step": 349
|
2454 |
+
},
|
2455 |
+
{
|
2456 |
+
"epoch": 0.7142857142857143,
|
2457 |
+
"grad_norm": 0.18359375,
|
2458 |
+
"learning_rate": 2.8775510204081636e-06,
|
2459 |
+
"loss": 0.4814,
|
2460 |
+
"step": 350
|
2461 |
+
},
|
2462 |
+
{
|
2463 |
+
"epoch": 0.7163265306122449,
|
2464 |
+
"grad_norm": 0.26171875,
|
2465 |
+
"learning_rate": 2.8571428571428573e-06,
|
2466 |
+
"loss": 0.497,
|
2467 |
+
"step": 351
|
2468 |
+
},
|
2469 |
+
{
|
2470 |
+
"epoch": 0.7183673469387755,
|
2471 |
+
"grad_norm": 0.1826171875,
|
2472 |
+
"learning_rate": 2.8367346938775514e-06,
|
2473 |
+
"loss": 0.4952,
|
2474 |
+
"step": 352
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 0.7204081632653061,
|
2478 |
+
"grad_norm": 0.189453125,
|
2479 |
+
"learning_rate": 2.816326530612245e-06,
|
2480 |
+
"loss": 0.4904,
|
2481 |
+
"step": 353
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 0.7224489795918367,
|
2485 |
+
"grad_norm": 0.1875,
|
2486 |
+
"learning_rate": 2.795918367346939e-06,
|
2487 |
+
"loss": 0.4774,
|
2488 |
+
"step": 354
|
2489 |
+
},
|
2490 |
+
{
|
2491 |
+
"epoch": 0.7244897959183674,
|
2492 |
+
"grad_norm": 0.1875,
|
2493 |
+
"learning_rate": 2.775510204081633e-06,
|
2494 |
+
"loss": 0.4776,
|
2495 |
+
"step": 355
|
2496 |
+
},
|
2497 |
+
{
|
2498 |
+
"epoch": 0.726530612244898,
|
2499 |
+
"grad_norm": 0.193359375,
|
2500 |
+
"learning_rate": 2.7551020408163266e-06,
|
2501 |
+
"loss": 0.5087,
|
2502 |
+
"step": 356
|
2503 |
+
},
|
2504 |
+
{
|
2505 |
+
"epoch": 0.7285714285714285,
|
2506 |
+
"grad_norm": 0.203125,
|
2507 |
+
"learning_rate": 2.7346938775510207e-06,
|
2508 |
+
"loss": 0.4768,
|
2509 |
+
"step": 357
|
2510 |
+
},
|
2511 |
+
{
|
2512 |
+
"epoch": 0.7306122448979592,
|
2513 |
+
"grad_norm": 0.193359375,
|
2514 |
+
"learning_rate": 2.7142857142857144e-06,
|
2515 |
+
"loss": 0.4974,
|
2516 |
+
"step": 358
|
2517 |
+
},
|
2518 |
+
{
|
2519 |
+
"epoch": 0.7326530612244898,
|
2520 |
+
"grad_norm": 0.1748046875,
|
2521 |
+
"learning_rate": 2.6938775510204086e-06,
|
2522 |
+
"loss": 0.4741,
|
2523 |
+
"step": 359
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 0.7346938775510204,
|
2527 |
+
"grad_norm": 0.1689453125,
|
2528 |
+
"learning_rate": 2.6734693877551023e-06,
|
2529 |
+
"loss": 0.484,
|
2530 |
+
"step": 360
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 0.736734693877551,
|
2534 |
+
"grad_norm": 0.2392578125,
|
2535 |
+
"learning_rate": 2.6530612244897964e-06,
|
2536 |
+
"loss": 0.4797,
|
2537 |
+
"step": 361
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 0.7387755102040816,
|
2541 |
+
"grad_norm": 0.2138671875,
|
2542 |
+
"learning_rate": 2.63265306122449e-06,
|
2543 |
+
"loss": 0.5066,
|
2544 |
+
"step": 362
|
2545 |
+
},
|
2546 |
+
{
|
2547 |
+
"epoch": 0.7408163265306122,
|
2548 |
+
"grad_norm": 0.1728515625,
|
2549 |
+
"learning_rate": 2.6122448979591842e-06,
|
2550 |
+
"loss": 0.4865,
|
2551 |
+
"step": 363
|
2552 |
+
},
|
2553 |
+
{
|
2554 |
+
"epoch": 0.7428571428571429,
|
2555 |
+
"grad_norm": 0.2373046875,
|
2556 |
+
"learning_rate": 2.591836734693878e-06,
|
2557 |
+
"loss": 0.4788,
|
2558 |
+
"step": 364
|
2559 |
+
},
|
2560 |
+
{
|
2561 |
+
"epoch": 0.7448979591836735,
|
2562 |
+
"grad_norm": 0.1767578125,
|
2563 |
+
"learning_rate": 2.571428571428571e-06,
|
2564 |
+
"loss": 0.4934,
|
2565 |
+
"step": 365
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 0.746938775510204,
|
2569 |
+
"grad_norm": 0.2265625,
|
2570 |
+
"learning_rate": 2.5510204081632657e-06,
|
2571 |
+
"loss": 0.5031,
|
2572 |
+
"step": 366
|
2573 |
+
},
|
2574 |
+
{
|
2575 |
+
"epoch": 0.7489795918367347,
|
2576 |
+
"grad_norm": 0.1806640625,
|
2577 |
+
"learning_rate": 2.530612244897959e-06,
|
2578 |
+
"loss": 0.5129,
|
2579 |
+
"step": 367
