Training in progress, epoch 46, checkpoint
Browse files- checkpoint-8812/adapter_config.json +1 -1
- checkpoint-8812/adapter_model.bin +3 -0
- checkpoint-8812/added_tokens.json +3 -3
- checkpoint-8812/optimizer.pt +2 -2
- checkpoint-8812/rng_state_0.pth +1 -1
- checkpoint-8812/rng_state_1.pth +1 -1
- checkpoint-8812/rng_state_2.pth +1 -1
- checkpoint-8812/rng_state_3.pth +1 -1
- checkpoint-8812/special_tokens_map.json +4 -12
- checkpoint-8812/tokenizer.json +0 -0
- checkpoint-8812/tokenizer.model +3 -0
- checkpoint-8812/tokenizer_config.json +17 -20
- checkpoint-8812/trainer_state.json +524 -626
- checkpoint-8812/training_args.bin +2 -2
checkpoint-8812/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,
|
|
|
|
| 1 |
{
|
| 2 |
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
| 4 |
"bias": "none",
|
| 5 |
"fan_in_fan_out": false,
|
| 6 |
"inference_mode": true,
|
checkpoint-8812/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99568ee19adece13719b46b1ab441857bdbd6e22e65712641508ee3dfd1db88c
|
| 3 |
+
size 143269386
|
checkpoint-8812/added_tokens.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"</s>": 2,
|
| 3 |
+
"<s>": 1,
|
| 4 |
+
"<unk>": 0
|
| 5 |
}
|
checkpoint-8812/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:af525b332a4e82829deffe122a7acb13158c36f2219bbc46ae8f88291d3c4c0d
|
| 3 |
+
size 286585234
|
checkpoint-8812/rng_state_0.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b05d0b5cc03817ab8fd8102c8b8a1d2dc36bd263421763d32bf0bed32eddaafc
|
| 3 |
size 15024
|
checkpoint-8812/rng_state_1.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c283538ddc6e3aeab308b91fe47c500a5220a020e2c9857ae2f528cb2d2dc589
|
| 3 |
size 15024
|
checkpoint-8812/rng_state_2.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:493f3513a70345f31465797381e5f15e827e5439980f28ac7c39f9a1a9d5e090
|
| 3 |
size 15024
|
checkpoint-8812/rng_state_3.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffd053072bbabcaadaa1e75a0f283f63ea3d8b322769e311111fbbe0167bb675
|
| 3 |
size 15024
|
checkpoint-8812/special_tokens_map.json
CHANGED
|
@@ -1,14 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
"eos_token": {
|
| 7 |
-
"content": "<|endoftext|>",
|
| 8 |
-
"lstrip": false,
|
| 9 |
-
"normalized": false,
|
| 10 |
-
"rstrip": false,
|
| 11 |
-
"single_word": false
|
| 12 |
-
},
|
| 13 |
-
"pad_token": "<|endoftext|>"
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "</s>",
|
| 5 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
}
|
checkpoint-8812/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8812/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-8812/tokenizer_config.json
CHANGED
|
@@ -1,24 +1,23 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
-
"
|
| 5 |
-
"content": "
|
| 6 |
"lstrip": false,
|
| 7 |
"normalized": false,
|
| 8 |
"rstrip": false,
|
| 9 |
"single_word": false,
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
-
"
|
| 13 |
-
"content": "
|
| 14 |
"lstrip": false,
|
| 15 |
"normalized": false,
|
| 16 |
"rstrip": false,
|
| 17 |
"single_word": false,
|
| 18 |
"special": true
|
| 19 |
},
|
| 20 |
-
"
|
| 21 |
-
"content": "
|
| 22 |
"lstrip": false,
|
| 23 |
"normalized": false,
|
| 24 |
"rstrip": false,
|
|
@@ -26,18 +25,16 @@
|
|
| 26 |
"special": true
|
| 27 |
}
|
| 28 |
},
|
| 29 |
-
"additional_special_tokens": [
|
| 30 |
-
|
| 31 |
-
"<|im_end|>"
|
| 32 |
-
],
|
| 33 |
-
"bos_token": null,
|
| 34 |
-
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
| 35 |
"clean_up_tokenization_spaces": false,
|
| 36 |
-
"eos_token": "
|
| 37 |
-
"
|
| 38 |
-
"model_max_length":
|
| 39 |
-
"pad_token": "
|
| 40 |
-
"
|
| 41 |
-
"
|
| 42 |
-
"
|
|
|
|
|
|
|
| 43 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
"lstrip": false,
|
| 6 |
"normalized": false,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
"special": true
|
| 10 |
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": false,
|
| 15 |
"rstrip": false,
|
| 16 |
"single_word": false,
|
| 17 |
"special": true
|
| 18 |
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
"lstrip": false,
|
| 22 |
"normalized": false,
|
| 23 |
"rstrip": false,
|
|
|
|
| 25 |
"special": true
|
| 26 |
}
|
| 27 |
},
|
| 28 |
+
"additional_special_tokens": [],
|
| 29 |
+
"bos_token": "<s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
"clean_up_tokenization_spaces": false,
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"legacy": false,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": "</s>",
|
| 35 |
+
"padding_side": "left",
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 38 |
+
"unk_token": "<unk>",
|
| 39 |
+
"use_default_system_prompt": true
|
| 40 |
}
|
checkpoint-8812/trainer_state.json
CHANGED
|
@@ -9,1346 +9,1244 @@
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"grad_norm": 0.7527768015861511,
|
| 14 |
"learning_rate": 0.0005,
|
| 15 |
-
"loss": 1.
|
| 16 |
"step": 100
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0
|
| 20 |
-
"eval_accuracy": 0.
|
| 21 |
-
"eval_loss": 1.
|
| 22 |
-
"eval_runtime":
|
| 23 |
-
"eval_samples_per_second":
|
| 24 |
-
"eval_steps_per_second": 12.
|
| 25 |
"step": 187
|
| 26 |
},
|
| 27 |
{
|
| 28 |
-
"epoch": 0
|
| 29 |
-
"eval_exact_match":
|
| 30 |
-
"eval_f1":
|
| 31 |
"step": 187
|
| 32 |
},
|
| 33 |
{
|
| 34 |
-
"epoch": 1.
|
| 35 |
-
"grad_norm": 0.7723727226257324,
|
| 36 |
"learning_rate": 0.0005,
|
| 37 |
-
"loss": 1.
|
| 38 |
"step": 200
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 1.6,
|
| 42 |
-
"grad_norm": 0.8481244444847107,
|
| 43 |
"learning_rate": 0.0005,
|
| 44 |
-
"loss": 1.
|
| 45 |
"step": 300
|
| 46 |
},
|
| 47 |
{
|
| 48 |
"epoch": 2.0,
|
| 49 |
-
"eval_accuracy": 0.
|
| 50 |
-
"eval_loss": 1.
|
| 51 |
-
"eval_runtime":
|
| 52 |
-
"eval_samples_per_second":
|
| 53 |
-
"eval_steps_per_second":
|
| 54 |
"step": 375
|
| 55 |
},
|
| 56 |
{
|
| 57 |
"epoch": 2.0,
|
| 58 |
-
"eval_exact_match":
|
| 59 |
-
"eval_f1":
|
| 60 |
"step": 375
|
| 61 |
},
|
| 62 |
{
|
| 63 |
-
"epoch": 2.
|
| 64 |
-
"grad_norm": 0.810580313205719,
|
| 65 |
"learning_rate": 0.0005,
|
| 66 |
-
"loss":
|
| 67 |
"step": 400
|
| 68 |
},
|
| 69 |
{
|
| 70 |
-
"epoch": 2.
|
| 71 |
-
"grad_norm": 0.8971414566040039,
|
| 72 |
"learning_rate": 0.0005,
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"eval_accuracy": 0.
|
| 79 |
-
"eval_loss": 1.
|
| 80 |
-
"eval_runtime": 4.
|
| 81 |
-
"eval_samples_per_second":
|
| 82 |
-
"eval_steps_per_second":
|
| 83 |
"step": 562
|
| 84 |
},
|
| 85 |
{
|
| 86 |
-
"epoch":
|
| 87 |
-
"eval_exact_match":
|
| 88 |
-
"eval_f1":
|
| 89 |
"step": 562
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 3.2,
|
| 93 |
-
"grad_norm": 0.7627168297767639,
|
| 94 |
"learning_rate": 0.0005,
|
| 95 |
-
"loss": 0.
|
| 96 |
"step": 600
|
| 97 |
},
|
| 98 |
{
|
| 99 |
-
"epoch": 3.
|
| 100 |
-
"grad_norm": 0.7384397387504578,
|
| 101 |
"learning_rate": 0.0005,
|
| 102 |
-
"loss": 0.
|
| 103 |
"step": 700
|
| 104 |
},
|
| 105 |
{
|
| 106 |
"epoch": 4.0,
|
| 107 |
-
"eval_accuracy": 0.
|
| 108 |
-
"eval_loss": 1.
|
| 109 |
-
"eval_runtime":
|
| 110 |
-
"eval_samples_per_second":
|
| 111 |
-
"eval_steps_per_second":
|
| 112 |
"step": 750
|
| 113 |
},
|
| 114 |
{
|
| 115 |
"epoch": 4.0,
|
| 116 |
-
"eval_exact_match":
|
| 117 |
-
"eval_f1":
|
| 118 |
"step": 750
|
| 119 |
},
|
| 120 |
{
|
| 121 |
-
"epoch": 4.
|
| 122 |
-
"grad_norm": 0.7065069079399109,
|
| 123 |
"learning_rate": 0.0005,
|
| 124 |
-
"loss": 0.
|
| 125 |
"step": 800
|
| 126 |
},
|
| 127 |
{
|
| 128 |
"epoch": 4.8,
|
| 129 |
-
"grad_norm": 0.7625908851623535,
|
| 130 |
"learning_rate": 0.0005,
|
| 131 |
-
"loss": 0.
|
| 132 |
"step": 900
|
| 133 |
},
|
| 134 |
{
|
| 135 |
-
"epoch":
|
| 136 |
-
"eval_accuracy": 0.
|
| 137 |
-
"eval_loss":
|
| 138 |
-
"eval_runtime":
|
| 139 |
-
"eval_samples_per_second":
|
| 140 |
-
"eval_steps_per_second":
|
| 141 |
"step": 937
|
| 142 |
},
|
| 143 |
{
|
| 144 |
-
"epoch":
|
| 145 |
-
"eval_exact_match":
|
| 146 |
-
"eval_f1":
|
| 147 |
"step": 937
|
| 148 |
},
|
| 149 |
{
|
| 150 |
-
"epoch": 5.
