Commit
·
130eb1f
1
Parent(s):
5196783
Upload 8 files
Browse files- README.md +21 -0
- adapter_config.json +26 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +1907 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: False
|
| 10 |
+
- load_in_4bit: True
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: nf4
|
| 16 |
+
- bnb_4bit_use_double_quant: True
|
| 17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.6.0.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 16,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"k_proj",
|
| 19 |
+
"v_proj",
|
| 20 |
+
"gate_proj",
|
| 21 |
+
"up_proj",
|
| 22 |
+
"down_proj",
|
| 23 |
+
"lm_head"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87c7618c9f93d96a81c4c950d004f8ea727ada0223db8604dbeef4730d13670c
|
| 3 |
+
size 145579733
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d135f8d64764faeb1a8acd9d7349578f85379a1ee14503ce1d004318774ed1f
|
| 3 |
+
size 73315495
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bae24c78ae9a40eb23b6c22cea6c4ef3853554fc3dca4124c70160fb4776e4cd
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:673b3f08c3f4ccc6c91c0ef0b0e0e10e67ec6a38b17664157f4e94e8533aef87
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1907 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.496,
|
| 5 |
+
"eval_steps": 156,
|
| 6 |
+
"global_step": 312,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 0.0001,
|
| 14 |
+
"loss": 1.2612,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 0.0002,
|
| 20 |
+
"loss": 0.5839,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 0.0001994638069705094,
|
| 26 |
+
"loss": 1.2718,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 0.00019892761394101877,
|
| 32 |
+
"loss": 0.9663,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.04,
|
| 37 |
+
"learning_rate": 0.00019839142091152817,
|
| 38 |
+
"loss": 0.8353,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.05,
|
| 43 |
+
"learning_rate": 0.00019785522788203755,
|
| 44 |
+
"loss": 0.4235,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.06,
|
| 49 |
+
"learning_rate": 0.00019731903485254693,
|
| 50 |
+
"loss": 0.3499,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.06,
|
| 55 |
+
"learning_rate": 0.0001967828418230563,
|
| 56 |
+
"loss": 0.8885,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.07,
|
| 61 |
+
"learning_rate": 0.00019624664879356568,
|
| 62 |
+
"loss": 0.6318,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.08,
|
| 67 |
+
"learning_rate": 0.00019571045576407506,
|
| 68 |
+
"loss": 0.7978,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.09,
|
| 73 |
+
"learning_rate": 0.00019517426273458447,
|
| 74 |
+
"loss": 0.3304,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.1,
|
| 79 |
+
"learning_rate": 0.00019463806970509384,
|
| 80 |
+
"loss": 0.8138,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.1,
|
| 85 |
+
"learning_rate": 0.00019410187667560322,
|
| 86 |
+
"loss": 0.3049,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.11,
|
| 91 |
+
"learning_rate": 0.0001935656836461126,
|
| 92 |
+
"loss": 0.9467,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.12,
|
| 97 |
+
"learning_rate": 0.00019302949061662198,
|
| 98 |
+
"loss": 0.4926,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.13,
|
| 103 |
+
"learning_rate": 0.00019249329758713138,
|
| 104 |
+
"loss": 0.2896,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.14,
|
| 109 |
+
"learning_rate": 0.00019195710455764076,
|
| 110 |
+
"loss": 0.314,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.14,
|
| 115 |
+
"learning_rate": 0.00019142091152815014,
|
| 116 |
+
"loss": 0.6319,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.15,
|
| 121 |
+
"learning_rate": 0.00019088471849865952,
|
| 122 |
+
"loss": 0.8047,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.16,
|
| 127 |
+
"learning_rate": 0.0001903485254691689,
|
| 128 |
+
"loss": 0.6664,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.17,
|
| 133 |
+
"learning_rate": 0.00018981233243967828,
|
| 134 |
+
"loss": 0.7509,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.18,
|
| 139 |
+
"learning_rate": 0.00018927613941018768,
|
| 140 |
+
"loss": 0.572,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.18,
|
| 145 |
+
"learning_rate": 0.00018873994638069706,
|
| 146 |
+
"loss": 0.6726,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.19,
|
| 151 |
+
"learning_rate": 0.00018820375335120644,
|
| 152 |
+
"loss": 0.2929,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.2,
|
| 157 |
+
"learning_rate": 0.00018766756032171581,
|
| 158 |
+
"loss": 0.5821,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.21,
|
| 163 |
+
"learning_rate": 0.0001871313672922252,
|
| 164 |
+
"loss": 0.5325,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.22,
|
| 169 |
+
"learning_rate": 0.00018659517426273457,
|
| 170 |
+
"loss": 0.4568,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.22,
|
| 175 |
+
"learning_rate": 0.00018605898123324398,
|
| 176 |
+
"loss": 0.2517,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.23,
|
| 181 |
+
"learning_rate": 0.00018552278820375335,
|
| 182 |
+
"loss": 0.5343,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.24,
|
| 187 |
+
"learning_rate": 0.00018498659517426273,
|
| 188 |
+
"loss": 0.3203,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.25,
|
| 193 |
+
"learning_rate": 0.0001844504021447721,
|
| 194 |
+
"loss": 0.0,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.26,
|
| 199 |
+
"learning_rate": 0.0001839142091152815,
|
| 200 |
+
"loss": 0.2905,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.26,
|
| 205 |
+
"learning_rate": 0.0001833780160857909,
|
| 206 |
+
"loss": 0.5738,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.27,
|
| 211 |
+
"learning_rate": 0.0001828418230563003,
|
| 212 |
+
"loss": 0.5445,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.28,
|
| 217 |
+
"learning_rate": 0.00018230563002680968,
|
| 218 |
+
"loss": 0.6075,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.29,
|
| 223 |
+
"learning_rate": 0.00018176943699731906,
|
| 224 |
+
"loss": 0.6869,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.3,
|
| 229 |
+
"learning_rate": 0.00018123324396782843,
|
| 230 |
+
