Upload 13 files
Browse files- adapter_config.json +28 -28
- adapter_model.safetensors +1 -1
- added_tokens.json +3 -0
- optimizer.pt +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +24 -24
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -49
- trainer_state.json +313 -173
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -1,29 +1,29 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"fan_in_fan_out": false,
|
| 7 |
-
"inference_mode": true,
|
| 8 |
-
"init_lora_weights": true,
|
| 9 |
-
"layer_replication": null,
|
| 10 |
-
"layers_pattern": null,
|
| 11 |
-
"layers_to_transform": null,
|
| 12 |
-
"loftq_config": {},
|
| 13 |
-
"lora_alpha": 16,
|
| 14 |
-
"lora_dropout": 0.1,
|
| 15 |
-
"megatron_config": null,
|
| 16 |
-
"megatron_core": "megatron.core",
|
| 17 |
-
"modules_to_save": null,
|
| 18 |
-
"peft_type": "LORA",
|
| 19 |
-
"r": 64,
|
| 20 |
-
"rank_pattern": {},
|
| 21 |
-
"revision": null,
|
| 22 |
-
"target_modules": [
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
],
|
| 26 |
-
"task_type": "CAUSAL_LM",
|
| 27 |
-
"use_dora": false,
|
| 28 |
-
"use_rslora": false
|
| 29 |
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 64,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"v_proj"
|
| 25 |
+
],
|
| 26 |
+
"task_type": "CAUSAL_LM",
|
| 27 |
+
"use_dora": false,
|
| 28 |
+
"use_rslora": false
|
| 29 |
}
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 134235048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a40e83b6ec10c3e18d82e9aae7fd1bd5640d73c4a12f9cd272527e448f237650
|
| 3 |
size 134235048
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6877126e4b893a0d6e5f0d8230d54a065c0a9028231747d7bdae69d2f0938025
|
| 3 |
+
size 268515066
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31f94440a84de8dcb7e3dc56f62912fe1cffa12753d6b0c3c9602e4effda4eec
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19bcbcfd505eb4fc1a12c7d832a77268d82b4a9b82157e01d48b5fb1cf5fbcc1
|
| 3 |
size 1064
|
special_tokens_map.json
CHANGED
|
@@ -1,24 +1,24 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": {
|
| 3 |
-
"content": "<s>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": true,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "</s>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": "</s>",
|
| 17 |
-
"unk_token": {
|
| 18 |
-
"content": "<unk>",
|
| 19 |
-
"lstrip": false,
|
| 20 |
-
"normalized": true,
|
| 21 |
-
"rstrip": false,
|
| 22 |
-
"single_word": false
|
| 23 |
-
}
|
| 24 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
CHANGED
|
@@ -1,49 +1,49 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": null,
|
| 5 |
-
"added_tokens_decoder": {
|
| 6 |
-
"0": {
|
| 7 |
-
"content": "<unk>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": true,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false,
|
| 12 |
-
"special": true
|
| 13 |
-
},
|
| 14 |
-
"1": {
|
| 15 |
-
"content": "<s>",
|
| 16 |
-
"lstrip": false,
|
| 17 |
-
"normalized": true,
|
| 18 |
-
"rstrip": false,
|
| 19 |
-
"single_word": false,
|
| 20 |
-
"special": true
|
| 21 |
-
},
|
| 22 |
-
"2": {
|
| 23 |
-
"content": "</s>",
|
| 24 |
-
"lstrip": false,
|
| 25 |
-
"normalized": true,
|
| 26 |
-
"rstrip": false,
|
| 27 |
-
"single_word": false,
|
| 28 |
-
"special": true
|
| 29 |
-
},
|
| 30 |
-
"32000": {
|
| 31 |
-
"content": "<pad>",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": true,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false,
|
| 36 |
-
"special": false
|
| 37 |
-
}
|
| 38 |
-
},
|
| 39 |
-
"bos_token": "<s>",
|
| 40 |
-
"clean_up_tokenization_spaces": false,
|
| 41 |
-
"eos_token": "</s>",
|
| 42 |
-
"legacy": false,
|
| 43 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 44 |
-
"pad_token": "</s>",
|
| 45 |
-
"sp_model_kwargs": {},
|
| 46 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 47 |
-
"unk_token": "<unk>",
|
| 48 |
-
"use_default_system_prompt": false
|
| 49 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<unk>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"2": {
|
| 23 |
+
"content": "</s>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": true
|
| 29 |
+
},
|
| 30 |
+
"32000": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"clean_up_tokenization_spaces": false,
|
| 41 |
+
"eos_token": "</s>",
|
| 42 |
+
"legacy": false,
|
| 43 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 44 |
+
"pad_token": "</s>",
|
| 45 |
+
"sp_model_kwargs": {},
|
| 46 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 47 |
+
"unk_token": "<unk>",
|
| 48 |
+
"use_default_system_prompt": false
|
| 49 |
+
}
|
trainer_state.json
CHANGED
|
@@ -1,173 +1,313 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 0
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch":
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
-
"learning_rate":
|
| 15 |
-
"loss":
|
| 16 |
-
"step": 25
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm":
|
| 21 |
-
"learning_rate":
|
| 22 |
-
"loss":
|
| 23 |
-
"step": 50
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm": 0.