|
| 151 |
-
"grad_norm": 0.6257635951042175,
|
| 152 |
"learning_rate": 0.0005,
|
| 153 |
-
"loss": 0.
|
| 154 |
"step": 1000
|
| 155 |
},
|
| 156 |
{
|
| 157 |
-
"epoch": 5.
|
| 158 |
-
"grad_norm": 0.7330732345581055,
|
| 159 |
"learning_rate": 0.0005,
|
| 160 |
-
"loss": 0.
|
| 161 |
"step": 1100
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 6.0,
|
| 165 |
-
"eval_accuracy": 0.
|
| 166 |
-
"eval_loss":
|
| 167 |
-
"eval_runtime":
|
| 168 |
-
"eval_samples_per_second":
|
| 169 |
-
"eval_steps_per_second":
|
| 170 |
"step": 1125
|
| 171 |
},
|
| 172 |
{
|
| 173 |
"epoch": 6.0,
|
| 174 |
-
"eval_exact_match":
|
| 175 |
-
"eval_f1":
|
| 176 |
"step": 1125
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 6.4,
|
| 180 |
-
"grad_norm": 0.5348079204559326,
|
| 181 |
"learning_rate": 0.0005,
|
| 182 |
-
"loss": 0.
|
| 183 |
"step": 1200
|
| 184 |
},
|
| 185 |
{
|
| 186 |
-
"epoch": 6.
|
| 187 |
-
"grad_norm": 0.4842449426651001,
|
| 188 |
"learning_rate": 0.0005,
|
| 189 |
-
"loss": 0.
|
| 190 |
"step": 1300
|
| 191 |
},
|
| 192 |
{
|
| 193 |
-
"epoch":
|
| 194 |
-
"eval_accuracy": 0.
|
| 195 |
-
"eval_loss":
|
| 196 |
-
"eval_runtime":
|
| 197 |
-
"eval_samples_per_second":
|
| 198 |
-
"eval_steps_per_second": 12.
|
| 199 |
"step": 1312
|
| 200 |
},
|
| 201 |
{
|
| 202 |
-
"epoch":
|
| 203 |
-
"eval_exact_match":
|
| 204 |
-
"eval_f1":
|
| 205 |
"step": 1312
|
| 206 |
},
|
| 207 |
{
|
| 208 |
-
"epoch": 7.
|
| 209 |
-
"grad_norm": 0.5476555824279785,
|
| 210 |
"learning_rate": 0.0005,
|
| 211 |
-
"loss": 0.
|
| 212 |
"step": 1400
|
| 213 |
},
|
| 214 |
{
|
| 215 |
"epoch": 8.0,
|
| 216 |
-
"grad_norm": 0.8545846939086914,
|
| 217 |
"learning_rate": 0.0005,
|
| 218 |
-
"loss": 0.
|
| 219 |
"step": 1500
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 8.0,
|
| 223 |
-
"eval_accuracy": 0.
|
| 224 |
-
"eval_loss":
|
| 225 |
-
"eval_runtime":
|
| 226 |
-
"eval_samples_per_second":
|
| 227 |
-
"eval_steps_per_second":
|
| 228 |
"step": 1500
|
| 229 |
},
|
| 230 |
{
|
| 231 |
"epoch": 8.0,
|
| 232 |
-
"eval_exact_match":
|
| 233 |
-
"eval_f1":
|
| 234 |
"step": 1500
|
| 235 |
},
|
| 236 |
{
|
| 237 |
-
"epoch": 8.
|
| 238 |
-
"grad_norm": 0.5809034705162048,
|
| 239 |
"learning_rate": 0.0005,
|
| 240 |
-
"loss": 0.
|
| 241 |
"step": 1600
|
| 242 |
},
|
| 243 |
{
|
| 244 |
-
"epoch":
|
| 245 |
-
"eval_accuracy": 0.
|
| 246 |
-
"eval_loss":
|
| 247 |
-
"eval_runtime":
|
| 248 |
-
"eval_samples_per_second":
|
| 249 |
-
"eval_steps_per_second":
|
| 250 |
"step": 1687
|
| 251 |
},
|
| 252 |
{
|
| 253 |
-
"epoch":
|
| 254 |
-
"eval_exact_match":
|
| 255 |
-
"eval_f1":
|
| 256 |
"step": 1687
|
| 257 |
},
|
| 258 |
{
|
| 259 |
-
"epoch": 9.
|
| 260 |
-
"grad_norm": 0.48757097125053406,
|
| 261 |
"learning_rate": 0.0005,
|
| 262 |
-
"loss": 0.
|
| 263 |
"step": 1700
|
| 264 |
},
|
| 265 |
{
|
| 266 |
"epoch": 9.6,
|
| 267 |
-
"grad_norm": 0.5225056409835815,
|
| 268 |
"learning_rate": 0.0005,
|
| 269 |
-
"loss": 0.
|
| 270 |
"step": 1800
|
| 271 |
},
|
| 272 |
{
|
| 273 |
"epoch": 10.0,
|
| 274 |
-
"eval_accuracy": 0.
|
| 275 |
-
"eval_loss":
|
| 276 |
-
"eval_runtime":
|
| 277 |
-
"eval_samples_per_second":
|
| 278 |
-
"eval_steps_per_second":
|
| 279 |
"step": 1875
|
| 280 |
},
|
| 281 |
{
|
| 282 |
"epoch": 10.0,
|
| 283 |
-
"eval_exact_match":
|
| 284 |
-
"eval_f1":
|
| 285 |
"step": 1875
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch": 10.
|
| 289 |
-
"grad_norm": 0.7123950719833374,
|
| 290 |
"learning_rate": 0.0005,
|
| 291 |
-
"loss": 0.
|
| 292 |
"step": 1900
|
| 293 |
},
|
| 294 |
{
|
| 295 |
-
"epoch": 10.
|
| 296 |
-
"grad_norm": 0.48232755064964294,
|
| 297 |
"learning_rate": 0.0005,
|
| 298 |
-
"loss": 0.
|
| 299 |
"step": 2000
|
| 300 |
},
|
| 301 |
{
|
| 302 |
-
"epoch":
|
| 303 |
-
"eval_accuracy": 0.
|
| 304 |
-
"eval_loss":
|
| 305 |
-
"eval_runtime":
|
| 306 |
-
"eval_samples_per_second":
|
| 307 |
-
"eval_steps_per_second":
|
| 308 |
"step": 2062
|
| 309 |
},
|
| 310 |
{
|
| 311 |
-
"epoch":
|
| 312 |
-
"eval_exact_match":
|
| 313 |
-
"eval_f1":
|
| 314 |
"step": 2062
|
| 315 |
},
|
| 316 |
{
|
| 317 |
"epoch": 11.2,
|
| 318 |
-
"grad_norm": 0.6355456113815308,
|
| 319 |
"learning_rate": 0.0005,
|
| 320 |
-
"loss": 0.
|
| 321 |
"step": 2100
|
| 322 |
},
|
| 323 |
{
|
| 324 |
-
"epoch": 11.
|
| 325 |
-
"grad_norm": 0.7310680150985718,
|
| 326 |
"learning_rate": 0.0005,
|
| 327 |
-
"loss": 0.
|
| 328 |
"step": 2200
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 12.0,
|
| 332 |
-
"eval_accuracy": 0.
|
| 333 |
-
"eval_loss":
|
| 334 |
-
"eval_runtime":
|
| 335 |
-
"eval_samples_per_second":
|
| 336 |
-
"eval_steps_per_second":
|
| 337 |
"step": 2250
|
| 338 |
},
|
| 339 |
{
|
| 340 |
"epoch": 12.0,
|
| 341 |
-
"eval_exact_match":
|
| 342 |
-
"eval_f1":
|
| 343 |
"step": 2250
|
| 344 |
},
|
| 345 |
{
|
| 346 |
-
"epoch": 12.
|
| 347 |
-
"grad_norm": 0.8953878879547119,
|
| 348 |
"learning_rate": 0.0005,
|
| 349 |
-
"loss": 0.
|
| 350 |
"step": 2300
|
| 351 |
},
|
| 352 |
{
|
| 353 |
"epoch": 12.8,
|
| 354 |
-
"grad_norm": 0.8268033266067505,
|
| 355 |
"learning_rate": 0.0005,
|
| 356 |
-
"loss": 0.
|
| 357 |
"step": 2400
|
| 358 |
},
|
| 359 |
{
|
| 360 |
-
"epoch":
|
| 361 |
-
"eval_accuracy": 0.
|
| 362 |
-
"eval_loss":
|
| 363 |
-
"eval_runtime":
|
| 364 |
-
"eval_samples_per_second":
|
| 365 |
-
"eval_steps_per_second":
|
| 366 |
"step": 2437
|
| 367 |
},
|
| 368 |
{
|
| 369 |
-
"epoch":
|
| 370 |
-
"eval_exact_match":
|
| 371 |
-
"eval_f1":
|
| 372 |
"step": 2437
|
| 373 |
},
|
| 374 |
{
|
| 375 |
-
"epoch": 13.
|
| 376 |
-
"grad_norm": 0.9471064209938049,
|
| 377 |
"learning_rate": 0.0005,
|
| 378 |
-
"loss": 0.
|
| 379 |
"step": 2500
|
| 380 |
},
|
| 381 |
{
|
| 382 |
-
"epoch": 13.
|
| 383 |
-
"grad_norm": 1.0178123712539673,
|
| 384 |
"learning_rate": 0.0005,
|
| 385 |
-
"loss": 0.
|
| 386 |
"step": 2600
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 14.0,
|
| 390 |
-
"eval_accuracy": 0.
|
| 391 |
-
"eval_loss":
|
| 392 |
-
"eval_runtime":
|
| 393 |
-
"eval_samples_per_second":
|
| 394 |
-
"eval_steps_per_second":
|
| 395 |
"step": 2625
|
| 396 |
},
|
| 397 |
{
|
| 398 |
"epoch": 14.0,
|
| 399 |
-
"eval_exact_match":
|
| 400 |
-
"eval_f1":
|
| 401 |
"step": 2625
|
| 402 |
},
|
| 403 |
{
|
| 404 |
"epoch": 14.4,
|
| 405 |
-
"grad_norm": 0.750542402267456,
|
| 406 |
"learning_rate": 0.0005,
|
| 407 |
-
"loss": 0.
|
| 408 |
"step": 2700
|
| 409 |
},
|
| 410 |
{
|
| 411 |
-
"epoch": 14.
|
| 412 |
-
"grad_norm": 0.8345568776130676,
|
| 413 |
"learning_rate": 0.0005,
|
| 414 |
-
"loss": 0.
|
| 415 |
"step": 2800
|
| 416 |
},
|
| 417 |
{
|
| 418 |
-
"epoch":
|
| 419 |
-
"eval_accuracy": 0.