"loss": 0.2808,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.3,
|
| 235 |
+
"learning_rate": 0.0001806970509383378,
|
| 236 |
+
"loss": 0.6005,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.31,
|
| 241 |
+
"learning_rate": 0.0001801608579088472,
|
| 242 |
+
"loss": 0.5839,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.32,
|
| 247 |
+
"learning_rate": 0.0001796246648793566,
|
| 248 |
+
"loss": 0.5602,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.33,
|
| 253 |
+
"learning_rate": 0.00017908847184986597,
|
| 254 |
+
"loss": 0.5986,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.34,
|
| 259 |
+
"learning_rate": 0.00017855227882037535,
|
| 260 |
+
"loss": 0.3701,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.34,
|
| 265 |
+
"learning_rate": 0.00017801608579088473,
|
| 266 |
+
"loss": 0.2545,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.35,
|
| 271 |
+
"learning_rate": 0.0001774798927613941,
|
| 272 |
+
"loss": 0.6094,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.36,
|
| 277 |
+
"learning_rate": 0.0001769436997319035,
|
| 278 |
+
"loss": 0.0,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.37,
|
| 283 |
+
"learning_rate": 0.0001764075067024129,
|
| 284 |
+
"loss": 0.4668,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.38,
|
| 289 |
+
"learning_rate": 0.00017587131367292227,
|
| 290 |
+
"loss": 0.2302,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.38,
|
| 295 |
+
"learning_rate": 0.00017533512064343165,
|
| 296 |
+
"loss": 0.2882,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.39,
|
| 301 |
+
"learning_rate": 0.00017479892761394103,
|
| 302 |
+
"loss": 0.2486,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.4,
|
| 307 |
+
"learning_rate": 0.0001742627345844504,
|
| 308 |
+
"loss": 0.2614,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.41,
|
| 313 |
+
"learning_rate": 0.0001737265415549598,
|
| 314 |
+
"loss": 0.237,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.42,
|
| 319 |
+
"learning_rate": 0.0001731903485254692,
|
| 320 |
+
"loss": 0.5986,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.42,
|
| 325 |
+
"learning_rate": 0.00017265415549597856,
|
| 326 |
+
"loss": 0.0,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.43,
|
| 331 |
+
"learning_rate": 0.00017211796246648794,
|
| 332 |
+
"loss": 0.5648,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.44,
|
| 337 |
+
"learning_rate": 0.00017158176943699732,
|
| 338 |
+
"loss": 0.5096,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.45,
|
| 343 |
+
"learning_rate": 0.00017104557640750673,
|
| 344 |
+
"loss": 0.5139,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.46,
|
| 349 |
+
"learning_rate": 0.0001705093833780161,
|
| 350 |
+
"loss": 0.2226,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.46,
|
| 355 |
+
"learning_rate": 0.00016997319034852548,
|
| 356 |
+
"loss": 0.4839,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.47,
|
| 361 |
+
"learning_rate": 0.00016943699731903486,
|
| 362 |
+
"loss": 0.5375,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.48,
|
| 367 |
+
"learning_rate": 0.00016890080428954424,
|
| 368 |
+
"loss": 0.5792,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.49,
|
| 373 |
+
"learning_rate": 0.00016836461126005362,
|
| 374 |
+
"loss": 0.6151,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.5,
|
| 379 |
+
"learning_rate": 0.00016782841823056302,
|
| 380 |
+
"loss": 0.5358,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.5,
|
| 385 |
+
"learning_rate": 0.0001672922252010724,
|
| 386 |
+
"loss": 0.4993,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.51,
|
| 391 |
+
"learning_rate": 0.00016675603217158178,
|
| 392 |
+
"loss": 0.2054,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.52,
|
| 397 |
+
"learning_rate": 0.00016621983914209116,
|
| 398 |
+
"loss": 0.2973,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.53,
|
| 403 |
+
"learning_rate": 0.00016568364611260053,
|
| 404 |
+
"loss": 0.4578,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.54,
|
| 409 |
+
"learning_rate": 0.00016514745308310994,
|
| 410 |
+
"loss": 0.4827,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.54,
|
| 415 |
+
"learning_rate": 0.00016461126005361932,
|
| 416 |
+
"loss": 0.2362,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.55,
|
| 421 |
+
"learning_rate": 0.0001640750670241287,
|
| 422 |
+
"loss": 0.2993,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.56,
|
| 427 |
+
"learning_rate": 0.00016353887399463807,
|
| 428 |
+
"loss": 0.6205,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.57,
|
| 433 |
+
"learning_rate": 0.00016300268096514745,
|
| 434 |
+
"loss": 0.5475,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.58,
|
| 439 |
+
"learning_rate": 0.00016246648793565683,
|
| 440 |
+
"loss": 0.4761,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.58,
|
| 445 |
+
"learning_rate": 0.00016193029490616624,
|
| 446 |
+
"loss": 0.2454,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.59,
|
| 451 |
+
"learning_rate": 0.00016139410187667561,
|
| 452 |
+
"loss": 0.559,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.6,
|
| 457 |
+
"learning_rate": 0.000160857908847185,
|
| 458 |
+
"loss": 0.4535,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.61,
|
| 463 |
+
"learning_rate": 0.00016032171581769437,
|
| 464 |
+
"loss": 0.5401,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.62,
|
| 469 |
+
"learning_rate": 0.00015978552278820375,
|
| 470 |
+
"loss": 0.4684,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.62,
|
| 475 |
+
"learning_rate": 0.00015924932975871313,
|
| 476 |
+
"loss": 0.2701,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.63,
|
| 481 |
+
"learning_rate": 0.00015871313672922253,
|
| 482 |
+
"loss": 0.2443,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.64,
|
| 487 |
+
"learning_rate": 0.0001581769436997319,
|
| 488 |
+
"loss": 0.3073,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.65,
|
| 493 |
+
"learning_rate": 0.0001576407506702413,
|
| 494 |
+
"loss": 0.3229,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.66,
|
| 499 |
+
"learning_rate": 0.00015710455764075067,
|
| 500 |
+
"loss": 0.4567,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.66,
|
| 505 |
+
