Upload folder using huggingface_hub
Browse files- adapter_config.json +4 -3
- adapter_model.bin +2 -2
- optimizer.pt +2 -2
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- special_tokens_map.json +4 -22
- tokenizer.json +0 -0
- tokenizer_config.json +190 -15
- trainer_state.json +313 -6
- training_args.bin +1 -1
adapter_config.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
-
"base_model_name_or_path": "
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
|
@@ -14,8 +14,9 @@
|
|
| 14 |
"r": 16,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
-
"
|
| 18 |
-
"
|
|
|
|
| 19 |
],
|
| 20 |
"task_type": "CAUSAL_LM"
|
| 21 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "stabilityai/stablelm-base-alpha-3b-v2",
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
|
|
|
| 14 |
"r": 16,
|
| 15 |
"revision": null,
|
| 16 |
"target_modules": [
|
| 17 |
+
"qkv_proj",
|
| 18 |
+
"gate_proj",
|
| 19 |
+
"out_proj"
|
| 20 |
],
|
| 21 |
"task_type": "CAUSAL_LM"
|
| 22 |
}
|
adapter_model.bin
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:c93e9e064e4836d718dd5817a31b8b922c096ac52b39320046ae8414fc3f164c
|
| 3 |
+
size 84504330
|
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:c4e047dcb32ec0ae668d771ec35f3567a0e70b1c03c1a1963e3252fa05b9c9e3
|
| 3 |
+
size 169035898
|
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 sha256:3d88943110975beabc6932e5d2c3d009f5f9a53729cb06aa62da38ef86bafb19
|
| 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 sha256:55453edc7ae4b6242ad6bf3479593988d77a7dd0d971dd86170c4caeeca3a0e8
|
| 3 |
size 1064
|
special_tokens_map.json
CHANGED
|
@@ -1,24 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 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": "<|endoftext|>",
|
| 3 |
+
"eos_token": "<|endoftext|>",
|
| 4 |
+
"pad_token": "<|endoftext|>",
|
| 5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,37 +1,212 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
-
"content": "<
|
| 5 |
"lstrip": false,
|
| 6 |
-
"normalized":
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
"1": {
|
| 12 |
-
"content": "<
|
| 13 |
"lstrip": false,
|
| 14 |
-
"normalized":
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
-
"
|
| 20 |
-
"content": "
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": true,
|
| 23 |
"rstrip": false,
|
| 24 |
"single_word": false,
|
| 25 |
-
"special":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
}
|
| 27 |
},
|
| 28 |
-
"bos_token": "<
|
| 29 |
-
"clean_up_tokenization_spaces":
|
| 30 |
-
"eos_token": "<
|
| 31 |
"model_max_length": 1024,
|
| 32 |
-
"pad_token": "<
|
| 33 |
-
"
|
| 34 |
-
"
|
| 35 |
-
"unk_token": "<unk>",
|
| 36 |
-
"use_default_system_prompt": true
|
| 37 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
+
"content": "<|endoftext|>",
|
| 6 |
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
"1": {
|
| 13 |
+
"content": "<|padding|>",
|
| 14 |
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
| 19 |
},
|
| 20 |
+
"50254": {
|
| 21 |
+
"content": " ",
|
| 22 |
"lstrip": false,
|
| 23 |
"normalized": true,
|
| 24 |
"rstrip": false,
|
| 25 |
"single_word": false,
|
| 26 |
+
"special": false
|
| 27 |
+
},
|
| 28 |
+
"50255": {
|
| 29 |
+
"content": " ",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": false
|
| 35 |
+
},
|
| 36 |
+
"50256": {
|
| 37 |
+
"content": " ",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": false
|
| 43 |
+
},
|
| 44 |
+
"50257": {
|
| 45 |
+
"content": " ",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": false
|
| 51 |
+
},
|
| 52 |
+
"50258": {
|
| 53 |
+
"content": " ",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": false
|
| 59 |
+
},
|
| 60 |
+
"50259": {
|
| 61 |
+
"content": " ",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": true,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": false
|
| 67 |
+
},
|
| 68 |
+
"50260": {
|
| 69 |
+
"content": " ",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": false
|
| 75 |
+
},
|
| 76 |
+
"50261": {
|
| 77 |
+