|
| 420 |
-
"eval_loss":
|
| 421 |
-
"eval_runtime":
|
| 422 |
-
"eval_samples_per_second":
|
| 423 |
-
"eval_steps_per_second":
|
| 424 |
"step": 2812
|
| 425 |
},
|
| 426 |
{
|
| 427 |
-
"epoch":
|
| 428 |
-
"eval_exact_match":
|
| 429 |
-
"eval_f1":
|
| 430 |
"step": 2812
|
| 431 |
},
|
| 432 |
{
|
| 433 |
-
"epoch": 15.
|
| 434 |
-
"grad_norm": 0.60535728931427,
|
| 435 |
"learning_rate": 0.0005,
|
| 436 |
-
"loss": 0.
|
| 437 |
"step": 2900
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 16.0,
|
| 441 |
-
"grad_norm": 0.7003186941146851,
|
| 442 |
"learning_rate": 0.0005,
|
| 443 |
-
"loss": 0.
|
| 444 |
"step": 3000
|
| 445 |
},
|
| 446 |
{
|
| 447 |
"epoch": 16.0,
|
| 448 |
-
"eval_accuracy": 0.
|
| 449 |
-
"eval_loss":
|
| 450 |
-
"eval_runtime":
|
| 451 |
-
"eval_samples_per_second":
|
| 452 |
-
"eval_steps_per_second":
|
| 453 |
"step": 3000
|
| 454 |
},
|
| 455 |
{
|
| 456 |
"epoch": 16.0,
|
| 457 |
-
"eval_exact_match":
|
| 458 |
-
"eval_f1":
|
| 459 |
"step": 3000
|
| 460 |
},
|
| 461 |
{
|
| 462 |
-
"epoch": 16.
|
| 463 |
-
"grad_norm": 0.9538315534591675,
|
| 464 |
"learning_rate": 0.0005,
|
| 465 |
-
"loss": 0.
|
| 466 |
"step": 3100
|
| 467 |
},
|
| 468 |
{
|
| 469 |
-
"epoch":
|
| 470 |
-
"eval_accuracy": 0.
|
| 471 |
-
"eval_loss":
|
| 472 |
-
"eval_runtime":
|
| 473 |
-
"eval_samples_per_second":
|
| 474 |
-
"eval_steps_per_second":
|
| 475 |
"step": 3187
|
| 476 |
},
|
| 477 |
{
|
| 478 |
-
"epoch":
|
| 479 |
-
"eval_exact_match":
|
| 480 |
-
"eval_f1":
|
| 481 |
"step": 3187
|
| 482 |
},
|
| 483 |
{
|
| 484 |
-
"epoch": 17.
|
| 485 |
-
"grad_norm": 0.7299863696098328,
|
| 486 |
"learning_rate": 0.0005,
|
| 487 |
-
"loss": 0.
|
| 488 |
"step": 3200
|
| 489 |
},
|
| 490 |
{
|
| 491 |
"epoch": 17.6,
|
| 492 |
-
"grad_norm": 0.49411433935165405,
|
| 493 |
"learning_rate": 0.0005,
|
| 494 |
-
"loss": 0.
|
| 495 |
"step": 3300
|
| 496 |
},
|
| 497 |
{
|
| 498 |
"epoch": 18.0,
|
| 499 |
-
"eval_accuracy": 0.
|
| 500 |
-
"eval_loss":
|
| 501 |
-
"eval_runtime":
|
| 502 |
-
"eval_samples_per_second":
|
| 503 |
-
"eval_steps_per_second":
|
| 504 |
"step": 3375
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 18.0,
|
| 508 |
-
"eval_exact_match":
|
| 509 |
-
"eval_f1":
|
| 510 |
"step": 3375
|
| 511 |
},
|
| 512 |
{
|
| 513 |
-
"epoch": 18.
|
| 514 |
-
"grad_norm": 0.5169008374214172,
|
| 515 |
"learning_rate": 0.0005,
|
| 516 |
-
"loss": 0.
|
| 517 |
"step": 3400
|
| 518 |
},
|
| 519 |
{
|
| 520 |
-
"epoch": 18.
|
| 521 |
-
"grad_norm": 0.4064069092273712,
|
| 522 |
"learning_rate": 0.0005,
|
| 523 |
-
"loss": 0.
|
| 524 |
"step": 3500
|
| 525 |
},
|
| 526 |
{
|
| 527 |
-
"epoch":
|
| 528 |
-
"eval_accuracy": 0.
|
| 529 |
-
"eval_loss":
|
| 530 |
-
"eval_runtime":
|
| 531 |
-
"eval_samples_per_second":
|
| 532 |
-
"eval_steps_per_second":
|
| 533 |
"step": 3562
|
| 534 |
},
|
| 535 |
{
|
| 536 |
-
"epoch":
|
| 537 |
-
"eval_exact_match":
|
| 538 |
-
"eval_f1":
|
| 539 |
"step": 3562
|
| 540 |
},
|
| 541 |
{
|
| 542 |
"epoch": 19.2,
|
| 543 |
-
"grad_norm": 0.362119197845459,
|
| 544 |
"learning_rate": 0.0005,
|
| 545 |
-
"loss": 0.
|
| 546 |
"step": 3600
|
| 547 |
},
|
| 548 |
{
|
| 549 |
-
"epoch": 19.
|
| 550 |
-
"grad_norm": 0.45963579416275024,
|
| 551 |
"learning_rate": 0.0005,
|
| 552 |
-
"loss": 0.
|
| 553 |
"step": 3700
|
| 554 |
},
|
| 555 |
{
|
| 556 |
"epoch": 20.0,
|
| 557 |
-
"eval_accuracy": 0.
|
| 558 |
-
"eval_loss":
|
| 559 |
-
"eval_runtime":
|
| 560 |
-
"eval_samples_per_second":
|
| 561 |
-
"eval_steps_per_second":
|
| 562 |
"step": 3750
|
| 563 |
},
|
| 564 |
{
|
| 565 |
"epoch": 20.0,
|
| 566 |
-
"eval_exact_match":
|
| 567 |
-
"eval_f1":
|
| 568 |
"step": 3750
|
| 569 |
},
|
| 570 |
{
|
| 571 |
-
"epoch": 20.
|
| 572 |
-
"grad_norm": 0.6107614636421204,
|
| 573 |
"learning_rate": 0.0005,
|
| 574 |
-
"loss": 0.
|
| 575 |
"step": 3800
|
| 576 |
},
|
| 577 |
{
|
| 578 |
"epoch": 20.8,
|
| 579 |
-
"grad_norm": 0.5394221544265747,
|
| 580 |
"learning_rate": 0.0005,
|
| 581 |
-
"loss": 0.
|
| 582 |
"step": 3900
|
| 583 |
},
|
| 584 |
{
|
| 585 |
-
"epoch":
|
| 586 |
-
"eval_accuracy": 0.
|
| 587 |
-
"eval_loss":
|
| 588 |
-
"eval_runtime":
|
| 589 |
-
"eval_samples_per_second":
|
| 590 |
-
"eval_steps_per_second":
|
| 591 |
"step": 3937
|
| 592 |
},
|
| 593 |
{
|
| 594 |
-
"epoch":
|
| 595 |
-
"eval_exact_match":
|
| 596 |
-
"eval_f1":
|
| 597 |
"step": 3937
|
| 598 |
},
|
| 599 |
{
|
| 600 |
-
"epoch": 21.
|
| 601 |
-
"grad_norm": 0.35812634229660034,
|
| 602 |
"learning_rate": 0.0005,
|
| 603 |
-
"loss": 0.
|
| 604 |
"step": 4000
|
| 605 |
},
|
| 606 |
{
|
| 607 |
-
"epoch": 21.
|
| 608 |
-
"grad_norm": 0.4076957404613495,
|
| 609 |
"learning_rate": 0.0005,
|
| 610 |
-
"loss": 0.
|
| 611 |
"step": 4100
|
| 612 |
},
|
| 613 |
{
|
| 614 |
"epoch": 22.0,
|
| 615 |
-
"eval_accuracy": 0.
|
| 616 |
-
"eval_loss": 2.
|
| 617 |
-
"eval_runtime":
|
| 618 |
-
"eval_samples_per_second":
|
| 619 |
-
"eval_steps_per_second":
|
| 620 |
"step": 4125
|
| 621 |
},
|
| 622 |
{
|
| 623 |
"epoch": 22.0,
|
| 624 |
-
"eval_exact_match":
|
| 625 |
-
"eval_f1":
|
| 626 |
"step": 4125
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 22.4,
|
| 630 |
-
"grad_norm": 0.5148049592971802,
|
| 631 |
"learning_rate": 0.0005,
|
| 632 |
-
"loss": 0.
|
| 633 |
"step": 4200
|
| 634 |
},
|
| 635 |
{
|
| 636 |
-
"epoch": 22.
|
| 637 |
-
"grad_norm": 0.7316868305206299,
|
| 638 |
"learning_rate": 0.0005,
|
| 639 |
-
"loss": 0.
|
| 640 |
"step": 4300
|
| 641 |
},
|
| 642 |
{
|
| 643 |
-
"epoch":
|
| 644 |
-
"eval_accuracy": 0.
|
| 645 |
-
"eval_loss": 2.
|
| 646 |
-
"eval_runtime":
|
| 647 |
-
"eval_samples_per_second":
|
| 648 |
-
"eval_steps_per_second":
|
| 649 |
"step": 4312
|
| 650 |
},
|
| 651 |
{
|
| 652 |
-
"epoch":
|
| 653 |
-
"eval_exact_match":
|
| 654 |
-
"eval_f1":
|
| 655 |
"step": 4312
|
| 656 |
},
|
| 657 |
{
|
| 658 |
-
"epoch": 23.
|
| 659 |
-
"grad_norm": 0.7490749955177307,
|
| 660 |
"learning_rate": 0.0005,
|
| 661 |
-
"loss": 0.
|
| 662 |
"step": 4400
|
| 663 |
},
|
| 664 |
{
|
| 665 |
"epoch": 24.0,
|
| 666 |
-
"grad_norm": 0.7351626753807068,
|
| 667 |
"learning_rate": 0.0005,
|
| 668 |
-
"loss": 0.
|
| 669 |
"step": 4500
|
| 670 |
},
|
| 671 |
{
|
| 672 |
"epoch": 24.0,
|
| 673 |
-
"eval_accuracy": 0.
|
| 674 |
-
"eval_loss": 2.
|
| 675 |
-
"eval_runtime": 4.