"learning_rate": 0.00015656836461126004,
|
| 506 |
+
"loss": 0.3031,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.67,
|
| 511 |
+
"learning_rate": 0.00015603217158176945,
|
| 512 |
+
"loss": 0.2604,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.68,
|
| 517 |
+
"learning_rate": 0.00015549597855227883,
|
| 518 |
+
"loss": 0.5654,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.69,
|
| 523 |
+
"learning_rate": 0.0001549597855227882,
|
| 524 |
+
"loss": 0.2723,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.7,
|
| 529 |
+
"learning_rate": 0.00015442359249329758,
|
| 530 |
+
"loss": 0.5312,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.7,
|
| 535 |
+
"learning_rate": 0.00015388739946380696,
|
| 536 |
+
"loss": 0.5638,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.71,
|
| 541 |
+
"learning_rate": 0.00015335120643431634,
|
| 542 |
+
"loss": 0.2928,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.72,
|
| 547 |
+
"learning_rate": 0.00015281501340482574,
|
| 548 |
+
"loss": 0.5724,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.73,
|
| 553 |
+
"learning_rate": 0.00015227882037533512,
|
| 554 |
+
"loss": 0.5019,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.74,
|
| 559 |
+
"learning_rate": 0.0001517426273458445,
|
| 560 |
+
"loss": 0.5651,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.74,
|
| 565 |
+
"learning_rate": 0.00015120643431635388,
|
| 566 |
+
"loss": 0.5588,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.75,
|
| 571 |
+
"learning_rate": 0.00015067024128686326,
|
| 572 |
+
"loss": 0.6167,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.76,
|
| 577 |
+
"learning_rate": 0.00015013404825737266,
|
| 578 |
+
"loss": 0.5652,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.77,
|
| 583 |
+
"learning_rate": 0.00014959785522788207,
|
| 584 |
+
"loss": 0.0,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.78,
|
| 589 |
+
"learning_rate": 0.00014906166219839145,
|
| 590 |
+
"loss": 0.2309,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.78,
|
| 595 |
+
"learning_rate": 0.00014852546916890082,
|
| 596 |
+
"loss": 0.5339,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.79,
|
| 601 |
+
"learning_rate": 0.0001479892761394102,
|
| 602 |
+
"loss": 0.522,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.8,
|
| 607 |
+
"learning_rate": 0.00014745308310991958,
|
| 608 |
+
"loss": 0.2473,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.81,
|
| 613 |
+
"learning_rate": 0.00014691689008042896,
|
| 614 |
+
"loss": 0.2674,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.82,
|
| 619 |
+
"learning_rate": 0.00014638069705093836,
|
| 620 |
+
"loss": 0.4833,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.82,
|
| 625 |
+
"learning_rate": 0.00014584450402144774,
|
| 626 |
+
"loss": 0.5153,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.83,
|
| 631 |
+
"learning_rate": 0.00014530831099195712,
|
| 632 |
+
"loss": 0.2366,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.84,
|
| 637 |
+
"learning_rate": 0.0001447721179624665,
|
| 638 |
+
"loss": 0.5037,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.85,
|
| 643 |
+
"learning_rate": 0.00014423592493297588,
|
| 644 |
+
"loss": 0.4913,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.86,
|
| 649 |
+
"learning_rate": 0.00014369973190348528,
|
| 650 |
+
"loss": 0.4979,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.86,
|
| 655 |
+
"learning_rate": 0.00014316353887399466,
|
| 656 |
+
"loss": 0.518,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.87,
|
| 661 |
+
"learning_rate": 0.00014262734584450404,
|
| 662 |
+
"loss": 0.0,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.88,
|
| 667 |
+
"learning_rate": 0.00014209115281501342,
|
| 668 |
+
"loss": 0.5866,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.89,
|
| 673 |
+
"learning_rate": 0.0001415549597855228,
|
| 674 |
+
"loss": 0.4525,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.9,
|
| 679 |
+
"learning_rate": 0.00014101876675603217,
|
| 680 |
+
"loss": 0.2802,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.9,
|
| 685 |
+
"learning_rate": 0.00014048257372654158,
|
| 686 |
+
"loss": 0.4686,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.91,
|
| 691 |
+
"learning_rate": 0.00013994638069705096,
|
| 692 |
+
"loss": 0.4963,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.92,
|
| 697 |
+
"learning_rate": 0.00013941018766756033,
|
| 698 |
+
"loss": 0.4853,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.93,
|
| 703 |
+
"learning_rate": 0.0001388739946380697,
|
| 704 |
+
"loss": 0.6237,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.94,
|
| 709 |
+
"learning_rate": 0.0001383378016085791,
|
| 710 |
+
"loss": 0.582,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.94,
|
| 715 |
+
"learning_rate": 0.0001378016085790885,
|
| 716 |
+
"loss": 0.5814,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.95,
|
| 721 |
+
"learning_rate": 0.00013726541554959787,
|
| 722 |
+
"loss": 0.4702,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.96,
|
| 727 |
+
"learning_rate": 0.00013672922252010725,
|
| 728 |
+
"loss": 0.2196,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.97,
|
| 733 |
+
"learning_rate": 0.00013619302949061663,
|
| 734 |
+
"loss": 0.5335,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.98,
|
| 739 |
+
"learning_rate": 0.000135656836461126,
|
| 740 |
+
"loss": 0.5734,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.98,
|
| 745 |
+
"learning_rate": 0.00013512064343163539,
|
| 746 |
+
"loss": 0.0,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.99,
|
| 751 |
+
"learning_rate": 0.0001345844504021448,
|
| 752 |
+
"loss": 0.385,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 1.0,
|
| 757 |
+
"learning_rate": 0.00013404825737265417,
|
| 758 |
+
"loss": 0.4994,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.01,
|
| 763 |
+
"learning_rate": 0.00013351206434316355,
|
| 764 |
+
"loss": 0.2143,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 1.02,
|
| 769 |
+
"learning_rate": 0.00013297587131367293,
|
| 770 |
+
"loss": 0.609,
|
| 771 |
+
"step": 127
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 1.02,
|
| 775 |
+
"learning_rate": 0.0001324396782841823,
|