"content": " ",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": true,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": false
|
| 83 |
+
},
|
| 84 |
+
"50262": {
|
| 85 |
+
"content": " ",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": true,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": false
|
| 91 |
+
},
|
| 92 |
+
"50263": {
|
| 93 |
+
"content": " ",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": true,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": false
|
| 99 |
+
},
|
| 100 |
+
"50264": {
|
| 101 |
+
"content": " ",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": true,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": false
|
| 107 |
+
},
|
| 108 |
+
"50265": {
|
| 109 |
+
"content": " ",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": true,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": false
|
| 115 |
+
},
|
| 116 |
+
"50266": {
|
| 117 |
+
"content": " ",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": true,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": false
|
| 123 |
+
},
|
| 124 |
+
"50267": {
|
| 125 |
+
"content": " ",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": true,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": false
|
| 131 |
+
},
|
| 132 |
+
"50268": {
|
| 133 |
+
"content": " ",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": true,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": false
|
| 139 |
+
},
|
| 140 |
+
"50269": {
|
| 141 |
+
"content": " ",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": true,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": false
|
| 147 |
+
},
|
| 148 |
+
"50270": {
|
| 149 |
+
"content": " ",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": true,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": false
|
| 155 |
+
},
|
| 156 |
+
"50271": {
|
| 157 |
+
"content": " ",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": true,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": false
|
| 163 |
+
},
|
| 164 |
+
"50272": {
|
| 165 |
+
"content": " ",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": true,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": false
|
| 171 |
+
},
|
| 172 |
+
"50273": {
|
| 173 |
+
"content": " ",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": true,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": false
|
| 179 |
+
},
|
| 180 |
+
"50274": {
|
| 181 |
+
"content": " ",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": true,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": false
|
| 187 |
+
},
|
| 188 |
+
"50275": {
|
| 189 |
+
"content": " ",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": true,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": false
|
| 195 |
+
},
|
| 196 |
+
"50276": {
|
| 197 |
+
"content": " ",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": true,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": false
|
| 203 |
}
|
| 204 |
},
|
| 205 |
+
"bos_token": "<|endoftext|>",
|
| 206 |
+
"clean_up_tokenization_spaces": true,
|
| 207 |
+
"eos_token": "<|endoftext|>",
|
| 208 |
"model_max_length": 1024,
|
| 209 |
+
"pad_token": "<|endoftext|>",
|
| 210 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 211 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
| 212 |
}
|
trainer_state.json
CHANGED
|
@@ -1,18 +1,325 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.
|
| 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 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
"num_train_epochs": 3,
|
| 14 |
"save_steps": 500,
|
| 15 |
-
"total_flos":
|
| 16 |
"trial_name": null,
|
| 17 |
"trial_params": null
|
| 18 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.978102189781022,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 102,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 14 |
+
"loss": 1.8667,
|
| 15 |
+
"step": 2
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 7.272727272727273e-05,
|
| 20 |
+
"loss": 1.669,
|
| 21 |
+
"step": 4
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.18,
|
| 25 |
+
"learning_rate": 0.00010909090909090909,
|
| 26 |
+