|
| 676 |
-
"eval_samples_per_second":
|
| 677 |
-
"eval_steps_per_second":
|
| 678 |
"step": 4500
|
| 679 |
},
|
| 680 |
{
|
| 681 |
"epoch": 24.0,
|
| 682 |
-
"eval_exact_match":
|
| 683 |
-
"eval_f1":
|
| 684 |
"step": 4500
|
| 685 |
},
|
| 686 |
{
|
| 687 |
-
"epoch": 24.
|
| 688 |
-
"grad_norm": 0.5879587531089783,
|
| 689 |
"learning_rate": 0.0005,
|
| 690 |
-
"loss": 0.
|
| 691 |
"step": 4600
|
| 692 |
},
|
| 693 |
{
|
| 694 |
-
"epoch":
|
| 695 |
-
"eval_accuracy": 0.
|
| 696 |
-
"eval_loss": 2.
|
| 697 |
-
"eval_runtime":
|
| 698 |
-
"eval_samples_per_second":
|
| 699 |
-
"eval_steps_per_second":
|
| 700 |
"step": 4687
|
| 701 |
},
|
| 702 |
{
|
| 703 |
-
"epoch":
|
| 704 |
-
"eval_exact_match":
|
| 705 |
-
"eval_f1":
|
| 706 |
"step": 4687
|
| 707 |
},
|
| 708 |
{
|
| 709 |
-
"epoch": 25.
|
| 710 |
-
"grad_norm": 0.61104816198349,
|
| 711 |
"learning_rate": 0.0005,
|
| 712 |
-
"loss": 0.
|
| 713 |
"step": 4700
|
| 714 |
},
|
| 715 |
{
|
| 716 |
"epoch": 25.6,
|
| 717 |
-
"grad_norm": 1.318751335144043,
|
| 718 |
"learning_rate": 0.0005,
|
| 719 |
-
"loss": 0.
|
| 720 |
"step": 4800
|
| 721 |
},
|
| 722 |
{
|
| 723 |
"epoch": 26.0,
|
| 724 |
-
"eval_accuracy": 0.
|
| 725 |
-
"eval_loss": 2.
|
| 726 |
-
"eval_runtime":
|
| 727 |
-
"eval_samples_per_second":
|
| 728 |
-
"eval_steps_per_second":
|
| 729 |
"step": 4875
|
| 730 |
},
|
| 731 |
{
|
| 732 |
"epoch": 26.0,
|
| 733 |
-
"eval_exact_match":
|
| 734 |
-
"eval_f1":
|
| 735 |
"step": 4875
|
| 736 |
},
|
| 737 |
{
|
| 738 |
-
"epoch": 26.
|
| 739 |
-
"grad_norm": 0.8964791893959045,
|
| 740 |
"learning_rate": 0.0005,
|
| 741 |
-
"loss": 0.
|
| 742 |
"step": 4900
|
| 743 |
},
|
| 744 |
{
|
| 745 |
-
"epoch": 26.
|
| 746 |
-
"grad_norm": 0.6350087523460388,
|
| 747 |
"learning_rate": 0.0005,
|
| 748 |
-
"loss": 0.
|
| 749 |
"step": 5000
|
| 750 |
},
|
| 751 |
{
|
| 752 |
-
"epoch":
|
| 753 |
-
"eval_accuracy": 0.
|
| 754 |
-
"eval_loss": 2.
|
| 755 |
-
"eval_runtime":
|
| 756 |
-
"eval_samples_per_second":
|
| 757 |
-
"eval_steps_per_second":
|
| 758 |
"step": 5062
|
| 759 |
},
|
| 760 |
{
|
| 761 |
-
"epoch":
|
| 762 |
-
"eval_exact_match":
|
| 763 |
-
"eval_f1":
|
| 764 |
"step": 5062
|
| 765 |
},
|
| 766 |
{
|
| 767 |
"epoch": 27.2,
|
| 768 |
-
"grad_norm": 0.47840726375579834,
|
| 769 |
"learning_rate": 0.0005,
|
| 770 |
-
"loss": 0.
|
| 771 |
"step": 5100
|
| 772 |
},
|
| 773 |
{
|
| 774 |
-
"epoch": 27.
|
| 775 |
-
"grad_norm": 0.474448561668396,
|
| 776 |
"learning_rate": 0.0005,
|
| 777 |
-
"loss": 0.
|
| 778 |
"step": 5200
|
| 779 |
},
|
| 780 |
{
|
| 781 |
"epoch": 28.0,
|
| 782 |
-
"eval_accuracy": 0.
|
| 783 |
-
"eval_loss": 2.
|
| 784 |
-
"eval_runtime":
|
| 785 |
-
"eval_samples_per_second":
|
| 786 |
-
"eval_steps_per_second":
|
| 787 |
"step": 5250
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 28.0,
|
| 791 |
-
"eval_exact_match":
|
| 792 |
-
"eval_f1":
|
| 793 |
"step": 5250
|
| 794 |
},
|
| 795 |
{
|
| 796 |
-
"epoch": 28.
|
| 797 |
-
"grad_norm": 0.4811856150627136,
|
| 798 |
"learning_rate": 0.0005,
|
| 799 |
-
"loss": 0.
|
| 800 |
"step": 5300
|
| 801 |
},
|
| 802 |
{
|
| 803 |
"epoch": 28.8,
|
| 804 |
-
"grad_norm": 0.7236740589141846,
|
| 805 |
"learning_rate": 0.0005,
|
| 806 |
-
"loss": 0.
|
| 807 |
"step": 5400
|
| 808 |
},
|
| 809 |
{
|
| 810 |
-
"epoch":
|
| 811 |
-
"eval_accuracy": 0.
|
| 812 |
-
"eval_loss": 2.
|
| 813 |
-
"eval_runtime":
|
| 814 |
-
"eval_samples_per_second":
|
| 815 |
-
"eval_steps_per_second":
|
| 816 |
"step": 5437
|
| 817 |
},
|
| 818 |
{
|
| 819 |
-
"epoch":
|
| 820 |
-
"eval_exact_match":
|
| 821 |
-
"eval_f1":
|
| 822 |
"step": 5437
|
| 823 |
},
|
| 824 |
{
|
| 825 |
-
"epoch": 29.
|
| 826 |
-
"grad_norm": 0.6178373098373413,
|
| 827 |
"learning_rate": 0.0005,
|
| 828 |
-
"loss": 0.
|
| 829 |
"step": 5500
|
| 830 |
},
|
| 831 |
{
|
| 832 |
-
"epoch": 29.
|
| 833 |
-
"grad_norm": 0.6287767887115479,
|
| 834 |
"learning_rate": 0.0005,
|
| 835 |
-
"loss": 0.
|
| 836 |
"step": 5600
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 30.0,
|
| 840 |
-
"eval_accuracy": 0.
|
| 841 |
-
"eval_loss": 2.
|
| 842 |
-
"eval_runtime":
|
| 843 |
-
"eval_samples_per_second":
|
| 844 |
-
"eval_steps_per_second":
|
| 845 |
"step": 5625
|
| 846 |
},
|
| 847 |
{
|
| 848 |
"epoch": 30.0,
|
| 849 |
-
"eval_exact_match":
|
| 850 |
-
"eval_f1":
|
| 851 |
"step": 5625
|
| 852 |
},
|
| 853 |
{
|
| 854 |
"epoch": 30.4,
|
| 855 |
-
"grad_norm": 0.45170456171035767,
|
| 856 |
"learning_rate": 0.0005,
|
| 857 |
-
"loss": 0.
|
| 858 |
"step": 5700
|
| 859 |
},
|
| 860 |
{
|
| 861 |
-
"epoch": 30.
|
| 862 |
-
"grad_norm": 0.36589592695236206,
|
| 863 |
"learning_rate": 0.0005,
|
| 864 |
-
"loss": 0.
|
| 865 |
"step": 5800
|
| 866 |
},
|
| 867 |
{
|
| 868 |
-
"epoch":
|
| 869 |
-
"eval_accuracy": 0.
|
| 870 |
-
"eval_loss": 2.
|
| 871 |
-
"eval_runtime":
|
| 872 |
-
"eval_samples_per_second":
|
| 873 |
-
"eval_steps_per_second":
|
| 874 |
"step": 5812
|
| 875 |
},
|
| 876 |
{
|
| 877 |
-
"epoch":
|
| 878 |
-
"eval_exact_match":
|
| 879 |
-
"eval_f1":
|
| 880 |
"step": 5812
|
| 881 |
},
|
| 882 |
{
|
| 883 |
-
"epoch": 31.
|
| 884 |
-
"grad_norm": 0.4986824095249176,
|
| 885 |
"learning_rate": 0.0005,
|
| 886 |
-
"loss": 0.
|
| 887 |
"step": 5900
|
| 888 |
},
|
| 889 |
{
|
| 890 |
"epoch": 32.0,
|
| 891 |
-
"grad_norm": 0.5775201320648193,
|
| 892 |
"learning_rate": 0.0005,
|
| 893 |
-
"loss": 0.
|
| 894 |
"step": 6000
|
| 895 |
},
|
| 896 |
{
|
| 897 |
"epoch": 32.0,
|
| 898 |
-
"eval_accuracy": 0.
|
| 899 |
-
"eval_loss": 2.
|
| 900 |
-
"eval_runtime":
|
| 901 |
-
"eval_samples_per_second":
|
| 902 |
-
"eval_steps_per_second":
|
| 903 |
"step": 6000
|
| 904 |
},
|
| 905 |
{
|
| 906 |
"epoch": 32.0,
|
| 907 |
-
"eval_exact_match":
|
| 908 |
-
"eval_f1":
|
| 909 |
"step": 6000
|
| 910 |
},
|
| 911 |
{
|
| 912 |
-
"epoch": 32.
|
| 913 |
-
"grad_norm": 0.8057941794395447,
|
| 914 |
"learning_rate": 0.0005,
|
| 915 |
-
"loss": 0.
|
| 916 |
"step": 6100
|
| 917 |
},
|
| 918 |
{
|
| 919 |
-
"epoch":
|
| 920 |
-
"eval_accuracy": 0.
|
| 921 |
-
"eval_loss": 2.
|
| 922 |
-
"eval_runtime":
|
| 923 |
-
"eval_samples_per_second":
|
| 924 |
-
"eval_steps_per_second":
|
| 925 |
"step": 6187
|
| 926 |
},
|
| 927 |
{
|
| 928 |
-
"epoch":
|
| 929 |
-
"eval_exact_match":
|
| 930 |
-
"eval_f1":
|
| 931 |
"step": 6187
|
| 932 |
},
|
| 933 |
{
|
| 934 |
-
"epoch": 33.
|
| 935 |
-
"grad_norm": 0.5468693375587463,
|
| 936 |
"learning_rate": 0.0005,
|
| 937 |
-
"loss": 0.