|
| 28 |
-
"learning_rate":
|
| 29 |
-
"loss":
|
| 30 |
-
"step": 75
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm":
|
| 35 |
-
"learning_rate":
|
| 36 |
-
"loss":
|
| 37 |
-
"step": 100
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 1.
|
| 44 |
-
"step": 125
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm": 1.
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 1.
|
| 51 |
-
"step": 150
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm":
|
| 56 |
-
"learning_rate":
|
| 57 |
-
"loss": 1.
|
| 58 |
-
"step": 175
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm":
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 1.
|
| 65 |
-
"step": 200
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm":
|
| 70 |
-
"learning_rate":
|
| 71 |
-
"loss": 1.
|
| 72 |
-
"step": 225
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm":
|
| 77 |
-
"learning_rate":
|
| 78 |
-
"loss": 1.
|
| 79 |
-
"step": 250
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.
|
| 83 |
-
"grad_norm":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 1.
|
| 86 |
-
"step": 275
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.
|
| 90 |
-
"grad_norm":
|
| 91 |
-
"learning_rate":
|
| 92 |
-
"loss": 1.
|
| 93 |
-
"step": 300
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.
|
| 97 |
-
"grad_norm": 0.
|
| 98 |
-
"learning_rate":
|
| 99 |
-
"loss": 1.
|
| 100 |
-
"step": 325
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.
|
| 104 |
-
"grad_norm": 0.
|
| 105 |
-
"learning_rate":
|
| 106 |
-
"loss": 1.
|
| 107 |
-
"step": 350
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.
|
| 111 |
-
"grad_norm": 0.
|
| 112 |
-
"learning_rate":
|
| 113 |
-
"loss": 1.
|
| 114 |
-
"step": 375
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.
|
| 118 |
-
"grad_norm": 0.
|
| 119 |
-
"learning_rate":
|
| 120 |
-
"loss": 1.
|
| 121 |
-
"step": 400
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.
|
| 125 |
-
"grad_norm":
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 1.
|
| 128 |
-
"step": 425
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.
|
| 132 |
-
"grad_norm":
|
| 133 |
-
"learning_rate":
|
| 134 |
-
"loss": 1.
|
| 135 |
-
"step": 450
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.
|
| 139 |
-
"grad_norm": 0.
|
| 140 |
-
"learning_rate":
|
| 141 |
-
"loss": 1.
|
| 142 |
-
"step": 475
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.
|
| 146 |
-
"grad_norm": 0.
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 1.