|
2580 |
+
},
|
2581 |
+
{
|
2582 |
+
"epoch": 0.7510204081632653,
|
2583 |
+
"grad_norm": 0.1728515625,
|
2584 |
+
"learning_rate": 2.5102040816326536e-06,
|
2585 |
+
"loss": 0.4971,
|
2586 |
+
"step": 368
|
2587 |
+
},
|
2588 |
+
{
|
2589 |
+
"epoch": 0.753061224489796,
|
2590 |
+
"grad_norm": 0.17578125,
|
2591 |
+
"learning_rate": 2.489795918367347e-06,
|
2592 |
+
"loss": 0.4849,
|
2593 |
+
"step": 369
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 0.7551020408163265,
|
2597 |
+
"grad_norm": 0.181640625,
|
2598 |
+
"learning_rate": 2.469387755102041e-06,
|
2599 |
+
"loss": 0.4725,
|
2600 |
+
"step": 370
|
2601 |
+
},
|
2602 |
+
{
|
2603 |
+
"epoch": 0.7571428571428571,
|
2604 |
+
"grad_norm": 0.19140625,
|
2605 |
+
"learning_rate": 2.4489795918367347e-06,
|
2606 |
+
"loss": 0.4832,
|
2607 |
+
"step": 371
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 0.7591836734693878,
|
2611 |
+
"grad_norm": 0.189453125,
|
2612 |
+
"learning_rate": 2.428571428571429e-06,
|
2613 |
+
"loss": 0.4779,
|
2614 |
+
"step": 372
|
2615 |
+
},
|
2616 |
+
{
|
2617 |
+
"epoch": 0.7612244897959184,
|
2618 |
+
"grad_norm": 0.1806640625,
|
2619 |
+
"learning_rate": 2.4081632653061225e-06,
|
2620 |
+
"loss": 0.479,
|
2621 |
+
"step": 373
|
2622 |
+
},
|
2623 |
+
{
|
2624 |
+
"epoch": 0.763265306122449,
|
2625 |
+
"grad_norm": 0.17578125,
|
2626 |
+
"learning_rate": 2.3877551020408166e-06,
|
2627 |
+
"loss": 0.5116,
|
2628 |
+
"step": 374
|
2629 |
+
},
|
2630 |
+
{
|
2631 |
+
"epoch": 0.7653061224489796,
|
2632 |
+
"grad_norm": 0.2158203125,
|
2633 |
+
"learning_rate": 2.3673469387755103e-06,
|
2634 |
+
"loss": 0.5151,
|
2635 |
+
"step": 375
|
2636 |
+
},
|
2637 |
+
{
|
2638 |
+
"epoch": 0.7673469387755102,
|
2639 |
+
"grad_norm": 0.2265625,
|
2640 |
+
"learning_rate": 2.3469387755102044e-06,
|
2641 |
+
"loss": 0.5034,
|
2642 |
+
"step": 376
|
2643 |
+
},
|
2644 |
+
{
|
2645 |
+
"epoch": 0.7693877551020408,
|
2646 |
+
"grad_norm": 0.2119140625,
|
2647 |
+
"learning_rate": 2.326530612244898e-06,
|
2648 |
+
"loss": 0.4843,
|
2649 |
+
"step": 377
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 0.7714285714285715,
|
2653 |
+
"grad_norm": 0.1748046875,
|
2654 |
+
"learning_rate": 2.306122448979592e-06,
|
2655 |
+
"loss": 0.4878,
|
2656 |
+
"step": 378
|
2657 |
+
},
|
2658 |
+
{
|
2659 |
+
"epoch": 0.773469387755102,
|
2660 |
+
"grad_norm": 0.1767578125,
|
2661 |
+
"learning_rate": 2.285714285714286e-06,
|
2662 |
+
"loss": 0.4909,
|
2663 |
+
"step": 379
|
2664 |
+
},
|
2665 |
+
{
|
2666 |
+
"epoch": 0.7755102040816326,
|
2667 |
+
"grad_norm": 0.193359375,
|
2668 |
+
"learning_rate": 2.2653061224489797e-06,
|
2669 |
+
"loss": 0.4908,
|
2670 |
+
"step": 380
|
2671 |
+
},
|
2672 |
+
{
|
2673 |
+
"epoch": 0.7775510204081633,
|
2674 |
+
"grad_norm": 0.1904296875,
|
2675 |
+
"learning_rate": 2.244897959183674e-06,
|
2676 |
+
"loss": 0.4776,
|
2677 |
+
"step": 381
|
2678 |
+
},
|
2679 |
+
{
|
2680 |
+
"epoch": 0.7795918367346939,
|
2681 |
+
"grad_norm": 0.1669921875,
|
2682 |
+
"learning_rate": 2.2244897959183675e-06,
|
2683 |
+
"loss": 0.4995,
|
2684 |
+
"step": 382
|
2685 |
+
},
|
2686 |
+
{
|
2687 |
+
"epoch": 0.7816326530612245,
|
2688 |
+
"grad_norm": 0.1650390625,
|
2689 |
+
"learning_rate": 2.2040816326530616e-06,
|
2690 |
+
"loss": 0.487,
|
2691 |
+
"step": 383
|
2692 |
+
},
|
2693 |
+
{
|
2694 |
+
"epoch": 0.7836734693877551,
|
2695 |
+
"grad_norm": 0.19921875,
|
2696 |
+
"learning_rate": 2.1836734693877553e-06,
|
2697 |
+
"loss": 0.4912,
|
2698 |
+
"step": 384
|
2699 |
+
},
|
2700 |
+
{
|
2701 |
+
"epoch": 0.7857142857142857,
|
2702 |
+
"grad_norm": 0.1953125,
|
2703 |
+
"learning_rate": 2.1632653061224495e-06,
|
2704 |
+
"loss": 0.4778,
|
2705 |
+
"step": 385
|
2706 |
+
},
|
2707 |