"loss": 1.607,
|
| 27 |
+
"step": 6
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.23,
|
| 31 |
+
"learning_rate": 0.00014545454545454546,
|
| 32 |
+
"loss": 2.0734,
|
| 33 |
+
"step": 8
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.29,
|
| 37 |
+
"learning_rate": 0.00018181818181818183,
|
| 38 |
+
"loss": 1.5327,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.35,
|
| 43 |
+
"learning_rate": 0.0001978021978021978,
|
| 44 |
+
"loss": 1.7996,
|
| 45 |
+
"step": 12
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.41,
|
| 49 |
+
"learning_rate": 0.00019340659340659342,
|
| 50 |
+
"loss": 1.6866,
|
| 51 |
+
"step": 14
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.47,
|
| 55 |
+
"learning_rate": 0.00018901098901098903,
|
| 56 |
+
"loss": 1.6299,
|
| 57 |
+
"step": 16
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.53,
|
| 61 |
+
"learning_rate": 0.00018461538461538463,
|
| 62 |
+
"loss": 1.8521,
|
| 63 |
+
"step": 18
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.58,
|
| 67 |
+
"learning_rate": 0.00018021978021978024,
|
| 68 |
+
"loss": 1.7468,
|
| 69 |
+
"step": 20
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.64,
|
| 73 |
+
"learning_rate": 0.00017582417582417582,
|
| 74 |
+
"loss": 1.8712,
|
| 75 |
+
"step": 22
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.7,
|
| 79 |
+
"learning_rate": 0.00017142857142857143,
|
| 80 |
+
"loss": 1.6447,
|
| 81 |
+
"step": 24
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.76,
|
| 85 |
+
"learning_rate": 0.00016703296703296706,
|
| 86 |
+
"loss": 1.7091,
|
| 87 |
+
"step": 26
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.82,
|
| 91 |
+
"learning_rate": 0.00016263736263736264,
|
| 92 |
+
"loss": 1.5068,
|
| 93 |
+
"step": 28
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.88,
|
| 97 |
+
"learning_rate": 0.00015824175824175824,
|
| 98 |
+
"loss": 1.7822,
|
| 99 |
+
"step": 30
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.93,
|
| 103 |
+
"learning_rate": 0.00015384615384615385,
|
| 104 |
+
"loss": 1.7897,
|
| 105 |
+
"step": 32
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.99,
|
| 109 |
+
"learning_rate": 0.00014945054945054946,
|
| 110 |
+
"loss": 1.5594,
|
| 111 |
+
"step": 34
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.05,
|
| 115 |
+
"learning_rate": 0.00014505494505494506,
|
| 116 |
+
"loss": 1.5073,
|
| 117 |
+
"step": 36
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.11,
|
| 121 |
+
"learning_rate": 0.00014065934065934067,
|
| 122 |
+
"loss": 2.0299,
|
| 123 |
+
"step": 38
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.17,
|
| 127 |
+
"learning_rate": 0.00013626373626373628,
|
| 128 |
+
"loss": 1.643,
|
| 129 |
+
"step": 40
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.23,
|
| 133 |
+
"learning_rate": 0.00013186813186813188,
|
| 134 |
+
"loss": 1.5875,
|
| 135 |
+
"step": 42
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.28,
|
| 139 |
+
"learning_rate": 0.00012747252747252746,
|
| 140 |
+
"loss": 1.5646,
|
| 141 |
+
"step": 44
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.34,
|
| 145 |
+
"learning_rate": 0.0001230769230769231,
|
| 146 |
+
"loss": 1.4487,
|
| 147 |
+
"step": 46
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.4,
|
| 151 |
+
"learning_rate": 0.00011868131868131869,
|
| 152 |
+
"loss": 1.7054,
|
| 153 |
+
"step": 48
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.46,
|
| 157 |
+
"learning_rate": 0.00011428571428571428,
|
| 158 |
+
"loss": 1.5121,
|
| 159 |
+
"step": 50
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.52,
|
| 163 |
+
"learning_rate": 0.0001098901098901099,
|
| 164 |
+
"loss": 1.2679,
|
| 165 |
+
"step": 52
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.58,
|
| 169 |
+
"learning_rate": 0.0001054945054945055,
|
| 170 |
+
"loss": 1.2186,
|
| 171 |
+
"step": 54
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.64,
|
| 175 |
+
"learning_rate": 0.0001010989010989011,
|
| 176 |
+
"loss": 1.7126,
|
| 177 |
+
"step": 56
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.69,
|
| 181 |
+