| 776 |
+
"loss": 0.2692,
|
| 777 |
+
"step": 128
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 1.03,
|
| 781 |
+
"learning_rate": 0.00013190348525469168,
|
| 782 |
+
"loss": 0.2581,
|
| 783 |
+
"step": 129
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 1.04,
|
| 787 |
+
"learning_rate": 0.0001313672922252011,
|
| 788 |
+
"loss": 0.3353,
|
| 789 |
+
"step": 130
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 1.05,
|
| 793 |
+
"learning_rate": 0.00013083109919571046,
|
| 794 |
+
"loss": 0.4328,
|
| 795 |
+
"step": 131
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 1.06,
|
| 799 |
+
"learning_rate": 0.00013029490616621984,
|
| 800 |
+
"loss": 0.2286,
|
| 801 |
+
"step": 132
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.06,
|
| 805 |
+
"learning_rate": 0.00012975871313672922,
|
| 806 |
+
"loss": 0.4495,
|
| 807 |
+
"step": 133
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 1.07,
|
| 811 |
+
"learning_rate": 0.0001292225201072386,
|
| 812 |
+
"loss": 0.5591,
|
| 813 |
+
"step": 134
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 1.08,
|
| 817 |
+
"learning_rate": 0.000128686327077748,
|
| 818 |
+
"loss": 0.2977,
|
| 819 |
+
"step": 135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 1.09,
|
| 823 |
+
"learning_rate": 0.00012815013404825738,
|
| 824 |
+
"loss": 0.4241,
|
| 825 |
+
"step": 136
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 1.1,
|
| 829 |
+
"learning_rate": 0.00012761394101876676,
|
| 830 |
+
"loss": 0.3706,
|
| 831 |
+
"step": 137
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 1.1,
|
| 835 |
+
"learning_rate": 0.00012707774798927614,
|
| 836 |
+
"loss": 0.4937,
|
| 837 |
+
"step": 138
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 1.11,
|
| 841 |
+
"learning_rate": 0.00012654155495978552,
|
| 842 |
+
"loss": 0.4193,
|
| 843 |
+
"step": 139
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.12,
|
| 847 |
+
"learning_rate": 0.0001260053619302949,
|
| 848 |
+
"loss": 0.4165,
|
| 849 |
+
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 1.13,
|
| 853 |
+
"learning_rate": 0.0001254691689008043,
|
| 854 |
+
"loss": 0.4585,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 1.14,
|
| 859 |
+
"learning_rate": 0.00012493297587131368,
|
| 860 |
+
"loss": 0.4031,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 1.14,
|
| 865 |
+
"learning_rate": 0.00012439678284182306,
|
| 866 |
+
"loss": 0.1778,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 1.15,
|
| 871 |
+
"learning_rate": 0.00012386058981233243,
|
| 872 |
+
"loss": 0.4911,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 1.16,
|
| 877 |
+
"learning_rate": 0.0001233243967828418,
|
| 878 |
+
"loss": 0.489,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 1.17,
|
| 883 |
+
"learning_rate": 0.00012278820375335122,
|
| 884 |
+
"loss": 0.3833,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.18,
|
| 889 |
+
"learning_rate": 0.0001222520107238606,
|
| 890 |
+
"loss": 0.4249,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.18,
|
| 895 |
+
"learning_rate": 0.00012171581769436997,
|
| 896 |
+
"loss": 0.1813,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.19,
|
| 901 |
+
"learning_rate": 0.00012117962466487935,
|
| 902 |
+
"loss": 0.2181,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.2,
|
| 907 |
+
"learning_rate": 0.00012064343163538874,
|
| 908 |
+
"loss": 0.4004,
|
| 909 |
+
"step": 150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.21,
|
| 913 |
+
"learning_rate": 0.00012010723860589812,
|
| 914 |
+
"loss": 0.5599,
|
| 915 |
+
"step": 151
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 1.22,
|
| 919 |
+
"learning_rate": 0.0001195710455764075,
|
| 920 |
+
"loss": 0.2171,
|
| 921 |
+
"step": 152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 1.22,
|
| 925 |
+
"learning_rate": 0.00011903485254691689,
|
| 926 |
+
"loss": 0.4072,
|
| 927 |
+
"step": 153
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.23,
|
| 931 |
+
"learning_rate": 0.00011849865951742627,
|
| 932 |
+
"loss": 0.4229,
|
| 933 |
+
"step": 154
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 1.24,
|
| 937 |
+
"learning_rate": 0.00011796246648793565,
|
| 938 |
+
"loss": 0.3922,
|
| 939 |
+
"step": 155
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 1.25,
|
| 943 |
+
"learning_rate": 0.00011742627345844504,
|
| 944 |
+
"loss": 0.4483,
|
| 945 |
+
"step": 156
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 1.25,
|
| 949 |
+
"eval_loss": 0.4745557904243469,
|
| 950 |
+
"eval_runtime": 507.5138,
|
| 951 |
+
"eval_samples_per_second": 1.97,
|
| 952 |
+
"eval_steps_per_second": 0.124,
|
| 953 |
+
"step": 156
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.26,
|
| 957 |
+
"learning_rate": 0.00011689008042895442,
|
| 958 |
+
"loss": 0.3986,
|
| 959 |
+
"step": 157
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.26,
|
| 963 |
+
"learning_rate": 0.00011635388739946382,
|
| 964 |
+
"loss": 0.3715,
|
| 965 |
+
"step": 158
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.27,
|
| 969 |
+
"learning_rate": 0.0001158176943699732,
|
| 970 |
+
"loss": 0.3707,
|
| 971 |
+
"step": 159
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.28,
|
| 975 |
+
"learning_rate": 0.00011528150134048259,
|
| 976 |
+
"loss": 0.2226,
|
| 977 |
+
"step": 160
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 1.29,
|
| 981 |
+
"learning_rate": 0.00011474530831099197,
|
| 982 |
+
"loss": 0.1913,
|
| 983 |
+
"step": 161
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.3,
|
| 987 |
+
"learning_rate": 0.00011420911528150135,
|
| 988 |
+
"loss": 0.0,
|
| 989 |
+
"step": 162
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 1.3,
|
| 993 |
+
"learning_rate": 0.00011367292225201074,
|
| 994 |
+
"loss": 0.4847,
|
| 995 |
+
"step": 163
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 1.31,
|
| 999 |
+
"learning_rate": 0.00011313672922252012,
|
| 1000 |
+
"loss": 0.0,
|
| 1001 |
+
"step": 164
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 1.32,
|
| 1005 |
+
"learning_rate": 0.00011260053619302951,
|
| 1006 |
+
"loss": 0.2191,
|
| 1007 |
+
"step": 165
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 1.33,
|
| 1011 |
+
"learning_rate": 0.00011206434316353889,
|
| 1012 |
+