+
{
|
2708 |
+
"epoch": 0.7877551020408163,
|
2709 |
+
"grad_norm": 0.25390625,
|
2710 |
+
"learning_rate": 2.1428571428571427e-06,
|
2711 |
+
"loss": 0.4963,
|
2712 |
+
"step": 386
|
2713 |
+
},
|
2714 |
+
{
|
2715 |
+
"epoch": 0.789795918367347,
|
2716 |
+
"grad_norm": 0.22265625,
|
2717 |
+
"learning_rate": 2.122448979591837e-06,
|
2718 |
+
"loss": 0.4896,
|
2719 |
+
"step": 387
|
2720 |
+
},
|
2721 |
+
{
|
2722 |
+
"epoch": 0.7918367346938775,
|
2723 |
+
"grad_norm": 0.16796875,
|
2724 |
+
"learning_rate": 2.1020408163265306e-06,
|
2725 |
+
"loss": 0.4832,
|
2726 |
+
"step": 388
|
2727 |
+
},
|
2728 |
+
{
|
2729 |
+
"epoch": 0.7938775510204081,
|
2730 |
+
"grad_norm": 0.271484375,
|
2731 |
+
"learning_rate": 2.0816326530612247e-06,
|
2732 |
+
"loss": 0.4942,
|
2733 |
+
"step": 389
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 0.7959183673469388,
|
2737 |
+
"grad_norm": 0.1943359375,
|
2738 |
+
"learning_rate": 2.0612244897959184e-06,
|
2739 |
+
"loss": 0.4737,
|
2740 |
+
"step": 390
|
2741 |
+
},
|
2742 |
+
{
|
2743 |
+
"epoch": 0.7979591836734694,
|
2744 |
+
"grad_norm": 0.203125,
|
2745 |
+
"learning_rate": 2.0408163265306125e-06,
|
2746 |
+
"loss": 0.4932,
|
2747 |
+
"step": 391
|
2748 |
+
},
|
2749 |
+
{
|
2750 |
+
"epoch": 0.8,
|
2751 |
+
"grad_norm": 0.1884765625,
|
2752 |
+
"learning_rate": 2.020408163265306e-06,
|
2753 |
+
"loss": 0.4541,
|
2754 |
+
"step": 392
|
2755 |
+
},
|
2756 |
+
{
|
2757 |
+
"epoch": 0.8020408163265306,
|
2758 |
+
"grad_norm": 0.2216796875,
|
2759 |
+
"learning_rate": 2.0000000000000003e-06,
|
2760 |
+
"loss": 0.4942,
|
2761 |
+
"step": 393
|
2762 |
+
},
|
2763 |
+
{
|
2764 |
+
"epoch": 0.8040816326530612,
|
2765 |
+
"grad_norm": 0.1845703125,
|
2766 |
+
"learning_rate": 1.979591836734694e-06,
|
2767 |
+
"loss": 0.4994,
|
2768 |
+
"step": 394
|
2769 |
+
},
|
2770 |
+
{
|
2771 |
+
"epoch": 0.8061224489795918,
|
2772 |
+
"grad_norm": 0.201171875,
|
2773 |
+
"learning_rate": 1.9591836734693877e-06,
|
2774 |
+
"loss": 0.4963,
|
2775 |
+
"step": 395
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 0.8081632653061225,
|
2779 |
+
"grad_norm": 0.2021484375,
|
2780 |
+
"learning_rate": 1.938775510204082e-06,
|
2781 |
+
"loss": 0.4847,
|
2782 |
+
"step": 396
|
2783 |
+
},
|
2784 |
+
{
|
2785 |
+
"epoch": 0.810204081632653,
|
2786 |
+
"grad_norm": 0.2119140625,
|
2787 |
+
"learning_rate": 1.9183673469387756e-06,
|
2788 |
+
"loss": 0.4808,
|
2789 |
+
"step": 397
|
2790 |
+
},
|
2791 |
+
{
|
2792 |
+
"epoch": 0.8122448979591836,
|
2793 |
+
"grad_norm": 0.1669921875,
|
2794 |
+
"learning_rate": 1.8979591836734695e-06,
|
2795 |
+
"loss": 0.4835,
|
2796 |
+
"step": 398
|
2797 |
+
},
|
2798 |
+
{
|
2799 |
+
"epoch": 0.8142857142857143,
|
2800 |
+
"grad_norm": 0.1826171875,
|
2801 |
+
"learning_rate": 1.8775510204081634e-06,
|
2802 |
+
"loss": 0.489,
|
2803 |
+
"step": 399
|
2804 |
+
},
|
2805 |
+
{
|
2806 |
+
"epoch": 0.8163265306122449,
|
2807 |
+
"grad_norm": 0.201171875,
|
2808 |
+
"learning_rate": 1.8571428571428573e-06,
|
2809 |
+
"loss": 0.4694,
|
2810 |
+
"step": 400
|
2811 |
+
},
|
2812 |
+
{
|
2813 |
+
"epoch": 0.8183673469387756,
|
2814 |
+
"grad_norm": 0.1767578125,
|
2815 |
+
"learning_rate": 1.8367346938775512e-06,
|
2816 |
+
"loss": 0.494,
|
2817 |
+
"step": 401
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 0.8204081632653061,
|
2821 |
+
"grad_norm": 0.1875,
|
2822 |
+
"learning_rate": 1.8163265306122451e-06,
|
2823 |
+
"loss": 0.4648,
|
2824 |
+
"step": 402
|
2825 |
+
},
|
2826 |
+
{
|
2827 |
+
"epoch": 0.8224489795918367,
|
2828 |
+
"grad_norm": 0.205078125,
|
2829 |
+
"learning_rate": 1.7959183673469388e-06,
|
2830 |
+
"loss": 0.4949,
|
2831 |
+
"step": 403
|
2832 |
+
},
|
2833 |
+
{
|
2834 |
+
"epoch": 0.8244897959183674,