|
| 938 |
"step": 6200
|
| 939 |
},
|
| 940 |
{
|
| 941 |
"epoch": 33.6,
|
| 942 |
-
"grad_norm": 0.4891034960746765,
|
| 943 |
"learning_rate": 0.0005,
|
| 944 |
-
"loss": 0.
|
| 945 |
"step": 6300
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 34.0,
|
| 949 |
-
"eval_accuracy": 0.
|
| 950 |
-
"eval_loss": 2.
|
| 951 |
-
"eval_runtime":
|
| 952 |
-
"eval_samples_per_second":
|
| 953 |
-
"eval_steps_per_second":
|
| 954 |
"step": 6375
|
| 955 |
},
|
| 956 |
{
|
| 957 |
"epoch": 34.0,
|
| 958 |
-
"eval_exact_match":
|
| 959 |
-
"eval_f1":
|
| 960 |
"step": 6375
|
| 961 |
},
|
| 962 |
{
|
| 963 |
-
"epoch": 34.
|
| 964 |
-
"grad_norm": 0.9730343818664551,
|
| 965 |
"learning_rate": 0.0005,
|
| 966 |
-
"loss": 0.
|
| 967 |
"step": 6400
|
| 968 |
},
|
| 969 |
{
|
| 970 |
-
"epoch": 34.
|
| 971 |
-
"grad_norm": 0.8066098093986511,
|
| 972 |
"learning_rate": 0.0005,
|
| 973 |
-
"loss": 0.
|
| 974 |
"step": 6500
|
| 975 |
},
|
| 976 |
{
|
| 977 |
-
"epoch":
|
| 978 |
-
"eval_accuracy": 0.
|
| 979 |
-
"eval_loss": 2.
|
| 980 |
-
"eval_runtime":
|
| 981 |
-
"eval_samples_per_second":
|
| 982 |
-
"eval_steps_per_second":
|
| 983 |
"step": 6562
|
| 984 |
},
|
| 985 |
{
|
| 986 |
-
"epoch":
|
| 987 |
-
"eval_exact_match":
|
| 988 |
-
"eval_f1":
|
| 989 |
"step": 6562
|
| 990 |
},
|
| 991 |
{
|
| 992 |
"epoch": 35.2,
|
| 993 |
-
"grad_norm": 1.1951669454574585,
|
| 994 |
"learning_rate": 0.0005,
|
| 995 |
-
"loss": 0.
|
| 996 |
"step": 6600
|
| 997 |
},
|
| 998 |
{
|
| 999 |
-
"epoch": 35.
|
| 1000 |
-
"grad_norm": 0.7211179137229919,
|
| 1001 |
"learning_rate": 0.0005,
|
| 1002 |
-
"loss": 0.
|
| 1003 |
"step": 6700
|
| 1004 |
},
|
| 1005 |
{
|
| 1006 |
"epoch": 36.0,
|
| 1007 |
-
"eval_accuracy": 0.
|
| 1008 |
-
"eval_loss": 2.
|
| 1009 |
-
"eval_runtime":
|
| 1010 |
-
"eval_samples_per_second":
|
| 1011 |
-
"eval_steps_per_second": 12.
|
| 1012 |
"step": 6750
|
| 1013 |
},
|
| 1014 |
{
|
| 1015 |
"epoch": 36.0,
|
| 1016 |
-
"eval_exact_match":
|
| 1017 |
-
"eval_f1":
|
| 1018 |
"step": 6750
|
| 1019 |
},
|
| 1020 |
{
|
| 1021 |
-
"epoch": 36.
|
| 1022 |
-
"grad_norm": 0.4955157935619354,
|
| 1023 |
"learning_rate": 0.0005,
|
| 1024 |
-
"loss": 0.
|
| 1025 |
"step": 6800
|
| 1026 |
},
|
| 1027 |
{
|
| 1028 |
"epoch": 36.8,
|
| 1029 |
-
"grad_norm": 0.6588331460952759,
|
| 1030 |
"learning_rate": 0.0005,
|
| 1031 |
-
"loss": 0.
|
| 1032 |
"step": 6900
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
-
"epoch":
|
| 1036 |
-
"eval_accuracy": 0.
|
| 1037 |
-
"eval_loss": 2.
|
| 1038 |
-
"eval_runtime":
|
| 1039 |
-
"eval_samples_per_second":
|
| 1040 |
-
"eval_steps_per_second":
|
| 1041 |
"step": 6937
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
-
"epoch":
|
| 1045 |
-
"eval_exact_match": 11.
|
| 1046 |
-
"eval_f1":
|
| 1047 |
"step": 6937
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
-
"epoch": 37.
|
| 1051 |
-
"grad_norm": 0.5928548574447632,
|
| 1052 |
"learning_rate": 0.0005,
|
| 1053 |
-
"loss": 0.
|
| 1054 |
"step": 7000
|
| 1055 |
},
|
| 1056 |
{
|
| 1057 |
-
"epoch": 37.
|
| 1058 |
-
"grad_norm": 0.5979794263839722,
|
| 1059 |
"learning_rate": 0.0005,
|
| 1060 |
-
"loss": 0.
|
| 1061 |
"step": 7100
|
| 1062 |
},
|
| 1063 |
{
|
| 1064 |
"epoch": 38.0,
|
| 1065 |
-
"eval_accuracy": 0.
|
| 1066 |
-
"eval_loss": 2.
|
| 1067 |
-
"eval_runtime":
|
| 1068 |
-
"eval_samples_per_second":
|
| 1069 |
-
"eval_steps_per_second":
|
| 1070 |
"step": 7125
|
| 1071 |
},
|
| 1072 |
{
|
| 1073 |
"epoch": 38.0,
|
| 1074 |
-
"eval_exact_match":
|
| 1075 |
-
"eval_f1":
|
| 1076 |
"step": 7125
|
| 1077 |
},
|
| 1078 |
{
|
| 1079 |
"epoch": 38.4,
|
| 1080 |
-
"grad_norm": 0.6051629185676575,
|
| 1081 |
"learning_rate": 0.0005,
|
| 1082 |
-
"loss": 0.
|
| 1083 |
"step": 7200
|
| 1084 |
},
|
| 1085 |
{
|
| 1086 |
-
"epoch": 38.
|
| 1087 |
-
"grad_norm": 0.7862063646316528,
|
| 1088 |
"learning_rate": 0.0005,
|
| 1089 |
-
"loss": 0.
|
| 1090 |
"step": 7300
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
-
"epoch":
|
| 1094 |
-
"eval_accuracy": 0.
|
| 1095 |
-
"eval_loss": 2.
|
| 1096 |
-
"eval_runtime":
|
| 1097 |
-
"eval_samples_per_second":
|
| 1098 |
-
"eval_steps_per_second":
|
| 1099 |
"step": 7312
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
-
"epoch":
|
| 1103 |
-
"eval_exact_match":
|
| 1104 |
-
"eval_f1":
|
| 1105 |
"step": 7312
|
| 1106 |
},
|
| 1107 |
{
|
| 1108 |
-
"epoch": 39.
|
| 1109 |
-
"grad_norm": 0.5463705658912659,
|
| 1110 |
"learning_rate": 0.0005,
|
| 1111 |
-
"loss": 0.
|
| 1112 |
"step": 7400
|
| 1113 |
},
|
| 1114 |
{
|
| 1115 |
"epoch": 40.0,
|
| 1116 |
-
"grad_norm": 0.6618899703025818,
|
| 1117 |
"learning_rate": 0.0005,
|
| 1118 |
-
"loss": 0.
|
| 1119 |
"step": 7500
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
"epoch": 40.0,
|
| 1123 |
-
"eval_accuracy": 0.
|
| 1124 |
-
"eval_loss": 2.
|
| 1125 |
-
"eval_runtime":
|
| 1126 |
-
"eval_samples_per_second":
|
| 1127 |
-
"eval_steps_per_second":
|
| 1128 |
"step": 7500
|
| 1129 |
},
|
| 1130 |
{
|
| 1131 |
"epoch": 40.0,
|
| 1132 |
-
"eval_exact_match":
|
| 1133 |
-
"eval_f1":
|
| 1134 |
"step": 7500
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
-
"epoch": 40.
|
| 1138 |
-
"grad_norm": 0.8436341285705566,
|
| 1139 |
"learning_rate": 0.0005,
|
| 1140 |
-
"loss": 0.
|
| 1141 |
"step": 7600
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
-
"epoch":
|
| 1145 |
-
"eval_accuracy": 0.
|
| 1146 |
-
"eval_loss": 2.
|
| 1147 |
-
"eval_runtime":
|
| 1148 |
-
"eval_samples_per_second":
|
| 1149 |
-
"eval_steps_per_second":
|
| 1150 |
"step": 7687
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
-
"epoch":
|
| 1154 |
-
"eval_exact_match":
|
| 1155 |
-
"eval_f1":
|
| 1156 |
"step": 7687
|
| 1157 |
},
|
| 1158 |
{
|
| 1159 |
-
"epoch": 41.
|
| 1160 |
-
"grad_norm": 0.5301070809364319,
|
| 1161 |
"learning_rate": 0.0005,
|
| 1162 |
-
"loss": 0.
|
| 1163 |
"step": 7700
|
| 1164 |
},
|
| 1165 |
{
|
| 1166 |
"epoch": 41.6,
|
| 1167 |
-
"grad_norm": 0.503410816192627,
|
| 1168 |
"learning_rate": 0.0005,
|
| 1169 |
-
"loss": 0.
|
| 1170 |
"step": 7800
|
| 1171 |
},
|
| 1172 |
{
|
| 1173 |
"epoch": 42.0,
|
| 1174 |
-
"eval_accuracy": 0.
|
| 1175 |
-
"eval_loss": 2.
|
| 1176 |
-
"eval_runtime": 4.
|
| 1177 |
-
"eval_samples_per_second":
|
| 1178 |
-
"eval_steps_per_second":
|
| 1179 |
"step": 7875
|
| 1180 |
},
|
| 1181 |
{
|
| 1182 |
"epoch": 42.0,
|
| 1183 |
"eval_exact_match": 12.2,
|
| 1184 |
-
"eval_f1":
|
| 1185 |
"step": 7875
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
-
"epoch": 42.
|
| 1189 |
-
"grad_norm": 0.5958962440490723,
|
| 1190 |
"learning_rate": 0.0005,
|
| 1191 |
-
"loss": 0.
|
| 1192 |
"step": 7900
|
| 1193 |
},
|
| 1194 |
{
|
| 1195 |
-
"epoch": 42.
|
| 1196 |
-
"grad_norm": 0.345262736082077,
|
| 1197 |
"learning_rate": 0.0005,
|
| 1198 |
-
"loss": 0.