|
| 149 |
-
"step": 500
|
| 150 |
-
}
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
|
| 157 |
-
|
| 158 |
-
|
| 159 |
-
"
|
| 160 |
-
|
| 161 |
-
|
| 162 |
-
|
| 163 |
-
|
| 164 |
-
|
| 165 |
-
|
| 166 |
-
"
|
| 167 |
-
|
| 168 |
-
|
| 169 |
-
|
| 170 |
-
|
| 171 |
-
|
| 172 |
-
|
| 173 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.025,
|
| 13 |
+
"grad_norm": 0.2357209473848343,
|
| 14 |
+
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 1.4572,
|
| 16 |
+
"step": 25
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 4.098695278167725,
|
| 21 |
+
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 1.6134,
|
| 23 |
+
"step": 50
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.075,
|
| 27 |
+
"grad_norm": 0.36763498187065125,
|
| 28 |
+
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 1.1204,
|
| 30 |
+
"step": 75
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.1,
|
| 34 |
+
"grad_norm": 3.215606927871704,
|
| 35 |
+
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 1.6429,
|
| 37 |
+
"step": 100
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.125,
|
| 41 |
+
"grad_norm": 0.24122707545757294,
|
| 42 |
+
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 1.1536,
|
| 44 |
+
"step": 125
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15,
|
| 48 |
+
"grad_norm": 1.240979552268982,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 1.5328,
|
| 51 |
+
"step": 150
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.175,
|
| 55 |
+
"grad_norm": 0.5094348788261414,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 1.1057,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.2,
|
| 62 |
+
"grad_norm": 1.9274498224258423,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 1.4537,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.225,
|
| 69 |
+
"grad_norm": 0.22062620520591736,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 1.0565,
|
| 72 |
+
"step": 225
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.25,
|
| 76 |
+
"grad_norm": 1.489973545074463,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 1.3707,
|
| 79 |
+
"step": 250
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.275,
|
| 83 |
+
"grad_norm": 0.2041197568178177,
|
| 84 |
+
"learning_rate": 0.0002,
|
| 85 |
+
"loss": 1.1186,
|
| 86 |
+
"step": 275
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3,
|
| 90 |
+
"grad_norm": 0.5328978896141052,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 1.5287,
|
| 93 |
+
"step": 300
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.325,
|
| 97 |
+
"grad_norm": 0.2129279226064682,
|
| 98 |
+
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 1.3442,
|
| 100 |
+
"step": 325
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.35,
|
| 104 |
+
"grad_norm": 0.42091837525367737,
|
| 105 |
+
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 1.4075,
|
| 107 |
+
"step": 350
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.375,
|
| 111 |
+
"grad_norm": 0.13680295646190643,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 1.2503,
|
| 114 |
+
"step": 375
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4,
|
| 118 |
+
"grad_norm": 0.8510954976081848,
|
| 119 |
+
"learning_rate": 0.0002,
|
| 120 |
+
"loss": 1.3453,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.425,
|
| 125 |
+
"grad_norm": 0.19430848956108093,
|
| 126 |
+
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 1.1908,
|
| 128 |
+
"step": 425
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.45,
|
| 132 |
+
"grad_norm": 0.6921439170837402,
|
| 133 |
+
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 1.3728,
|
| 135 |
+
"step": 450
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.475,
|
| 139 |
+
"grad_norm": 0.2126462459564209,
|
| 140 |
+
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 1.1244,
|
| 142 |
+
"step": 475
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5,
|
| 146 |
+
"grad_norm": 0.6232830882072449,
|
| 147 |
+
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 1.2055,
|
| 149 |
+
"step": 500
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.525,
|
| 153 |
+
"grad_norm": 0.20547091960906982,
|
| 154 |
+
"learning_rate": 0.0002,
|
| 155 |
+
"loss": 1.1497,
|
| 156 |
+
"step": 525
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.55,
|
| 160 |
+
"grad_norm": 0.489362508058548,
|
| 161 |
+
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 1.2601,