|
2835 |
+
"grad_norm": 0.2138671875,
|
2836 |
+
"learning_rate": 1.7755102040816327e-06,
|
2837 |
+
"loss": 0.4829,
|
2838 |
+
"step": 404
|
2839 |
+
},
|
2840 |
+
{
|
2841 |
+
"epoch": 0.826530612244898,
|
2842 |
+
"grad_norm": 0.1845703125,
|
2843 |
+
"learning_rate": 1.7551020408163267e-06,
|
2844 |
+
"loss": 0.48,
|
2845 |
+
"step": 405
|
2846 |
+
},
|
2847 |
+
{
|
2848 |
+
"epoch": 0.8285714285714286,
|
2849 |
+
"grad_norm": 0.1875,
|
2850 |
+
"learning_rate": 1.7346938775510206e-06,
|
2851 |
+
"loss": 0.4779,
|
2852 |
+
"step": 406
|
2853 |
+
},
|
2854 |
+
{
|
2855 |
+
"epoch": 0.8306122448979592,
|
2856 |
+
"grad_norm": 0.1708984375,
|
2857 |
+
"learning_rate": 1.7142857142857145e-06,
|
2858 |
+
"loss": 0.5022,
|
2859 |
+
"step": 407
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 0.8326530612244898,
|
2863 |
+
"grad_norm": 0.171875,
|
2864 |
+
"learning_rate": 1.6938775510204084e-06,
|
2865 |
+
"loss": 0.486,
|
2866 |
+
"step": 408
|
2867 |
+
},
|
2868 |
+
{
|
2869 |
+
"epoch": 0.8346938775510204,
|
2870 |
+
"grad_norm": 0.1865234375,
|
2871 |
+
"learning_rate": 1.6734693877551023e-06,
|
2872 |
+
"loss": 0.4822,
|
2873 |
+
"step": 409
|
2874 |
+
},
|
2875 |
+
{
|
2876 |
+
"epoch": 0.8367346938775511,
|
2877 |
+
"grad_norm": 0.173828125,
|
2878 |
+
"learning_rate": 1.6530612244897962e-06,
|
2879 |
+
"loss": 0.4987,
|
2880 |
+
"step": 410
|
2881 |
+
},
|
2882 |
+
{
|
2883 |
+
"epoch": 0.8387755102040816,
|
2884 |
+
"grad_norm": 0.17578125,
|
2885 |
+
"learning_rate": 1.6326530612244897e-06,
|
2886 |
+
"loss": 0.4839,
|
2887 |
+
"step": 411
|
2888 |
+
},
|
2889 |
+
{
|
2890 |
+
"epoch": 0.8408163265306122,
|
2891 |
+
"grad_norm": 0.24609375,
|
2892 |
+
"learning_rate": 1.6122448979591836e-06,
|
2893 |
+
"loss": 0.4982,
|
2894 |
+
"step": 412
|
2895 |
+
},
|
2896 |
+
{
|
2897 |
+
"epoch": 0.8428571428571429,
|
2898 |
+
"grad_norm": 0.2275390625,
|
2899 |
+
"learning_rate": 1.5918367346938775e-06,
|
2900 |
+
"loss": 0.4893,
|
2901 |
+
"step": 413
|
2902 |
+
},
|
2903 |
+
{
|
2904 |
+
"epoch": 0.8448979591836735,
|
2905 |
+
"grad_norm": 0.2041015625,
|
2906 |
+
"learning_rate": 1.5714285714285714e-06,
|
2907 |
+
"loss": 0.4957,
|
2908 |
+
"step": 414
|
2909 |
+
},
|
2910 |
+
{
|
2911 |
+
"epoch": 0.8469387755102041,
|
2912 |
+
"grad_norm": 0.1689453125,
|
2913 |
+
"learning_rate": 1.5510204081632654e-06,
|
2914 |
+
"loss": 0.4863,
|
2915 |
+
"step": 415
|
2916 |
+
},
|
2917 |
+
{
|
2918 |
+
"epoch": 0.8489795918367347,
|
2919 |
+
"grad_norm": 0.2001953125,
|
2920 |
+
"learning_rate": 1.5306122448979593e-06,
|
2921 |
+
"loss": 0.5009,
|
2922 |
+
"step": 416
|
2923 |
+
},
|
2924 |
+
{
|
2925 |
+
"epoch": 0.8510204081632653,
|
2926 |
+
"grad_norm": 0.185546875,
|
2927 |
+
"learning_rate": 1.5102040816326532e-06,
|
2928 |
+
"loss": 0.4895,
|
2929 |
+
"step": 417
|
2930 |
+
},
|
2931 |
+
{
|
2932 |
+
"epoch": 0.8530612244897959,
|
2933 |
+
"grad_norm": 0.251953125,
|
2934 |
+
"learning_rate": 1.489795918367347e-06,
|
2935 |
+
"loss": 0.48,
|
2936 |
+
"step": 418
|
2937 |
+
},
|
2938 |
+
{
|
2939 |
+
"epoch": 0.8551020408163266,
|
2940 |
+
"grad_norm": 0.185546875,
|
2941 |
+
"learning_rate": 1.469387755102041e-06,
|
2942 |
+
"loss": 0.4653,
|
2943 |
+
"step": 419
|
2944 |
+
},
|
2945 |
+
{
|
2946 |
+
"epoch": 0.8571428571428571,
|
2947 |
+
"grad_norm": 0.1728515625,
|
2948 |
+
"learning_rate": 1.4489795918367347e-06,
|
2949 |
+
"loss": 0.4902,
|
2950 |
+
"step": 420
|
2951 |
+
},
|
2952 |
+
{
|
2953 |
+
"epoch": 0.8591836734693877,
|
2954 |
+
"grad_norm": 0.1708984375,
|
2955 |
+
"learning_rate": 1.4285714285714286e-06,
|
2956 |
+
"loss": 0.4849,
|
2957 |
+
"step": 421
|
2958 |
+
},
|
2959 |
+
{
|
2960 |
+
"epoch": 0.8612244897959184,
|
2961 |
+
"grad_norm": 0.189453125,