"loss": 0.4678,
|
| 1013 |
+
"step": 166
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 1.34,
|
| 1017 |
+
"learning_rate": 0.00011152815013404827,
|
| 1018 |
+
"loss": 0.4135,
|
| 1019 |
+
"step": 167
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 1.34,
|
| 1023 |
+
"learning_rate": 0.00011099195710455766,
|
| 1024 |
+
"loss": 0.4971,
|
| 1025 |
+
"step": 168
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.35,
|
| 1029 |
+
"learning_rate": 0.00011045576407506704,
|
| 1030 |
+
"loss": 0.2149,
|
| 1031 |
+
"step": 169
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 1.36,
|
| 1035 |
+
"learning_rate": 0.00010991957104557641,
|
| 1036 |
+
"loss": 0.2638,
|
| 1037 |
+
"step": 170
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 1.37,
|
| 1041 |
+
"learning_rate": 0.0001093833780160858,
|
| 1042 |
+
"loss": 0.5197,
|
| 1043 |
+
"step": 171
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 1.38,
|
| 1047 |
+
"learning_rate": 0.00010884718498659518,
|
| 1048 |
+
"loss": 0.4409,
|
| 1049 |
+
"step": 172
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 1.38,
|
| 1053 |
+
"learning_rate": 0.00010831099195710456,
|
| 1054 |
+
"loss": 0.4943,
|
| 1055 |
+
"step": 173
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 1.39,
|
| 1059 |
+
"learning_rate": 0.00010777479892761395,
|
| 1060 |
+
"loss": 0.4369,
|
| 1061 |
+
"step": 174
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 1.4,
|
| 1065 |
+
"learning_rate": 0.00010723860589812333,
|
| 1066 |
+
"loss": 0.281,
|
| 1067 |
+
"step": 175
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.41,
|
| 1071 |
+
"learning_rate": 0.00010670241286863272,
|
| 1072 |
+
"loss": 0.5053,
|
| 1073 |
+
"step": 176
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 1.42,
|
| 1077 |
+
"learning_rate": 0.0001061662198391421,
|
| 1078 |
+
"loss": 0.4787,
|
| 1079 |
+
"step": 177
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 1.42,
|
| 1083 |
+
"learning_rate": 0.00010563002680965148,
|
| 1084 |
+
"loss": 0.4353,
|
| 1085 |
+
"step": 178
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 1.43,
|
| 1089 |
+
"learning_rate": 0.00010509383378016087,
|
| 1090 |
+
"loss": 0.437,
|
| 1091 |
+
"step": 179
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 1.44,
|
| 1095 |
+
"learning_rate": 0.00010455764075067025,
|
| 1096 |
+
"loss": 0.2177,
|
| 1097 |
+
"step": 180
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 1.45,
|
| 1101 |
+
"learning_rate": 0.00010402144772117963,
|
| 1102 |
+
"loss": 0.0,
|
| 1103 |
+
"step": 181
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 1.46,
|
| 1107 |
+
"learning_rate": 0.00010348525469168902,
|
| 1108 |
+
"loss": 0.2128,
|
| 1109 |
+
"step": 182
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.46,
|
| 1113 |
+
"learning_rate": 0.0001029490616621984,
|
| 1114 |
+
"loss": 0.622,
|
| 1115 |
+
"step": 183
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 1.47,
|
| 1119 |
+
"learning_rate": 0.00010241286863270778,
|
| 1120 |
+
"loss": 0.0,
|
| 1121 |
+
"step": 184
|
| 1122 |
+
},
|
| 1123 |
+
{
|
| 1124 |
+
"epoch": 1.48,
|
| 1125 |
+
"learning_rate": 0.00010187667560321717,
|
| 1126 |
+
"loss": 0.285,
|
| 1127 |
+
"step": 185
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 1.49,
|
| 1131 |
+
"learning_rate": 0.00010134048257372655,
|
| 1132 |
+
"loss": 0.4149,
|
| 1133 |
+
"step": 186
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.5,
|
| 1137 |
+
"learning_rate": 0.00010080428954423592,
|
| 1138 |
+
"loss": 0.426,
|
| 1139 |
+
"step": 187
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.5,
|
| 1143 |
+
"learning_rate": 0.00010026809651474532,
|
| 1144 |
+
"loss": 0.5177,
|
| 1145 |
+
"step": 188
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.51,
|
| 1149 |
+
"learning_rate": 9.97319034852547e-05,
|
| 1150 |
+
"loss": 0.5009,
|
| 1151 |
+
"step": 189
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.52,
|
| 1155 |
+
"learning_rate": 9.919571045576409e-05,
|
| 1156 |
+
"loss": 0.2128,
|
| 1157 |
+
"step": 190
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.53,
|
| 1161 |
+
"learning_rate": 9.865951742627346e-05,
|
| 1162 |
+
"loss": 0.2701,
|
| 1163 |
+
"step": 191
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 1.54,
|
| 1167 |
+
"learning_rate": 9.812332439678284e-05,
|
| 1168 |
+
"loss": 0.4293,
|
| 1169 |
+
"step": 192
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 1.54,
|
| 1173 |
+
"learning_rate": 9.758713136729223e-05,
|
| 1174 |
+
"loss": 0.4286,
|
| 1175 |
+
"step": 193
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 1.55,
|
| 1179 |
+
"learning_rate": 9.705093833780161e-05,
|
| 1180 |
+
"loss": 0.4106,
|
| 1181 |
+
"step": 194
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 1.56,
|
| 1185 |
+
"learning_rate": 9.651474530831099e-05,
|
| 1186 |
+
"loss": 0.6385,
|
| 1187 |
+
"step": 195
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 1.57,
|
| 1191 |
+
"learning_rate": 9.597855227882038e-05,
|
| 1192 |
+
"loss": 0.2073,
|
| 1193 |
+
"step": 196
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.58,
|
| 1197 |
+
"learning_rate": 9.544235924932976e-05,
|
| 1198 |
+
"loss": 0.5092,
|
| 1199 |
+
"step": 197
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 1.58,
|
| 1203 |
+
"learning_rate": 9.490616621983914e-05,
|
| 1204 |
+
"loss": 0.1404,
|
| 1205 |
+
"step": 198
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 1.59,
|
| 1209 |
+
"learning_rate": 9.436997319034853e-05,
|
| 1210 |
+
"loss": 0.0,
|
| 1211 |
+
"step": 199
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 1.6,
|
| 1215 |
+
"learning_rate": 9.383378016085791e-05,
|
| 1216 |
+
"loss": 0.5251,
|
| 1217 |
+
"step": 200
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 1.61,
|
| 1221 |
+
"learning_rate": 9.329758713136729e-05,
|
| 1222 |
+
"loss": 0.4321,
|
| 1223 |
+
"step": 201
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 1.62,
|
| 1227 |
+
"learning_rate": 9.276139410187668e-05,
|
| 1228 |
+
"loss": 0.5201,
|
| 1229 |
+
"step": 202
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 1.62,
|
| 1233 |
+
"learning_rate": 9.222520107238606e-05,
|
| 1234 |
+
"loss": 0.4687,
|
| 1235 |
+
"step": 203
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.63,