|
| 1199 |
"step": 8000
|
| 1200 |
},
|
| 1201 |
{
|
| 1202 |
-
"epoch":
|
| 1203 |
-
"eval_accuracy": 0.
|
| 1204 |
-
"eval_loss": 2.
|
| 1205 |
-
"eval_runtime":
|
| 1206 |
-
"eval_samples_per_second":
|
| 1207 |
-
"eval_steps_per_second":
|
| 1208 |
"step": 8062
|
| 1209 |
},
|
| 1210 |
{
|
| 1211 |
-
"epoch":
|
| 1212 |
-
"eval_exact_match":
|
| 1213 |
-
"eval_f1":
|
| 1214 |
"step": 8062
|
| 1215 |
},
|
| 1216 |
{
|
| 1217 |
"epoch": 43.2,
|
| 1218 |
-
"grad_norm": 0.9052207469940186,
|
| 1219 |
"learning_rate": 0.0005,
|
| 1220 |
-
"loss": 0.
|
| 1221 |
"step": 8100
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
-
"epoch": 43.
|
| 1225 |
-
"grad_norm": 0.6936642527580261,
|
| 1226 |
"learning_rate": 0.0005,
|
| 1227 |
-
"loss": 0.
|
| 1228 |
"step": 8200
|
| 1229 |
},
|
| 1230 |
{
|
| 1231 |
"epoch": 44.0,
|
| 1232 |
-
"eval_accuracy": 0.
|
| 1233 |
-
"eval_loss": 2.
|
| 1234 |
-
"eval_runtime":
|
| 1235 |
-
"eval_samples_per_second":
|
| 1236 |
-
"eval_steps_per_second":
|
| 1237 |
"step": 8250
|
| 1238 |
},
|
| 1239 |
{
|
| 1240 |
"epoch": 44.0,
|
| 1241 |
-
"eval_exact_match":
|
| 1242 |
-
"eval_f1":
|
| 1243 |
"step": 8250
|
| 1244 |
},
|
| 1245 |
{
|
| 1246 |
-
"epoch": 44.
|
| 1247 |
-
"grad_norm": 0.7840509414672852,
|
| 1248 |
"learning_rate": 0.0005,
|
| 1249 |
-
"loss": 0.
|
| 1250 |
"step": 8300
|
| 1251 |
},
|
| 1252 |
{
|
| 1253 |
"epoch": 44.8,
|
| 1254 |
-
"grad_norm": 0.7178289294242859,
|
| 1255 |
"learning_rate": 0.0005,
|
| 1256 |
-
"loss": 0.
|
| 1257 |
"step": 8400
|
| 1258 |
},
|
| 1259 |
{
|
| 1260 |
-
"epoch":
|
| 1261 |
-
"eval_accuracy": 0.
|
| 1262 |
-
"eval_loss": 2.
|
| 1263 |
-
"eval_runtime":
|
| 1264 |
-
"eval_samples_per_second":
|
| 1265 |
-
"eval_steps_per_second":
|
| 1266 |
"step": 8437
|
| 1267 |
},
|
| 1268 |
{
|
| 1269 |
-
"epoch":
|
| 1270 |
-
"eval_exact_match":
|
| 1271 |
-
"eval_f1":
|
| 1272 |
"step": 8437
|
| 1273 |
},
|
| 1274 |
{
|
| 1275 |
-
"epoch": 45.
|
| 1276 |
-
"grad_norm": 0.5202128291130066,
|
| 1277 |
"learning_rate": 0.0005,
|
| 1278 |
-
"loss": 0.
|
| 1279 |
"step": 8500
|
| 1280 |
},
|
| 1281 |
{
|
| 1282 |
-
"epoch": 45.
|
| 1283 |
-
"grad_norm": 0.7298985719680786,
|
| 1284 |
"learning_rate": 0.0005,
|
| 1285 |
-
"loss": 0.
|
| 1286 |
"step": 8600
|
| 1287 |
},
|
| 1288 |
{
|
| 1289 |
"epoch": 46.0,
|
| 1290 |
-
"eval_accuracy": 0.
|
| 1291 |
-
"eval_loss": 2.
|
| 1292 |
-
"eval_runtime": 4.
|
| 1293 |
-
"eval_samples_per_second":
|
| 1294 |
-
"eval_steps_per_second":
|
| 1295 |
"step": 8625
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 46.0,
|
| 1299 |
-
"eval_exact_match":
|
| 1300 |
-
"eval_f1":
|
| 1301 |
"step": 8625
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
"epoch": 46.4,
|
| 1305 |
-
"grad_norm": 0.5158805847167969,
|
| 1306 |
"learning_rate": 0.0005,
|
| 1307 |
-
"loss": 0.
|
| 1308 |
"step": 8700
|
| 1309 |
},
|
| 1310 |
{
|
| 1311 |
-
"epoch": 46.
|
| 1312 |
-
"grad_norm": 0.7611350417137146,
|
| 1313 |
"learning_rate": 0.0005,
|
| 1314 |
-
"loss":
|
| 1315 |
"step": 8800
|
| 1316 |
},
|
| 1317 |
{
|
| 1318 |
-
"epoch":
|
| 1319 |
-
"eval_accuracy": 0.
|
| 1320 |
-
"eval_loss": 2.
|
| 1321 |
-
"eval_runtime": 4.
|
| 1322 |
-
"eval_samples_per_second":
|
| 1323 |
-
"eval_steps_per_second":
|
| 1324 |
"step": 8812
|
| 1325 |
},
|
| 1326 |
{
|
| 1327 |
-
"epoch":
|
| 1328 |
-
"eval_exact_match":
|
| 1329 |
-
"eval_f1":
|
| 1330 |
"step": 8812
|
| 1331 |
}
|
| 1332 |
],
|
| 1333 |
"logging_steps": 100,
|
| 1334 |
"max_steps": 9350,
|
| 1335 |
-
"num_input_tokens_seen": 0,
|
| 1336 |
"num_train_epochs": 50,
|
| 1337 |
"save_steps": 500,
|
| 1338 |
-
"
|
| 1339 |
-
"TrainerControl": {
|
| 1340 |
-
"args": {
|
| 1341 |
-
"should_epoch_stop": false,
|
| 1342 |
-
"should_evaluate": false,
|
| 1343 |
-
"should_log": false,
|
| 1344 |
-
"should_save": true,
|
| 1345 |
-
"should_training_stop": false
|
| 1346 |
-
},
|
| 1347 |
-
"attributes": {}
|
| 1348 |
-
}
|
| 1349 |
-
},
|
| 1350 |
-
"total_flos": 1.5347672233384346e+17,
|
| 1351 |
-
"train_batch_size": 1,
|
| 1352 |
"trial_name": null,
|
| 1353 |
"trial_params": null
|
| 1354 |
}
|
|
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.53,
|
|
|
|
| 13 |
"learning_rate": 0.0005,
|
| 14 |
+
"loss": 1.43,
|
| 15 |
"step": 100
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 1.0,
|
| 19 |
+
"eval_accuracy": 0.6161538461538462,
|
| 20 |
+
"eval_loss": 1.2682808637619019,
|
| 21 |
+
"eval_runtime": 4.85,
|
| 22 |
+
"eval_samples_per_second": 103.093,
|
| 23 |
+
"eval_steps_per_second": 12.99,
|
| 24 |
"step": 187
|
| 25 |
},
|
| 26 |
{
|
| 27 |
+
"epoch": 1.0,
|
| 28 |
+
"eval_exact_match": 26.6,
|
| 29 |
+
"eval_f1": 38.8657142857143,
|
| 30 |
"step": 187
|
| 31 |
},
|
| 32 |
{
|
| 33 |
+
"epoch": 1.07,
|
|
|
|
| 34 |
"learning_rate": 0.0005,
|
| 35 |
+
"loss": 1.2637,
|
| 36 |
"step": 200
|
| 37 |
},
|
| 38 |
{
|
| 39 |
"epoch": 1.6,
|
|
|
|
| 40 |
"learning_rate": 0.0005,
|
| 41 |
+
"loss": 1.0285,
|
| 42 |
"step": 300
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 2.0,
|
| 46 |
+
"eval_accuracy": 0.6129230769230769,
|
| 47 |
+
"eval_loss": 1.3220478296279907,
|
| 48 |
+
"eval_runtime": 4.4227,
|
| 49 |
+
"eval_samples_per_second": 113.052,
|
| 50 |
+
"eval_steps_per_second": 14.245,
|
| 51 |
"step": 375
|
| 52 |
},
|
| 53 |
{
|
| 54 |
"epoch": 2.0,
|
| 55 |
+
"eval_exact_match": 24.2,
|
| 56 |
+
"eval_f1": 37.12603174603175,
|
| 57 |
"step": 375
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 2.13,
|
|
|
|
| 61 |
"learning_rate": 0.0005,
|
| 62 |
+
"loss": 0.9478,
|
| 63 |
"step": 400
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 2.67,
|
|
|
|
| 67 |
"learning_rate": 0.0005,
|
| 68 |
+
"loss": 0.7318,
|
| 69 |
"step": 500
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 3.0,
|
| 73 |
+
"eval_accuracy": 0.6075897435897436,
|
| 74 |
+
"eval_loss": 1.4644758701324463,
|
| 75 |
+
"eval_runtime": 4.8316,
|
| 76 |
+
"eval_samples_per_second": 103.486,
|
| 77 |
+
"eval_steps_per_second": 13.039,
|
| 78 |
"step": 562
|
| 79 |
},
|
| 80 |
{
|
| 81 |
+
"epoch": 3.0,
|
| 82 |
+
"eval_exact_match": 22.8,
|
| 83 |
+
"eval_f1": 36.51031746031747,
|
| 84 |
"step": 562
|
| 85 |
},
|
| 86 |
{
|
| 87 |
"epoch": 3.2,
|
|
|
|
| 88 |
"learning_rate": 0.0005,
|
| 89 |
+
"loss": 0.6922,
|
| 90 |
"step": 600
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"epoch": 3.73,
|
|
|
|
| 94 |
"learning_rate": 0.0005,
|
| 95 |
+
"loss": 0.5898,
|
| 96 |
"step": 700
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 4.0,
|
| 100 |
+
"eval_accuracy": 0.604974358974359,
|
| 101 |
+
"eval_loss": 1.54537832736969,
|
| 102 |
+
"eval_runtime": 4.119,
|
| 103 |
+
"eval_samples_per_second": 121.388,
|
| 104 |
+
"eval_steps_per_second": 15.295,
|
| 105 |
"step": 750
|
| 106 |
},
|
| 107 |
{
|
| 108 |
"epoch": 4.0,