|
2962 |
+
"learning_rate": 1.4081632653061225e-06,
|
2963 |
+
"loss": 0.4916,
|
2964 |
+
"step": 422
|
2965 |
+
},
|
2966 |
+
{
|
2967 |
+
"epoch": 0.863265306122449,
|
2968 |
+
"grad_norm": 0.177734375,
|
2969 |
+
"learning_rate": 1.3877551020408165e-06,
|
2970 |
+
"loss": 0.4879,
|
2971 |
+
"step": 423
|
2972 |
+
},
|
2973 |
+
{
|
2974 |
+
"epoch": 0.8653061224489796,
|
2975 |
+
"grad_norm": 0.2041015625,
|
2976 |
+
"learning_rate": 1.3673469387755104e-06,
|
2977 |
+
"loss": 0.5008,
|
2978 |
+
"step": 424
|
2979 |
+
},
|
2980 |
+
{
|
2981 |
+
"epoch": 0.8673469387755102,
|
2982 |
+
"grad_norm": 0.177734375,
|
2983 |
+
"learning_rate": 1.3469387755102043e-06,
|
2984 |
+
"loss": 0.4752,
|
2985 |
+
"step": 425
|
2986 |
+
},
|
2987 |
+
{
|
2988 |
+
"epoch": 0.8693877551020408,
|
2989 |
+
"grad_norm": 0.16015625,
|
2990 |
+
"learning_rate": 1.3265306122448982e-06,
|
2991 |
+
"loss": 0.4856,
|
2992 |
+
"step": 426
|
2993 |
+
},
|
2994 |
+
{
|
2995 |
+
"epoch": 0.8714285714285714,
|
2996 |
+
"grad_norm": 0.2138671875,
|
2997 |
+
"learning_rate": 1.3061224489795921e-06,
|
2998 |
+
"loss": 0.483,
|
2999 |
+
"step": 427
|
3000 |
+
},
|
3001 |
+
{
|
3002 |
+
"epoch": 0.8734693877551021,
|
3003 |
+
"grad_norm": 0.189453125,
|
3004 |
+
"learning_rate": 1.2857142857142856e-06,
|
3005 |
+
"loss": 0.4752,
|
3006 |
+
"step": 428
|
3007 |
+
},
|
3008 |
+
{
|
3009 |
+
"epoch": 0.8755102040816326,
|
3010 |
+
"grad_norm": 0.1962890625,
|
3011 |
+
"learning_rate": 1.2653061224489795e-06,
|
3012 |
+
"loss": 0.4982,
|
3013 |
+
"step": 429
|
3014 |
+
},
|
3015 |
+
{
|
3016 |
+
"epoch": 0.8775510204081632,
|
3017 |
+
"grad_norm": 0.1875,
|
3018 |
+
"learning_rate": 1.2448979591836734e-06,
|
3019 |
+
"loss": 0.4767,
|
3020 |
+
"step": 430
|
3021 |
+
},
|
3022 |
+
{
|
3023 |
+
"epoch": 0.8795918367346939,
|
3024 |
+
"grad_norm": 0.1708984375,
|
3025 |
+
"learning_rate": 1.2244897959183673e-06,
|
3026 |
+
"loss": 0.4879,
|
3027 |
+
"step": 431
|
3028 |
+
},
|
3029 |
+
{
|
3030 |
+
"epoch": 0.8816326530612245,
|
3031 |
+
"grad_norm": 0.1669921875,
|
3032 |
+
"learning_rate": 1.2040816326530612e-06,
|
3033 |
+
"loss": 0.4881,
|
3034 |
+
"step": 432
|
3035 |
+
},
|
3036 |
+
{
|
3037 |
+
"epoch": 0.8836734693877552,
|
3038 |
+
"grad_norm": 0.1630859375,
|
3039 |
+
"learning_rate": 1.1836734693877552e-06,
|
3040 |
+
"loss": 0.4863,
|
3041 |
+
"step": 433
|
3042 |
+
},
|
3043 |
+
{
|
3044 |
+
"epoch": 0.8857142857142857,
|
3045 |
+
"grad_norm": 0.212890625,
|
3046 |
+
"learning_rate": 1.163265306122449e-06,
|
3047 |
+
"loss": 0.5022,
|
3048 |
+
"step": 434
|
3049 |
+
},
|
3050 |
+
{
|
3051 |
+
"epoch": 0.8877551020408163,
|
3052 |
+
"grad_norm": 0.181640625,
|
3053 |
+
"learning_rate": 1.142857142857143e-06,
|
3054 |
+
"loss": 0.4908,
|
3055 |
+
"step": 435
|
3056 |
+
},
|
3057 |
+
{
|
3058 |
+
"epoch": 0.889795918367347,
|
3059 |
+
"grad_norm": 0.17578125,
|
3060 |
+
"learning_rate": 1.122448979591837e-06,
|
3061 |
+
"loss": 0.4884,
|
3062 |
+
"step": 436
|
3063 |
+
},
|
3064 |
+
{
|
3065 |
+
"epoch": 0.8918367346938776,
|
3066 |
+
"grad_norm": 0.173828125,
|
3067 |
+
"learning_rate": 1.1020408163265308e-06,
|
3068 |
+
"loss": 0.489,
|
3069 |
+
"step": 437
|
3070 |
+
},
|
3071 |
+
{
|
3072 |
+
"epoch": 0.8938775510204081,
|
3073 |
+
"grad_norm": 0.193359375,
|
3074 |
+
"learning_rate": 1.0816326530612247e-06,
|
3075 |
+
"loss": 0.4821,
|
3076 |
+
"step": 438
|
3077 |
+
},
|
3078 |
+
{
|
3079 |
+
"epoch": 0.8959183673469387,
|
3080 |
+
"grad_norm": 0.1689453125,
|
3081 |
+
"learning_rate": 1.0612244897959184e-06,
|
3082 |
+
"loss": 0.4748,
|
3083 |
+
"step": 439
|
3084 |
+
},
|
3085 |
+
{
|
3086 |
+
"epoch": 0.8979591836734694,
|
3087 |
+
"grad_norm": 0.181640625,
|
3088 |
+