|
| 1239 |
+
"learning_rate": 9.168900804289545e-05,
|
| 1240 |
+
"loss": 0.0,
|
| 1241 |
+
"step": 204
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 1.64,
|
| 1245 |
+
"learning_rate": 9.115281501340484e-05,
|
| 1246 |
+
"loss": 0.4181,
|
| 1247 |
+
"step": 205
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 1.65,
|
| 1251 |
+
"learning_rate": 9.061662198391422e-05,
|
| 1252 |
+
"loss": 0.39,
|
| 1253 |
+
"step": 206
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 1.66,
|
| 1257 |
+
"learning_rate": 9.00804289544236e-05,
|
| 1258 |
+
"loss": 0.4724,
|
| 1259 |
+
"step": 207
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 1.66,
|
| 1263 |
+
"learning_rate": 8.954423592493299e-05,
|
| 1264 |
+
"loss": 0.2146,
|
| 1265 |
+
"step": 208
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 1.67,
|
| 1269 |
+
"learning_rate": 8.900804289544236e-05,
|
| 1270 |
+
"loss": 0.4829,
|
| 1271 |
+
"step": 209
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 1.68,
|
| 1275 |
+
"learning_rate": 8.847184986595176e-05,
|
| 1276 |
+
"loss": 0.2066,
|
| 1277 |
+
"step": 210
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.69,
|
| 1281 |
+
"learning_rate": 8.793565683646113e-05,
|
| 1282 |
+
"loss": 0.48,
|
| 1283 |
+
"step": 211
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 1.7,
|
| 1287 |
+
"learning_rate": 8.739946380697051e-05,
|
| 1288 |
+
"loss": 0.3879,
|
| 1289 |
+
"step": 212
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 1.7,
|
| 1293 |
+
"learning_rate": 8.68632707774799e-05,
|
| 1294 |
+
"loss": 0.3477,
|
| 1295 |
+
"step": 213
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.71,
|
| 1299 |
+
"learning_rate": 8.632707774798928e-05,
|
| 1300 |
+
"loss": 0.5459,
|
| 1301 |
+
"step": 214
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 1.72,
|
| 1305 |
+
"learning_rate": 8.579088471849866e-05,
|
| 1306 |
+
"loss": 0.0,
|
| 1307 |
+
"step": 215
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 1.73,
|
| 1311 |
+
"learning_rate": 8.525469168900805e-05,
|
| 1312 |
+
"loss": 0.26,
|
| 1313 |
+
"step": 216
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 1.74,
|
| 1317 |
+
"learning_rate": 8.471849865951743e-05,
|
| 1318 |
+
"loss": 0.4626,
|
| 1319 |
+
"step": 217
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.74,
|
| 1323 |
+
"learning_rate": 8.418230563002681e-05,
|
| 1324 |
+
"loss": 0.4755,
|
| 1325 |
+
"step": 218
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.75,
|
| 1329 |
+
"learning_rate": 8.36461126005362e-05,
|
| 1330 |
+
"loss": 0.4189,
|
| 1331 |
+
"step": 219
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 1.76,
|
| 1335 |
+
"learning_rate": 8.310991957104558e-05,
|
| 1336 |
+
"loss": 0.2322,
|
| 1337 |
+
"step": 220
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.77,
|
| 1341 |
+
"learning_rate": 8.257372654155497e-05,
|
| 1342 |
+
"loss": 0.3844,
|
| 1343 |
+
"step": 221
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 1.78,
|
| 1347 |
+
"learning_rate": 8.203753351206435e-05,
|
| 1348 |
+
"loss": 0.1986,
|
| 1349 |
+
"step": 222
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 1.78,
|
| 1353 |
+
"learning_rate": 8.150134048257373e-05,
|
| 1354 |
+
"loss": 0.3902,
|
| 1355 |
+
"step": 223
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 1.79,
|
| 1359 |
+
"learning_rate": 8.096514745308312e-05,
|
| 1360 |
+
"loss": 0.4943,
|
| 1361 |
+
"step": 224
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.8,
|
| 1365 |
+
"learning_rate": 8.04289544235925e-05,
|
| 1366 |
+
"loss": 0.2464,
|
| 1367 |
+
"step": 225
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 1.81,
|
| 1371 |
+
"learning_rate": 7.989276139410187e-05,
|
| 1372 |
+
"loss": 0.6758,
|
| 1373 |
+
"step": 226
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 1.82,
|
| 1377 |
+
"learning_rate": 7.935656836461127e-05,
|
| 1378 |
+
"loss": 0.4641,
|
| 1379 |
+
"step": 227
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 1.82,
|
| 1383 |
+
"learning_rate": 7.882037533512064e-05,
|
| 1384 |
+
"loss": 0.4743,
|
| 1385 |
+
"step": 228
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 1.83,
|
| 1389 |
+
"learning_rate": 7.828418230563002e-05,
|
| 1390 |
+
"loss": 0.4186,
|
| 1391 |
+
"step": 229
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 1.84,
|
| 1395 |
+
"learning_rate": 7.774798927613941e-05,
|
| 1396 |
+
"loss": 0.4553,
|
| 1397 |
+
"step": 230
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 1.85,
|
| 1401 |
+
"learning_rate": 7.721179624664879e-05,
|
| 1402 |
+
"loss": 0.4656,
|
| 1403 |
+
"step": 231
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.86,
|
| 1407 |
+
"learning_rate": 7.667560321715817e-05,
|
| 1408 |
+
"loss": 0.4051,
|
| 1409 |
+
"step": 232
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 1.86,
|
| 1413 |
+
"learning_rate": 7.613941018766756e-05,
|
| 1414 |
+
"loss": 0.2216,
|
| 1415 |
+
"step": 233
|
| 1416 |
+
},
|
| 1417 |
+
{
|
| 1418 |
+
"epoch": 1.87,
|
| 1419 |
+
"learning_rate": 7.560321715817694e-05,
|
| 1420 |
+
"loss": 0.186,
|
| 1421 |
+
"step": 234
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 1.88,
|
| 1425 |
+
"learning_rate": 7.506702412868633e-05,
|
| 1426 |
+
"loss": 0.4749,
|
| 1427 |
+
"step": 235
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 1.89,
|
| 1431 |
+
"learning_rate": 7.453083109919572e-05,
|
| 1432 |
+
"loss": 0.4781,
|
| 1433 |
+
"step": 236
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 1.9,
|
| 1437 |
+
"learning_rate": 7.39946380697051e-05,
|
| 1438 |
+
"loss": 0.4187,
|
| 1439 |
+
"step": 237
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 1.9,
|
| 1443 |
+
"learning_rate": 7.345844504021448e-05,
|
| 1444 |
+
"loss": 0.1483,
|
| 1445 |
+
"step": 238
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.91,
|
| 1449 |
+
"learning_rate": 7.292225201072387e-05,
|
| 1450 |
+
"loss": 0.1983,
|
| 1451 |
+
"step": 239
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 1.92,
|
| 1455 |
+
"learning_rate": 7.238605898123325e-05,
|
| 1456 |
+
"loss": 0.3519,
|
| 1457 |
+
"step": 240
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 1.93,
|
| 1461 |
+
"learning_rate": 7.184986595174264e-05,
|
| 1462 |
+
"loss": 0.196,
|
| 1463 |
+
"step": 241