|
| 163 |
+
"step": 550
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.575,
|
| 167 |
+
"grad_norm": 0.1969325989484787,
|
| 168 |
+
"learning_rate": 0.0002,
|
| 169 |
+
"loss": 1.1765,
|
| 170 |
+
"step": 575
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6,
|
| 174 |
+
"grad_norm": 0.6766378879547119,
|
| 175 |
+
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 1.5613,
|
| 177 |
+
"step": 600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.625,
|
| 181 |
+
"grad_norm": 0.13454963266849518,
|
| 182 |
+
"learning_rate": 0.0002,
|
| 183 |
+
"loss": 1.2215,
|
| 184 |
+
"step": 625
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.65,
|
| 188 |
+
"grad_norm": 0.32630065083503723,
|
| 189 |
+
"learning_rate": 0.0002,
|
| 190 |
+
"loss": 1.3704,
|
| 191 |
+
"step": 650
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.675,
|
| 195 |
+
"grad_norm": 0.2560375928878784,
|
| 196 |
+
"learning_rate": 0.0002,
|
| 197 |
+
"loss": 1.0987,
|
| 198 |
+
"step": 675
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.7,
|
| 202 |
+
"grad_norm": 1.6413543224334717,
|
| 203 |
+
"learning_rate": 0.0002,
|
| 204 |
+
"loss": 1.5937,
|
| 205 |
+
"step": 700
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.725,
|
| 209 |
+
"grad_norm": 0.2766744792461395,
|
| 210 |
+
"learning_rate": 0.0002,
|
| 211 |
+
"loss": 1.1834,
|
| 212 |
+
"step": 725
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.75,
|
| 216 |
+
"grad_norm": 0.9574869275093079,
|
| 217 |
+
"learning_rate": 0.0002,
|
| 218 |
+
"loss": 1.4304,
|
| 219 |
+
"step": 750
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.775,
|
| 223 |
+
"grad_norm": 0.13615752756595612,
|
| 224 |
+
"learning_rate": 0.0002,
|
| 225 |
+
"loss": 1.1135,
|
| 226 |
+
"step": 775
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.8,
|
| 230 |
+
"grad_norm": 0.6256314516067505,
|
| 231 |
+
"learning_rate": 0.0002,
|
| 232 |
+
"loss": 1.3999,
|
| 233 |
+
"step": 800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.825,
|
| 237 |
+
"grad_norm": 0.2913402020931244,
|
| 238 |
+
"learning_rate": 0.0002,
|
| 239 |
+
"loss": 1.0998,
|
| 240 |
+
"step": 825
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.85,
|
| 244 |
+
"grad_norm": 0.8512757420539856,
|
| 245 |
+
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 1.5836,
|
| 247 |
+
"step": 850
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.875,
|
| 251 |
+
"grad_norm": 0.1915389448404312,
|
| 252 |
+
"learning_rate": 0.0002,
|
| 253 |
+
"loss": 1.1269,
|
| 254 |
+
"step": 875
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.9,
|
| 258 |
+
"grad_norm": 0.6881994605064392,
|
| 259 |
+
"learning_rate": 0.0002,
|
| 260 |
+
"loss": 1.4682,
|
| 261 |
+
"step": 900
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.925,
|
| 265 |
+
"grad_norm": 0.15422898530960083,
|
| 266 |
+
"learning_rate": 0.0002,
|
| 267 |
+
"loss": 1.0977,
|
| 268 |
+
"step": 925
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.95,
|
| 272 |
+
"grad_norm": 0.775578498840332,
|
| 273 |
+
"learning_rate": 0.0002,
|
| 274 |
+
"loss": 1.6679,
|
| 275 |
+
"step": 950
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.975,
|
| 279 |
+
"grad_norm": 0.28175973892211914,
|
| 280 |
+
"learning_rate": 0.0002,
|
| 281 |
+
"loss": 1.2866,
|
| 282 |
+
"step": 975
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.0,
|
| 286 |
+
"grad_norm": 0.5729475021362305,
|
| 287 |
+
"learning_rate": 0.0002,
|
| 288 |
+
"loss": 1.3361,
|
| 289 |
+
"step": 1000
|
| 290 |
+
}
|
| 291 |
+
],
|
| 292 |
+
"logging_steps": 25,
|
| 293 |
+
"max_steps": 1000,
|
| 294 |
+
"num_input_tokens_seen": 0,
|
| 295 |
+
"num_train_epochs": 1,
|
| 296 |
+
"save_steps": 25,
|
| 297 |
+
"stateful_callbacks": {
|
| 298 |
+
"TrainerControl": {
|
| 299 |
+
"args": {
|
| 300 |
+
"should_epoch_stop": false,
|
| 301 |
+
"should_evaluate": false,
|
| 302 |
+
"should_log": false,
|
| 303 |
+
"should_save": true,
|
| 304 |
+
"should_training_stop": true
|
| 305 |
+
},
|
| 306 |
+
"attributes": {}
|
| 307 |
+
}
|
| 308 |
+
},
|
| 309 |
+
"total_flos": 1.679542884421632e+16,
|
| 310 |
+
"train_batch_size": 1,
|
| 311 |
+
"trial_name": null,
|
| 312 |
+
"trial_params": null
|
| 313 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5432
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ced240fd53834fa3700f173685f9aeeb3a5d2ca39269ec93a8f139d341c48537
|
| 3 |
size 5432
|