"learning_rate": 1.0408163265306123e-06,
|
3089 |
+
"loss": 0.4757,
|
3090 |
+
"step": 440
|
3091 |
+
},
|
3092 |
+
{
|
3093 |
+
"epoch": 0.9,
|
3094 |
+
"grad_norm": 0.189453125,
|
3095 |
+
"learning_rate": 1.0204081632653063e-06,
|
3096 |
+
"loss": 0.4986,
|
3097 |
+
"step": 441
|
3098 |
+
},
|
3099 |
+
{
|
3100 |
+
"epoch": 0.9020408163265307,
|
3101 |
+
"grad_norm": 0.203125,
|
3102 |
+
"learning_rate": 1.0000000000000002e-06,
|
3103 |
+
"loss": 0.5032,
|
3104 |
+
"step": 442
|
3105 |
+
},
|
3106 |
+
{
|
3107 |
+
"epoch": 0.9040816326530612,
|
3108 |
+
"grad_norm": 0.220703125,
|
3109 |
+
"learning_rate": 9.795918367346939e-07,
|
3110 |
+
"loss": 0.4933,
|
3111 |
+
"step": 443
|
3112 |
+
},
|
3113 |
+
{
|
3114 |
+
"epoch": 0.9061224489795918,
|
3115 |
+
"grad_norm": 0.173828125,
|
3116 |
+
"learning_rate": 9.591836734693878e-07,
|
3117 |
+
"loss": 0.4711,
|
3118 |
+
"step": 444
|
3119 |
+
},
|
3120 |
+
{
|
3121 |
+
"epoch": 0.9081632653061225,
|
3122 |
+
"grad_norm": 0.19921875,
|
3123 |
+
"learning_rate": 9.387755102040817e-07,
|
3124 |
+
"loss": 0.4948,
|
3125 |
+
"step": 445
|
3126 |
+
},
|
3127 |
+
{
|
3128 |
+
"epoch": 0.9102040816326531,
|
3129 |
+
"grad_norm": 0.201171875,
|
3130 |
+
"learning_rate": 9.183673469387756e-07,
|
3131 |
+
"loss": 0.4721,
|
3132 |
+
"step": 446
|
3133 |
+
},
|
3134 |
+
{
|
3135 |
+
"epoch": 0.9122448979591836,
|
3136 |
+
"grad_norm": 0.17578125,
|
3137 |
+
"learning_rate": 8.979591836734694e-07,
|
3138 |
+
"loss": 0.5054,
|
3139 |
+
"step": 447
|
3140 |
+
},
|
3141 |
+
{
|
3142 |
+
"epoch": 0.9142857142857143,
|
3143 |
+
"grad_norm": 0.16796875,
|
3144 |
+
"learning_rate": 8.775510204081633e-07,
|
3145 |
+
"loss": 0.474,
|
3146 |
+
"step": 448
|
3147 |
+
},
|
3148 |
+
{
|
3149 |
+
"epoch": 0.9163265306122449,
|
3150 |
+
"grad_norm": 0.17578125,
|
3151 |
+
"learning_rate": 8.571428571428572e-07,
|
3152 |
+
"loss": 0.4803,
|
3153 |
+
"step": 449
|
3154 |
+
},
|
3155 |
+
{
|
3156 |
+
"epoch": 0.9183673469387755,
|
3157 |
+
"grad_norm": 0.1982421875,
|
3158 |
+
"learning_rate": 8.367346938775512e-07,
|
3159 |
+
"loss": 0.5031,
|
3160 |
+
"step": 450
|
3161 |
+
},
|
3162 |
+
{
|
3163 |
+
"epoch": 0.9204081632653062,
|
3164 |
+
"grad_norm": 0.228515625,
|
3165 |
+
"learning_rate": 8.163265306122449e-07,
|
3166 |
+
"loss": 0.4913,
|
3167 |
+
"step": 451
|
3168 |
+
},
|
3169 |
+
{
|
3170 |
+
"epoch": 0.9224489795918367,
|
3171 |
+
"grad_norm": 0.173828125,
|
3172 |
+
"learning_rate": 7.959183673469388e-07,
|
3173 |
+
"loss": 0.4708,
|
3174 |
+
"step": 452
|
3175 |
+
},
|
3176 |
+
{
|
3177 |
+
"epoch": 0.9244897959183673,
|
3178 |
+
"grad_norm": 0.1806640625,
|
3179 |
+
"learning_rate": 7.755102040816327e-07,
|
3180 |
+
"loss": 0.4783,
|
3181 |
+
"step": 453
|
3182 |
+
},
|
3183 |
+
{
|
3184 |
+
"epoch": 0.926530612244898,
|
3185 |
+
"grad_norm": 0.1796875,
|
3186 |
+
"learning_rate": 7.551020408163266e-07,
|
3187 |
+
"loss": 0.4929,
|
3188 |
+
"step": 454
|
3189 |
+
},
|
3190 |
+
{
|
3191 |
+
"epoch": 0.9285714285714286,
|
3192 |
+
"grad_norm": 0.171875,
|
3193 |
+
"learning_rate": 7.346938775510205e-07,
|
3194 |
+
"loss": 0.4846,
|
3195 |
+
"step": 455
|
3196 |
+
},
|
3197 |
+
{
|
3198 |
+
"epoch": 0.9306122448979591,
|
3199 |
+
"grad_norm": 0.25390625,
|
3200 |
+
"learning_rate": 7.142857142857143e-07,
|
3201 |
+
"loss": 0.4431,
|
3202 |
+
"step": 456
|
3203 |
+
},
|
3204 |
+
{
|
3205 |
+
"epoch": 0.9326530612244898,
|
3206 |
+
"grad_norm": 0.173828125,
|
3207 |
+
"learning_rate": 6.938775510204082e-07,
|
3208 |
+
"loss": 0.4878,
|
3209 |
+
"step": 457
|
3210 |
+
},
|
3211 |
+
{
|
3212 |
+
"epoch": 0.9346938775510204,
|
3213 |
+
"grad_norm": 0.1796875,
|
3214 |
+
"learning_rate": 6.734693877551021e-07,
|
3215 |
+
"loss": 0.4806,
|
3216 |
+
"step": 458
|