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.94,
|
| 1467 |
+
"learning_rate": 7.131367292225202e-05,
|
| 1468 |
+
"loss": 0.4758,
|
| 1469 |
+
"step": 242
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 1.94,
|
| 1473 |
+
"learning_rate": 7.07774798927614e-05,
|
| 1474 |
+
"loss": 0.5811,
|
| 1475 |
+
"step": 243
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 1.95,
|
| 1479 |
+
"learning_rate": 7.024128686327079e-05,
|
| 1480 |
+
"loss": 0.2388,
|
| 1481 |
+
"step": 244
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 1.96,
|
| 1485 |
+
"learning_rate": 6.970509383378017e-05,
|
| 1486 |
+
"loss": 0.1879,
|
| 1487 |
+
"step": 245
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.97,
|
| 1491 |
+
"learning_rate": 6.916890080428954e-05,
|
| 1492 |
+
"loss": 0.4715,
|
| 1493 |
+
"step": 246
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 1.98,
|
| 1497 |
+
"learning_rate": 6.863270777479894e-05,
|
| 1498 |
+
"loss": 0.4777,
|
| 1499 |
+
"step": 247
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 1.98,
|
| 1503 |
+
"learning_rate": 6.809651474530831e-05,
|
| 1504 |
+
"loss": 0.1942,
|
| 1505 |
+
"step": 248
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.99,
|
| 1509 |
+
"learning_rate": 6.756032171581769e-05,
|
| 1510 |
+
"loss": 0.3845,
|
| 1511 |
+
"step": 249
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 2.0,
|
| 1515 |
+
"learning_rate": 6.702412868632708e-05,
|
| 1516 |
+
"loss": 0.3878,
|
| 1517 |
+
"step": 250
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 2.01,
|
| 1521 |
+
"learning_rate": 6.648793565683646e-05,
|
| 1522 |
+
"loss": 0.3244,
|
| 1523 |
+
"step": 251
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 2.02,
|
| 1527 |
+
"learning_rate": 6.595174262734584e-05,
|
| 1528 |
+
"loss": 0.1966,
|
| 1529 |
+
"step": 252
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 2.02,
|
| 1533 |
+
"learning_rate": 6.541554959785523e-05,
|
| 1534 |
+
"loss": 0.3773,
|
| 1535 |
+
"step": 253
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 2.03,
|
| 1539 |
+
"learning_rate": 6.487935656836461e-05,
|
| 1540 |
+
"loss": 0.2275,
|
| 1541 |
+
"step": 254
|
| 1542 |
+
},
|
| 1543 |
+
{
|
| 1544 |
+
"epoch": 2.04,
|
| 1545 |
+
"learning_rate": 6.4343163538874e-05,
|
| 1546 |
+
"loss": 0.3814,
|
| 1547 |
+
"step": 255
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 2.05,
|
| 1551 |
+
"learning_rate": 6.380697050938338e-05,
|
| 1552 |
+
"loss": 0.3665,
|
| 1553 |
+
"step": 256
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 2.06,
|
| 1557 |
+
"learning_rate": 6.327077747989276e-05,
|
| 1558 |
+
"loss": 0.2171,
|
| 1559 |
+
"step": 257
|
| 1560 |
+
},
|
| 1561 |
+
{
|
| 1562 |
+
"epoch": 2.06,
|
| 1563 |
+
"learning_rate": 6.273458445040215e-05,
|
| 1564 |
+
"loss": 0.3475,
|
| 1565 |
+
"step": 258
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 2.07,
|
| 1569 |
+
"learning_rate": 6.219839142091153e-05,
|
| 1570 |
+
"loss": 0.3976,
|
| 1571 |
+
"step": 259
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 2.08,
|
| 1575 |
+
"learning_rate": 6.16621983914209e-05,
|
| 1576 |
+
"loss": 0.3182,
|
| 1577 |
+
"step": 260
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 2.09,
|
| 1581 |
+
"learning_rate": 6.11260053619303e-05,
|
| 1582 |
+
"loss": 0.1861,
|
| 1583 |
+
"step": 261
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 2.1,
|
| 1587 |
+
"learning_rate": 6.0589812332439676e-05,
|
| 1588 |
+
"loss": 0.1793,
|
| 1589 |
+
"step": 262
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 2.1,
|
| 1593 |
+
"learning_rate": 6.005361930294906e-05,
|
| 1594 |
+
"loss": 0.2179,
|
| 1595 |
+
"step": 263
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 2.11,
|
| 1599 |
+
"learning_rate": 5.9517426273458446e-05,
|
| 1600 |
+
"loss": 0.1979,
|
| 1601 |
+
"step": 264
|
| 1602 |
+
},
|
| 1603 |
+
{
|
| 1604 |
+
"epoch": 2.12,
|
| 1605 |
+
"learning_rate": 5.8981233243967824e-05,
|
| 1606 |
+
"loss": 0.3276,
|
| 1607 |
+
"step": 265
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.13,
|
| 1611 |
+
"learning_rate": 5.844504021447721e-05,
|
| 1612 |
+
"loss": 0.3906,
|
| 1613 |
+
"step": 266
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.14,
|
| 1617 |
+
"learning_rate": 5.79088471849866e-05,
|
| 1618 |
+
"loss": 0.2071,
|
| 1619 |
+
"step": 267
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 2.14,
|
| 1623 |
+
"learning_rate": 5.7372654155495985e-05,
|
| 1624 |
+
"loss": 0.4533,
|
| 1625 |
+
"step": 268
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 2.15,
|
| 1629 |
+
"learning_rate": 5.683646112600537e-05,
|
| 1630 |
+
"loss": 0.3243,
|
| 1631 |
+
"step": 269
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 2.16,
|
| 1635 |
+
"learning_rate": 5.6300268096514755e-05,
|
| 1636 |
+
"loss": 0.2265,
|
| 1637 |
+
"step": 270
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 2.17,
|
| 1641 |
+
"learning_rate": 5.5764075067024133e-05,
|
| 1642 |
+
"loss": 0.1803,
|
| 1643 |
+
"step": 271
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 2.18,
|
| 1647 |
+
"learning_rate": 5.522788203753352e-05,
|
| 1648 |
+
"loss": 0.3864,
|
| 1649 |
+
"step": 272
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 2.18,
|
| 1653 |
+
"learning_rate": 5.46916890080429e-05,
|
| 1654 |
+
"loss": 0.2345,
|
| 1655 |
+
"step": 273
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.19,
|
| 1659 |
+
"learning_rate": 5.415549597855228e-05,
|
| 1660 |
+
"loss": 0.3619,
|
| 1661 |
+
"step": 274
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 2.2,
|
| 1665 |
+
"learning_rate": 5.3619302949061666e-05,
|
| 1666 |
+
"loss": 0.359,
|
| 1667 |
+
"step": 275
|
| 1668 |
+
},
|
| 1669 |
+
{
|
| 1670 |
+
"epoch": 2.21,
|
| 1671 |
+
"learning_rate": 5.308310991957105e-05,
|
| 1672 |
+
"loss": 0.3599,
|
| 1673 |
+
"step": 276
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 2.22,
|
| 1677 |
+
"learning_rate": 5.2546916890080436e-05,
|
| 1678 |
+
"loss": 0.3484,
|
| 1679 |
+
"step": 277
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 2.22,
|
| 1683 |
+
"learning_rate": 5.2010723860589814e-05,
|
| 1684 |
+
"loss": 0.4419,
|
| 1685 |
+
"step": 278
|
| 1686 |
+
},
|
| 1687 |
+
{
|
| 1688 |
+
"epoch": 2.23,
|
| 1689 |
+
"learning_rate": 5.14745308310992e-05,