|
| 109 |
+
"eval_exact_match": 15.4,
|
| 110 |
+
"eval_f1": 25.034444444444457,
|
| 111 |
"step": 750
|
| 112 |
},
|
| 113 |
{
|
| 114 |
+
"epoch": 4.27,
|
|
|
|
| 115 |
"learning_rate": 0.0005,
|
| 116 |
+
"loss": 0.5599,
|
| 117 |
"step": 800
|
| 118 |
},
|
| 119 |
{
|
| 120 |
"epoch": 4.8,
|
|
|
|
| 121 |
"learning_rate": 0.0005,
|
| 122 |
+
"loss": 0.5309,
|
| 123 |
"step": 900
|
| 124 |
},
|
| 125 |
{
|
| 126 |
+
"epoch": 5.0,
|
| 127 |
+
"eval_accuracy": 0.6025641025641025,
|
| 128 |
+
"eval_loss": 1.6439025402069092,
|
| 129 |
+
"eval_runtime": 4.3353,
|
| 130 |
+
"eval_samples_per_second": 115.332,
|
| 131 |
+
"eval_steps_per_second": 14.532,
|
| 132 |
"step": 937
|
| 133 |
},
|
| 134 |
{
|
| 135 |
+
"epoch": 5.0,
|
| 136 |
+
"eval_exact_match": 21.6,
|
| 137 |
+
"eval_f1": 34.31112554112555,
|
| 138 |
"step": 937
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 5.33,
|
|
|
|
| 142 |
"learning_rate": 0.0005,
|
| 143 |
+
"loss": 0.5011,
|
| 144 |
"step": 1000
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 5.87,
|
|
|
|
| 148 |
"learning_rate": 0.0005,
|
| 149 |
+
"loss": 0.4985,
|
| 150 |
"step": 1100
|
| 151 |
},
|
| 152 |
{
|
| 153 |
"epoch": 6.0,
|
| 154 |
+
"eval_accuracy": 0.6034358974358974,
|
| 155 |
+
"eval_loss": 1.722017526626587,
|
| 156 |
+
"eval_runtime": 4.2182,
|
| 157 |
+
"eval_samples_per_second": 118.533,
|
| 158 |
+
"eval_steps_per_second": 14.935,
|
| 159 |
"step": 1125
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 6.0,
|
| 163 |
+
"eval_exact_match": 22.4,
|
| 164 |
+
"eval_f1": 34.31126984126985,
|
| 165 |
"step": 1125
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 6.4,
|
|
|
|
| 169 |
"learning_rate": 0.0005,
|
| 170 |
+
"loss": 0.4686,
|
| 171 |
"step": 1200
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 6.93,
|
|
|
|
| 175 |
"learning_rate": 0.0005,
|
| 176 |
+
"loss": 0.5091,
|
| 177 |
"step": 1300
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 7.0,
|
| 181 |
+
"eval_accuracy": 0.6008205128205129,
|
| 182 |
+
"eval_loss": 1.800759196281433,
|
| 183 |
+
"eval_runtime": 4.8504,
|
| 184 |
+
"eval_samples_per_second": 103.083,
|
| 185 |
+
"eval_steps_per_second": 12.989,
|
| 186 |
"step": 1312
|
| 187 |
},
|
| 188 |
{
|
| 189 |
+
"epoch": 7.0,
|
| 190 |
+
"eval_exact_match": 0.2,
|
| 191 |
+
"eval_f1": 2.1497326649958226,
|
| 192 |
"step": 1312
|
| 193 |
},
|
| 194 |
{
|
| 195 |
+
"epoch": 7.47,
|
|
|
|
| 196 |
"learning_rate": 0.0005,
|
| 197 |
+
"loss": 0.4576,
|
| 198 |
"step": 1400
|
| 199 |
},
|
| 200 |
{
|
| 201 |
"epoch": 8.0,
|
|
|
|
| 202 |
"learning_rate": 0.0005,
|
| 203 |
+
"loss": 0.4796,
|
| 204 |
"step": 1500
|
| 205 |
},
|
| 206 |
{
|
| 207 |
"epoch": 8.0,
|
| 208 |
+
"eval_accuracy": 0.6001025641025641,
|
| 209 |
+
"eval_loss": 1.7781891822814941,
|
| 210 |
+
"eval_runtime": 4.4147,
|
| 211 |
+
"eval_samples_per_second": 113.257,
|
| 212 |
+
"eval_steps_per_second": 14.27,
|
| 213 |
"step": 1500
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 8.0,
|
| 217 |
+
"eval_exact_match": 19.2,
|
| 218 |
+
"eval_f1": 29.972380952380963,
|
| 219 |
"step": 1500
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 8.53,
|
|
|
|
| 223 |
"learning_rate": 0.0005,
|
| 224 |
+
"loss": 0.4453,
|
| 225 |
"step": 1600
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 9.0,
|
| 229 |
+
"eval_accuracy": 0.5984615384615385,
|
| 230 |
+
"eval_loss": 1.8255126476287842,
|
| 231 |
+
"eval_runtime": 4.1057,
|
| 232 |
+
"eval_samples_per_second": 121.781,
|
| 233 |
+
"eval_steps_per_second": 15.344,
|
| 234 |
"step": 1687
|
| 235 |
},
|
| 236 |
{
|
| 237 |
+
"epoch": 9.0,
|
| 238 |
+
"eval_exact_match": 17.8,
|
| 239 |
+
"eval_f1": 29.10082251082252,
|
| 240 |
"step": 1687
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 9.07,
|
|
|
|
| 244 |
"learning_rate": 0.0005,
|
| 245 |
+
"loss": 0.4701,
|
| 246 |
"step": 1700
|
| 247 |
},
|
| 248 |
{
|
| 249 |
"epoch": 9.6,
|
|
|
|
| 250 |
"learning_rate": 0.0005,
|
| 251 |
+
"loss": 0.448,
|
| 252 |
"step": 1800
|
| 253 |
},
|
| 254 |
{
|
| 255 |
"epoch": 10.0,
|
| 256 |
+
"eval_accuracy": 0.5931282051282051,
|
| 257 |
+
"eval_loss": 1.7979023456573486,
|
| 258 |
+
"eval_runtime": 4.4695,
|
| 259 |
+
"eval_samples_per_second": 111.87,
|
| 260 |
+
"eval_steps_per_second": 14.096,
|
| 261 |
"step": 1875
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 10.0,
|
| 265 |
+
"eval_exact_match": 18.8,
|
| 266 |
+
"eval_f1": 28.28873015873017,
|
| 267 |
"step": 1875
|
| 268 |
},
|
| 269 |
{
|
| 270 |
+
"epoch": 10.13,
|
|
|
|
| 271 |
"learning_rate": 0.0005,
|
| 272 |
+
"loss": 0.4641,
|
| 273 |
"step": 1900
|
| 274 |
},
|
| 275 |
{
|
| 276 |
+
"epoch": 10.67,
|
|
|
|
| 277 |
"learning_rate": 0.0005,
|
| 278 |
+
"loss": 0.4522,
|
| 279 |
"step": 2000
|
| 280 |
},
|
| 281 |
{
|
| 282 |
+
"epoch": 11.0,
|
| 283 |
+
"eval_accuracy": 0.595948717948718,
|
| 284 |
+
"eval_loss": 1.8272360563278198,
|
| 285 |
+
"eval_runtime": 4.1203,
|
| 286 |
+
"eval_samples_per_second": 121.35,
|
| 287 |
+
"eval_steps_per_second": 15.29,
|
| 288 |
"step": 2062
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 11.0,
|
| 292 |
+
"eval_exact_match": 17.2,
|
| 293 |
+
"eval_f1": 28.030476190476207,
|
| 294 |
"step": 2062
|
| 295 |
},
|
| 296 |
{
|
| 297 |
"epoch": 11.2,
|
|
|
|
| 298 |
"learning_rate": 0.0005,
|
| 299 |
+
"loss": 0.4555,
|
| 300 |
"step": 2100
|
| 301 |
},
|
| 302 |
{
|
| 303 |
+
"epoch": 11.73,
|
|
|
|
| 304 |
"learning_rate": 0.0005,
|
| 305 |
+
"loss": 0.4552,
|
| 306 |
"step": 2200
|
| 307 |
},
|
| 308 |
{
|
| 309 |
"epoch": 12.0,
|
| 310 |
+
"eval_accuracy": 0.5946153846153847,
|
| 311 |
+
"eval_loss": 1.8670085668563843,
|
| 312 |
+
"eval_runtime": 4.2129,
|
| 313 |
+
"eval_samples_per_second": 118.684,
|
| 314 |
+
"eval_steps_per_second": 14.954,
|
| 315 |
"step": 2250
|
| 316 |
},
|
| 317 |
{
|
| 318 |
"epoch": 12.0,
|
| 319 |
+
"eval_exact_match": 17.8,
|
| 320 |
+
"eval_f1": 28.45285714285715,
|
| 321 |
"step": 2250
|
| 322 |
},
|
| 323 |
{
|
| 324 |
+
"epoch": 12.27,
|
|
|
|
| 325 |
"learning_rate": 0.0005,
|
| 326 |
+
"loss": 0.4492,
|
| 327 |
"step": 2300
|
| 328 |
},
|
| 329 |
{
|
| 330 |
"epoch": 12.8,
|
|
|
|
| 331 |
"learning_rate": 0.0005,
|
| 332 |
+
"loss": 0.4551,
|
| 333 |
"step": 2400
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 13.0,
|
| 337 |
+
"eval_accuracy": 0.595025641025641,
|
| 338 |
+
"eval_loss": 1.8706276416778564,
|
| 339 |
+
"eval_runtime": 4.2102,
|
| 340 |
+
"eval_samples_per_second": 118.759,
|
| 341 |
+
"eval_steps_per_second": 14.964,
|
| 342 |
"step": 2437
|
| 343 |
},
|
| 344 |
{
|
| 345 |
+
"epoch": 13.0,
|
| 346 |
+
"eval_exact_match": 19.0,
|
| 347 |
+
"eval_f1": 28.634603174603175,
|
| 348 |
"step": 2437
|
| 349 |
},
|
| 350 |
{
|
| 351 |
+
"epoch": 13.33,
|
|
|
|
| 352 |
"learning_rate": 0.0005,