3217 |
+
},
|
3218 |
+
{
|
3219 |
+
"epoch": 0.936734693877551,
|
3220 |
+
"grad_norm": 0.177734375,
|
3221 |
+
"learning_rate": 6.530612244897961e-07,
|
3222 |
+
"loss": 0.492,
|
3223 |
+
"step": 459
|
3224 |
+
},
|
3225 |
+
{
|
3226 |
+
"epoch": 0.9387755102040817,
|
3227 |
+
"grad_norm": 0.171875,
|
3228 |
+
"learning_rate": 6.326530612244898e-07,
|
3229 |
+
"loss": 0.4792,
|
3230 |
+
"step": 460
|
3231 |
+
},
|
3232 |
+
{
|
3233 |
+
"epoch": 0.9408163265306122,
|
3234 |
+
"grad_norm": 0.177734375,
|
3235 |
+
"learning_rate": 6.122448979591837e-07,
|
3236 |
+
"loss": 0.4876,
|
3237 |
+
"step": 461
|
3238 |
+
},
|
3239 |
+
{
|
3240 |
+
"epoch": 0.9428571428571428,
|
3241 |
+
"grad_norm": 0.171875,
|
3242 |
+
"learning_rate": 5.918367346938776e-07,
|
3243 |
+
"loss": 0.4853,
|
3244 |
+
"step": 462
|
3245 |
+
},
|
3246 |
+
{
|
3247 |
+
"epoch": 0.9448979591836735,
|
3248 |
+
"grad_norm": 0.2021484375,
|
3249 |
+
"learning_rate": 5.714285714285715e-07,
|
3250 |
+
"loss": 0.4884,
|
3251 |
+
"step": 463
|
3252 |
+
},
|
3253 |
+
{
|
3254 |
+
"epoch": 0.9469387755102041,
|
3255 |
+
"grad_norm": 0.197265625,
|
3256 |
+
"learning_rate": 5.510204081632654e-07,
|
3257 |
+
"loss": 0.4944,
|
3258 |
+
"step": 464
|
3259 |
+
},
|
3260 |
+
{
|
3261 |
+
"epoch": 0.9489795918367347,
|
3262 |
+
"grad_norm": 0.2197265625,
|
3263 |
+
"learning_rate": 5.306122448979592e-07,
|
3264 |
+
"loss": 0.4984,
|
3265 |
+
"step": 465
|
3266 |
+
},
|
3267 |
+
{
|
3268 |
+
"epoch": 0.9510204081632653,
|
3269 |
+
"grad_norm": 0.1669921875,
|
3270 |
+
"learning_rate": 5.102040816326531e-07,
|
3271 |
+
"loss": 0.4728,
|
3272 |
+
"step": 466
|
3273 |
+
},
|
3274 |
+
{
|
3275 |
+
"epoch": 0.9530612244897959,
|
3276 |
+
"grad_norm": 0.17578125,
|
3277 |
+
"learning_rate": 4.897959183673469e-07,
|
3278 |
+
"loss": 0.4906,
|
3279 |
+
"step": 467
|
3280 |
+
},
|
3281 |
+
{
|
3282 |
+
"epoch": 0.9551020408163265,
|
3283 |
+
"grad_norm": 0.181640625,
|
3284 |
+
"learning_rate": 4.6938775510204085e-07,
|
3285 |
+
"loss": 0.5009,
|
3286 |
+
"step": 468
|
3287 |
+
},
|
3288 |
+
{
|
3289 |
+
"epoch": 0.9571428571428572,
|
3290 |
+
"grad_norm": 0.1787109375,
|
3291 |
+
"learning_rate": 4.489795918367347e-07,
|
3292 |
+
"loss": 0.4978,
|
3293 |
+
"step": 469
|
3294 |
+
},
|
3295 |
+
{
|
3296 |
+
"epoch": 0.9591836734693877,
|
3297 |
+
"grad_norm": 0.1845703125,
|
3298 |
+
"learning_rate": 4.285714285714286e-07,
|
3299 |
+
"loss": 0.464,
|
3300 |
+
"step": 470
|
3301 |
+
},
|
3302 |
+
{
|
3303 |
+
"epoch": 0.9612244897959183,
|
3304 |
+
"grad_norm": 0.2021484375,
|
3305 |
+
"learning_rate": 4.0816326530612243e-07,
|
3306 |
+
"loss": 0.4881,
|
3307 |
+
"step": 471
|
3308 |
+
},
|
3309 |
+
{
|
3310 |
+
"epoch": 0.963265306122449,
|
3311 |
+
"grad_norm": 0.255859375,
|
3312 |
+
"learning_rate": 3.8775510204081634e-07,
|
3313 |
+
"loss": 0.4995,
|
3314 |
+
"step": 472
|
3315 |
+
},
|
3316 |
+
{
|
3317 |
+
"epoch": 0.9653061224489796,
|
3318 |
+
"grad_norm": 0.1982421875,
|
3319 |
+
"learning_rate": 3.6734693877551025e-07,
|
3320 |
+
"loss": 0.4848,
|
3321 |
+
"step": 473
|
3322 |
+
},
|
3323 |
+
{
|
3324 |
+
"epoch": 0.9673469387755103,
|
3325 |
+
"grad_norm": 0.169921875,
|
3326 |
+
"learning_rate": 3.469387755102041e-07,
|
3327 |
+
"loss": 0.4835,
|
3328 |
+
"step": 474
|
3329 |
+
},
|
3330 |
+
{
|
3331 |
+
"epoch": 0.9693877551020408,
|
3332 |
+
"grad_norm": 0.181640625,
|
3333 |
+
"learning_rate": 3.2653061224489803e-07,
|
3334 |
+
"loss": 0.5012,
|
3335 |
+
"step": 475
|
3336 |
+
},
|
3337 |
+
{
|
3338 |
+
"epoch": 0.9714285714285714,
|
3339 |
+
"grad_norm": 0.1572265625,
|
3340 |
+
"learning_rate": 3.0612244897959183e-07,
|
3341 |
+
"loss": 0.4772,
|
3342 |
+
"step": 476
|
3343 |
+
},
|
3344 |
+
{
|
3345 |
+