"learning_rate": 9.670329670329671e-05,
|
| 182 |
+
"loss": 1.4419,
|
| 183 |
+
"step": 58
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.75,
|
| 187 |
+
"learning_rate": 9.230769230769232e-05,
|
| 188 |
+
"loss": 1.4208,
|
| 189 |
+
"step": 60
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.81,
|
| 193 |
+
"learning_rate": 8.791208791208791e-05,
|
| 194 |
+
"loss": 1.5867,
|
| 195 |
+
"step": 62
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.87,
|
| 199 |
+
"learning_rate": 8.351648351648353e-05,
|
| 200 |
+
"loss": 1.4981,
|
| 201 |
+
"step": 64
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.93,
|
| 205 |
+
"learning_rate": 7.912087912087912e-05,
|
| 206 |
+
"loss": 1.5029,
|
| 207 |
+
"step": 66
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.99,
|
| 211 |
+
"learning_rate": 7.472527472527473e-05,
|
| 212 |
+
"loss": 1.2939,
|
| 213 |
+
"step": 68
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.04,
|
| 217 |
+
"learning_rate": 7.032967032967034e-05,
|
| 218 |
+
"loss": 1.6456,
|
| 219 |
+
"step": 70
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.1,
|
| 223 |
+
"learning_rate": 6.593406593406594e-05,
|
| 224 |
+
"loss": 1.5256,
|
| 225 |
+
"step": 72
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.16,
|
| 229 |
+
"learning_rate": 6.153846153846155e-05,
|
| 230 |
+
"loss": 1.2921,
|
| 231 |
+
"step": 74
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.22,
|
| 235 |
+
"learning_rate": 5.714285714285714e-05,
|
| 236 |
+
"loss": 1.292,
|
| 237 |
+
"step": 76
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.28,
|
| 241 |
+
"learning_rate": 5.274725274725275e-05,
|
| 242 |
+
"loss": 1.3151,
|
| 243 |
+
"step": 78
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.34,
|
| 247 |
+
"learning_rate": 4.8351648351648355e-05,
|
| 248 |
+
"loss": 1.8621,
|
| 249 |
+
"step": 80
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.39,
|
| 253 |
+
"learning_rate": 4.3956043956043955e-05,
|
| 254 |
+
"loss": 1.3737,
|
| 255 |
+
"step": 82
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.45,
|
| 259 |
+
"learning_rate": 3.956043956043956e-05,
|
| 260 |
+
"loss": 1.4477,
|
| 261 |
+
"step": 84
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.51,
|
| 265 |
+
"learning_rate": 3.516483516483517e-05,
|
| 266 |
+
"loss": 1.4073,
|
| 267 |
+
"step": 86
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.57,
|
| 271 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 272 |
+
"loss": 1.4966,
|
| 273 |
+
"step": 88
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.63,
|
| 277 |
+
"learning_rate": 2.6373626373626374e-05,
|
| 278 |
+
"loss": 1.1487,
|
| 279 |
+
"step": 90
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.69,
|
| 283 |
+
"learning_rate": 2.1978021978021977e-05,
|
| 284 |
+
"loss": 1.3299,
|
| 285 |
+
"step": 92
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.74,
|
| 289 |
+
"learning_rate": 1.7582417582417584e-05,
|
| 290 |
+
"loss": 1.7217,
|
| 291 |
+
"step": 94
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.8,
|
| 295 |
+
"learning_rate": 1.3186813186813187e-05,
|
| 296 |
+
"loss": 1.2555,
|
| 297 |
+
"step": 96
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.86,
|
| 301 |
+
"learning_rate": 8.791208791208792e-06,
|
| 302 |
+
"loss": 1.3967,
|
| 303 |
+
"step": 98
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.92,
|
| 307 |
+
"learning_rate": 4.395604395604396e-06,
|
| 308 |
+
"loss": 1.5847,
|
| 309 |
+
"step": 100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.98,
|
| 313 |
+
"learning_rate": 0.0,
|
| 314 |
+
"loss": 1.6002,
|
| 315 |
+
"step": 102
|
| 316 |
+
}
|
| 317 |
+
],
|
| 318 |
+
"logging_steps": 2,
|
| 319 |
+
"max_steps": 102,
|
| 320 |
"num_train_epochs": 3,
|
| 321 |
"save_steps": 500,
|
| 322 |
+
"total_flos": 2.6947930854260736e+16,
|
| 323 |
"trial_name": null,
|
| 324 |
"trial_params": null
|
| 325 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4472
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26d1905ca3abf82ab3bf45211ffccc2ef759d09640a7293e39e0c1a0ddd98eb0
|
| 3 |
size 4472
|