|
| 1690 |
+
"loss": 0.3972,
|
| 1691 |
+
"step": 279
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 2.24,
|
| 1695 |
+
"learning_rate": 5.0938337801608584e-05,
|
| 1696 |
+
"loss": 0.1137,
|
| 1697 |
+
"step": 280
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.25,
|
| 1701 |
+
"learning_rate": 5.040214477211796e-05,
|
| 1702 |
+
"loss": 0.1447,
|
| 1703 |
+
"step": 281
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 2.26,
|
| 1707 |
+
"learning_rate": 4.986595174262735e-05,
|
| 1708 |
+
"loss": 0.1893,
|
| 1709 |
+
"step": 282
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 2.26,
|
| 1713 |
+
"learning_rate": 4.932975871313673e-05,
|
| 1714 |
+
"loss": 0.3628,
|
| 1715 |
+
"step": 283
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 2.27,
|
| 1719 |
+
"learning_rate": 4.879356568364612e-05,
|
| 1720 |
+
"loss": 0.4312,
|
| 1721 |
+
"step": 284
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 2.28,
|
| 1725 |
+
"learning_rate": 4.8257372654155495e-05,
|
| 1726 |
+
"loss": 0.2004,
|
| 1727 |
+
"step": 285
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 2.29,
|
| 1731 |
+
"learning_rate": 4.772117962466488e-05,
|
| 1732 |
+
"loss": 0.2917,
|
| 1733 |
+
"step": 286
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 2.3,
|
| 1737 |
+
"learning_rate": 4.7184986595174265e-05,
|
| 1738 |
+
"loss": 0.2032,
|
| 1739 |
+
"step": 287
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.3,
|
| 1743 |
+
"learning_rate": 4.664879356568364e-05,
|
| 1744 |
+
"loss": 0.4294,
|
| 1745 |
+
"step": 288
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 2.31,
|
| 1749 |
+
"learning_rate": 4.611260053619303e-05,
|
| 1750 |
+
"loss": 0.3369,
|
| 1751 |
+
"step": 289
|
| 1752 |
+
},
|
| 1753 |
+
{
|
| 1754 |
+
"epoch": 2.32,
|
| 1755 |
+
"learning_rate": 4.557640750670242e-05,
|
| 1756 |
+
"loss": 0.5108,
|
| 1757 |
+
"step": 290
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 2.33,
|
| 1761 |
+
"learning_rate": 4.50402144772118e-05,
|
| 1762 |
+
"loss": 0.1781,
|
| 1763 |
+
"step": 291
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 2.34,
|
| 1767 |
+
"learning_rate": 4.450402144772118e-05,
|
| 1768 |
+
"loss": 0.3727,
|
| 1769 |
+
"step": 292
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 2.34,
|
| 1773 |
+
"learning_rate": 4.396782841823057e-05,
|
| 1774 |
+
"loss": 0.3751,
|
| 1775 |
+
"step": 293
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 2.35,
|
| 1779 |
+
"learning_rate": 4.343163538873995e-05,
|
| 1780 |
+
"loss": 0.3441,
|
| 1781 |
+
"step": 294
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.36,
|
| 1785 |
+
"learning_rate": 4.289544235924933e-05,
|
| 1786 |
+
"loss": 0.1936,
|
| 1787 |
+
"step": 295
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 2.37,
|
| 1791 |
+
"learning_rate": 4.2359249329758715e-05,
|
| 1792 |
+
"loss": 0.3061,
|
| 1793 |
+
"step": 296
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 2.38,
|
| 1797 |
+
"learning_rate": 4.18230563002681e-05,
|
| 1798 |
+
"loss": 0.1177,
|
| 1799 |
+
"step": 297
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 2.38,
|
| 1803 |
+
"learning_rate": 4.1286863270777485e-05,
|
| 1804 |
+
"loss": 0.3463,
|
| 1805 |
+
"step": 298
|
| 1806 |
+
},
|
| 1807 |
+
{
|
| 1808 |
+
"epoch": 2.39,
|
| 1809 |
+
"learning_rate": 4.075067024128686e-05,
|
| 1810 |
+
"loss": 0.2356,
|
| 1811 |
+
"step": 299
|
| 1812 |
+
},
|
| 1813 |
+
{
|
| 1814 |
+
"epoch": 2.4,
|
| 1815 |
+
"learning_rate": 4.021447721179625e-05,
|
| 1816 |
+
"loss": 0.1803,
|
| 1817 |
+
"step": 300
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 2.41,
|
| 1821 |
+
"learning_rate": 3.967828418230563e-05,
|
| 1822 |
+
"loss": 0.3799,
|
| 1823 |
+
"step": 301
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.42,
|
| 1827 |
+
"learning_rate": 3.914209115281501e-05,
|
| 1828 |
+
"loss": 0.1402,
|
| 1829 |
+
"step": 302
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 2.42,
|
| 1833 |
+
"learning_rate": 3.8605898123324396e-05,
|
| 1834 |
+
"loss": 0.388,
|
| 1835 |
+
"step": 303
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 2.43,
|
| 1839 |
+
"learning_rate": 3.806970509383378e-05,
|
| 1840 |
+
"loss": 0.4519,
|
| 1841 |
+
"step": 304
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 2.44,
|
| 1845 |
+
"learning_rate": 3.7533512064343166e-05,
|
| 1846 |
+
"loss": 0.2871,
|
| 1847 |
+
"step": 305
|
| 1848 |
+
},
|
| 1849 |
+
{
|
| 1850 |
+
"epoch": 2.45,
|
| 1851 |
+
"learning_rate": 3.699731903485255e-05,
|
| 1852 |
+
"loss": 0.4283,
|
| 1853 |
+
"step": 306
|
| 1854 |
+
},
|
| 1855 |
+
{
|
| 1856 |
+
"epoch": 2.46,
|
| 1857 |
+
"learning_rate": 3.6461126005361935e-05,
|
| 1858 |
+
"loss": 0.2182,
|
| 1859 |
+
"step": 307
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 2.46,
|
| 1863 |
+
"learning_rate": 3.592493297587132e-05,
|
| 1864 |
+
"loss": 0.4494,
|
| 1865 |
+
"step": 308
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.47,
|
| 1869 |
+
"learning_rate": 3.53887399463807e-05,
|
| 1870 |
+
"loss": 0.1482,
|
| 1871 |
+
"step": 309
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 2.48,
|
| 1875 |
+
"learning_rate": 3.485254691689008e-05,
|
| 1876 |
+
"loss": 0.5202,
|
| 1877 |
+
"step": 310
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 2.49,
|
| 1881 |
+
"learning_rate": 3.431635388739947e-05,
|
| 1882 |
+
"loss": 0.4222,
|
| 1883 |
+
"step": 311
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 2.5,
|
| 1887 |
+
"learning_rate": 3.3780160857908846e-05,
|
| 1888 |
+
"loss": 0.1812,
|
| 1889 |
+
"step": 312
|
| 1890 |
+
},
|
| 1891 |
+
{
|
| 1892 |
+
"epoch": 2.5,
|
| 1893 |
+
"eval_loss": 0.4782574772834778,
|
| 1894 |
+
"eval_runtime": 507.7885,
|
| 1895 |
+
"eval_samples_per_second": 1.969,
|
| 1896 |
+
"eval_steps_per_second": 0.124,
|
| 1897 |
+
"step": 312
|
| 1898 |
+
}
|
| 1899 |
+
],
|
| 1900 |
+
"logging_steps": 1,
|
| 1901 |
+
"max_steps": 375,
|
| 1902 |
+
"num_train_epochs": 3,
|
| 1903 |
+
"save_steps": 156,
|
| 1904 |
+
"total_flos": 2.0372969489301504e+17,
|
| 1905 |
+
"trial_name": null,
|
| 1906 |
+
"trial_params": null
|
| 1907 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d5fd2c453c1f941b148e3eb0b85118cea79dd57948f6b8ea4c2b161ebe5780c
|
| 3 |
+
size 4091
|