"epoch": 0.9734693877551021,
|
3346 |
+
"grad_norm": 0.169921875,
|
3347 |
+
"learning_rate": 2.8571428571428575e-07,
|
3348 |
+
"loss": 0.4963,
|
3349 |
+
"step": 477
|
3350 |
+
},
|
3351 |
+
{
|
3352 |
+
"epoch": 0.9755102040816327,
|
3353 |
+
"grad_norm": 0.1650390625,
|
3354 |
+
"learning_rate": 2.653061224489796e-07,
|
3355 |
+
"loss": 0.486,
|
3356 |
+
"step": 478
|
3357 |
+
},
|
3358 |
+
{
|
3359 |
+
"epoch": 0.9775510204081632,
|
3360 |
+
"grad_norm": 0.173828125,
|
3361 |
+
"learning_rate": 2.4489795918367347e-07,
|
3362 |
+
"loss": 0.4649,
|
3363 |
+
"step": 479
|
3364 |
+
},
|
3365 |
+
{
|
3366 |
+
"epoch": 0.9795918367346939,
|
3367 |
+
"grad_norm": 0.2265625,
|
3368 |
+
"learning_rate": 2.2448979591836735e-07,
|
3369 |
+
"loss": 0.4843,
|
3370 |
+
"step": 480
|
3371 |
+
},
|
3372 |
+
{
|
3373 |
+
"epoch": 0.9816326530612245,
|
3374 |
+
"grad_norm": 0.1982421875,
|
3375 |
+
"learning_rate": 2.0408163265306121e-07,
|
3376 |
+
"loss": 0.5108,
|
3377 |
+
"step": 481
|
3378 |
+
},
|
3379 |
+
{
|
3380 |
+
"epoch": 0.9836734693877551,
|
3381 |
+
"grad_norm": 0.1689453125,
|
3382 |
+
"learning_rate": 1.8367346938775513e-07,
|
3383 |
+
"loss": 0.4969,
|
3384 |
+
"step": 482
|
3385 |
+
},
|
3386 |
+
{
|
3387 |
+
"epoch": 0.9857142857142858,
|
3388 |
+
"grad_norm": 0.224609375,
|
3389 |
+
"learning_rate": 1.6326530612244901e-07,
|
3390 |
+
"loss": 0.4941,
|
3391 |
+
"step": 483
|
3392 |
+
},
|
3393 |
+
{
|
3394 |
+
"epoch": 0.9877551020408163,
|
3395 |
+
"grad_norm": 0.1787109375,
|
3396 |
+
"learning_rate": 1.4285714285714287e-07,
|
3397 |
+
"loss": 0.4895,
|
3398 |
+
"step": 484
|
3399 |
+
},
|
3400 |
+
{
|
3401 |
+
"epoch": 0.9897959183673469,
|
3402 |
+
"grad_norm": 0.17578125,
|
3403 |
+
"learning_rate": 1.2244897959183673e-07,
|
3404 |
+
"loss": 0.5014,
|
3405 |
+
"step": 485
|
3406 |
+
},
|
3407 |
+
{
|
3408 |
+
"epoch": 0.9918367346938776,
|
3409 |
+
"grad_norm": 0.177734375,
|
3410 |
+
"learning_rate": 1.0204081632653061e-07,
|
3411 |
+
"loss": 0.4883,
|
3412 |
+
"step": 486
|
3413 |
+
},
|
3414 |
+
{
|
3415 |
+
"epoch": 0.9938775510204082,
|
3416 |
+
"grad_norm": 0.171875,
|
3417 |
+
"learning_rate": 8.163265306122451e-08,
|
3418 |
+
"loss": 0.4971,
|
3419 |
+
"step": 487
|
3420 |
+
},
|
3421 |
+
{
|
3422 |
+
"epoch": 0.9959183673469387,
|
3423 |
+
"grad_norm": 0.1943359375,
|
3424 |
+
"learning_rate": 6.122448979591837e-08,
|
3425 |
+
"loss": 0.5062,
|
3426 |
+
"step": 488
|
3427 |
+
},
|
3428 |
+
{
|
3429 |
+
"epoch": 0.9979591836734694,
|
3430 |
+
"grad_norm": 0.1640625,
|
3431 |
+
"learning_rate": 4.0816326530612253e-08,
|
3432 |
+
"loss": 0.4818,
|
3433 |
+
"step": 489
|
3434 |
+
},
|
3435 |
+
{
|
3436 |
+
"epoch": 1.0,
|
3437 |
+
"grad_norm": 0.197265625,
|
3438 |
+
"learning_rate": 2.0408163265306127e-08,
|
3439 |
+
"loss": 0.4745,
|
3440 |
+
"step": 490
|
3441 |
+
},
|
3442 |
+
{
|
3443 |
+
"epoch": 1.0,
|
3444 |
+
"eval_loss": 0.4921317994594574,
|
3445 |
+
"eval_runtime": 17.5595,
|
3446 |
+
"eval_samples_per_second": 2.791,
|
3447 |
+
"eval_steps_per_second": 0.399,
|
3448 |
+
"step": 490
|
3449 |
+
}
|
3450 |
+
],
|
3451 |
+
"logging_steps": 1.0,
|
3452 |
+
"max_steps": 490,
|
3453 |
+
"num_input_tokens_seen": 0,
|
3454 |
+
"num_train_epochs": 1,
|
3455 |
+
"save_steps": 0,
|
3456 |
+
"stateful_callbacks": {
|
3457 |
+
"TrainerControl": {
|
3458 |
+
"args": {
|
3459 |
+
"should_epoch_stop": false,
|
3460 |
+
"should_evaluate": false,
|
3461 |
+
"should_log": false,
|
3462 |
+
"should_save": true,
|
3463 |
+
"should_training_stop": true
|
3464 |
+
},
|
3465 |
+
"attributes": {}
|
3466 |
+
}
|
3467 |
+
},
|
3468 |
+
"total_flos": 1.5692183426385838e+18,
|
3469 |
+
"train_batch_size": 1,
|
3470 |
+
"trial_name": null,
|
3471 |
+
"trial_params": null
|
3472 |
+
}
|