|
| 353 |
+
"loss": 0.4505,
|
| 354 |
"step": 2500
|
| 355 |
},
|
| 356 |
{
|
| 357 |
+
"epoch": 13.87,
|
|
|
|
| 358 |
"learning_rate": 0.0005,
|
| 359 |
+
"loss": 0.4559,
|
| 360 |
"step": 2600
|
| 361 |
},
|
| 362 |
{
|
| 363 |
"epoch": 14.0,
|
| 364 |
+
"eval_accuracy": 0.5925128205128205,
|
| 365 |
+
"eval_loss": 1.8730883598327637,
|
| 366 |
+
"eval_runtime": 4.1209,
|
| 367 |
+
"eval_samples_per_second": 121.333,
|
| 368 |
+
"eval_steps_per_second": 15.288,
|
| 369 |
"step": 2625
|
| 370 |
},
|
| 371 |
{
|
| 372 |
"epoch": 14.0,
|
| 373 |
+
"eval_exact_match": 16.4,
|
| 374 |
+
"eval_f1": 25.989682539682548,
|
| 375 |
"step": 2625
|
| 376 |
},
|
| 377 |
{
|
| 378 |
"epoch": 14.4,
|
|
|
|
| 379 |
"learning_rate": 0.0005,
|
| 380 |
+
"loss": 0.4455,
|
| 381 |
"step": 2700
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 14.93,
|
|
|
|
| 385 |
"learning_rate": 0.0005,
|
| 386 |
+
"loss": 0.4581,
|
| 387 |
"step": 2800
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 15.0,
|
| 391 |
+
"eval_accuracy": 0.5932307692307692,
|
| 392 |
+
"eval_loss": 1.8531454801559448,
|
| 393 |
+
"eval_runtime": 4.4124,
|
| 394 |
+
"eval_samples_per_second": 113.316,
|
| 395 |
+
"eval_steps_per_second": 14.278,
|
| 396 |
"step": 2812
|
| 397 |
},
|
| 398 |
{
|
| 399 |
+
"epoch": 15.0,
|
| 400 |
+
"eval_exact_match": 17.8,
|
| 401 |
+
"eval_f1": 28.33587301587303,
|
| 402 |
"step": 2812
|
| 403 |
},
|
| 404 |
{
|
| 405 |
+
"epoch": 15.47,
|
|
|
|
| 406 |
"learning_rate": 0.0005,
|
| 407 |
+
"loss": 0.4358,
|
| 408 |
"step": 2900
|
| 409 |
},
|
| 410 |
{
|
| 411 |
"epoch": 16.0,
|
|
|
|
| 412 |
"learning_rate": 0.0005,
|
| 413 |
+
"loss": 0.4535,
|
| 414 |
"step": 3000
|
| 415 |
},
|
| 416 |
{
|
| 417 |
"epoch": 16.0,
|
| 418 |
+
"eval_accuracy": 0.5923076923076923,
|
| 419 |
+
"eval_loss": 1.949161410331726,
|
| 420 |
+
"eval_runtime": 4.8341,
|
| 421 |
+
"eval_samples_per_second": 103.433,
|
| 422 |
+
"eval_steps_per_second": 13.033,
|
| 423 |
"step": 3000
|
| 424 |
},
|
| 425 |
{
|
| 426 |
"epoch": 16.0,
|
| 427 |
+
"eval_exact_match": 17.4,
|
| 428 |
+
"eval_f1": 27.222698412698417,
|
| 429 |
"step": 3000
|
| 430 |
},
|
| 431 |
{
|
| 432 |
+
"epoch": 16.53,
|
|
|
|
| 433 |
"learning_rate": 0.0005,
|
| 434 |
+
"loss": 0.4308,
|
| 435 |
"step": 3100
|
| 436 |
},
|
| 437 |
{
|
| 438 |
+
"epoch": 17.0,
|
| 439 |
+
"eval_accuracy": 0.5915384615384616,
|
| 440 |
+
"eval_loss": 1.8943943977355957,
|
| 441 |
+
"eval_runtime": 4.2634,
|
| 442 |
+
"eval_samples_per_second": 117.279,
|
| 443 |
+
"eval_steps_per_second": 14.777,
|
| 444 |
"step": 3187
|
| 445 |
},
|
| 446 |
{
|
| 447 |
+
"epoch": 17.0,
|
| 448 |
+
"eval_exact_match": 17.4,
|
| 449 |
+
"eval_f1": 26.819047619047623,
|
| 450 |
"step": 3187
|
| 451 |
},
|
| 452 |
{
|
| 453 |
+
"epoch": 17.07,
|
|
|
|
| 454 |
"learning_rate": 0.0005,
|
| 455 |
+
"loss": 0.4467,
|
| 456 |
"step": 3200
|
| 457 |
},
|
| 458 |
{
|
| 459 |
"epoch": 17.6,
|
|
|
|
| 460 |
"learning_rate": 0.0005,
|
| 461 |
+
"loss": 0.4312,
|
| 462 |
"step": 3300
|
| 463 |
},
|
| 464 |
{
|
| 465 |
"epoch": 18.0,
|
| 466 |
+
"eval_accuracy": 0.5903589743589743,
|
| 467 |
+
"eval_loss": 1.9315078258514404,
|
| 468 |
+
"eval_runtime": 4.84,
|
| 469 |
+
"eval_samples_per_second": 103.306,
|
| 470 |
+
"eval_steps_per_second": 13.017,
|
| 471 |
"step": 3375
|
| 472 |
},
|
| 473 |
{
|
| 474 |
"epoch": 18.0,
|
| 475 |
+
"eval_exact_match": 16.6,
|
| 476 |
+
"eval_f1": 26.37841269841271,
|
| 477 |
"step": 3375
|
| 478 |
},
|
| 479 |
{
|
| 480 |
+
"epoch": 18.13,
|
|
|
|
| 481 |
"learning_rate": 0.0005,
|
| 482 |
+
"loss": 0.4418,
|
| 483 |
"step": 3400
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 18.67,
|
|
|
|
| 487 |
"learning_rate": 0.0005,
|
| 488 |
+
"loss": 0.4372,
|
| 489 |
"step": 3500
|
| 490 |
},
|
| 491 |
{
|
| 492 |
+
"epoch": 19.0,
|
| 493 |
+
"eval_accuracy": 0.589948717948718,
|
| 494 |
+
"eval_loss": 1.9201208353042603,
|
| 495 |
+
"eval_runtime": 4.1791,
|
| 496 |
+
"eval_samples_per_second": 119.642,
|
| 497 |
+
"eval_steps_per_second": 15.075,
|
| 498 |
"step": 3562
|
| 499 |
},
|
| 500 |
{
|
| 501 |
+
"epoch": 19.0,
|
| 502 |
+
"eval_exact_match": 17.0,
|
| 503 |
+
"eval_f1": 26.170000000000005,
|
| 504 |
"step": 3562
|
| 505 |
},
|
| 506 |
{
|
| 507 |
"epoch": 19.2,
|
|
|
|
| 508 |
"learning_rate": 0.0005,
|
| 509 |
+
"loss": 0.4385,
|
| 510 |
"step": 3600
|
| 511 |
},
|
| 512 |
{
|
| 513 |
+
"epoch": 19.73,
|
|
|
|
| 514 |
"learning_rate": 0.0005,
|
| 515 |
+
"loss": 0.4359,
|
| 516 |
"step": 3700
|
| 517 |
},
|
| 518 |
{
|
| 519 |
"epoch": 20.0,
|
| 520 |
+
"eval_accuracy": 0.5895384615384616,
|
| 521 |
+
"eval_loss": 1.9752758741378784,
|
| 522 |
+
"eval_runtime": 4.6876,
|
| 523 |
+
"eval_samples_per_second": 106.664,
|
| 524 |
+
"eval_steps_per_second": 13.44,
|
| 525 |
"step": 3750
|
| 526 |
},
|
| 527 |
{
|
| 528 |
"epoch": 20.0,
|
| 529 |
+
"eval_exact_match": 16.6,
|
| 530 |
+
"eval_f1": 26.214126984126988,
|
| 531 |
"step": 3750
|
| 532 |
},
|
| 533 |
{
|
| 534 |
+
"epoch": 20.27,
|
|
|
|
| 535 |
"learning_rate": 0.0005,
|
| 536 |
+
"loss": 0.4294,
|
| 537 |
"step": 3800
|
| 538 |
},
|
| 539 |
{
|
| 540 |
"epoch": 20.8,
|
|
|
|
| 541 |
"learning_rate": 0.0005,
|
| 542 |
+
"loss": 0.4363,
|
| 543 |
"step": 3900
|
| 544 |
},
|
| 545 |
{
|
| 546 |
+
"epoch": 21.0,
|
| 547 |
+
"eval_accuracy": 0.5876923076923077,
|
| 548 |
+
"eval_loss": 1.993224024772644,
|
| 549 |
+
"eval_runtime": 4.8398,
|
| 550 |
+
"eval_samples_per_second": 103.31,
|
| 551 |
+
"eval_steps_per_second": 13.017,
|
| 552 |
"step": 3937
|
| 553 |
},
|
| 554 |
{
|
| 555 |
+
"epoch": 21.0,
|
| 556 |
+
"eval_exact_match": 15.6,
|
| 557 |
+
"eval_f1": 24.723492063492078,
|
| 558 |
"step": 3937
|
| 559 |
},
|
| 560 |
{
|
| 561 |
+
"epoch": 21.33,
|
|
|
|
| 562 |
"learning_rate": 0.0005,
|
| 563 |
+
"loss": 0.4291,
|
| 564 |
"step": 4000
|
| 565 |
},
|
| 566 |
{
|
| 567 |
+
"epoch": 21.87,
|
|
|
|
| 568 |
"learning_rate": 0.0005,
|
| 569 |
+
"loss": 0.4404,
|
| 570 |
"step": 4100
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 22.0,
|
| 574 |
+
"eval_accuracy": 0.5865641025641025,
|
| 575 |
+
"eval_loss": 2.0326027870178223,
|
| 576 |
+
"eval_runtime": 4.2213,
|
| 577 |
+
"eval_samples_per_second": 118.447,
|
| 578 |
+
"eval_steps_per_second": 14.924,
|
| 579 |
"step": 4125
|
| 580 |
},
|
| 581 |
{
|
| 582 |
"epoch": 22.0,
|
| 583 |
+
"eval_exact_match": 15.2,
|
| 584 |
+
"eval_f1": 24.99412698412699,
|
| 585 |
"step": 4125
|
| 586 |
},
|
| 587 |
{
|
| 588 |
"epoch": 22.4,
|
|
|
|
| 589 |
"learning_rate": 0.0005,
|
| 590 |
+
"loss": 0.4303,
|
| 591 |
"step": 4200
|
| 592 |
},
|
| 593 |
{
|
| 594 |
+
"epoch": 22.93,
|
|
|
|
| 595 |
"learning_rate": 0.0005,
|
| 596 |
+
"loss": 0.4436,
|
| 597 |
"step": 4300
|
| 598 |
},
|
| 599 |
{
|
| 600 |
+
"epoch": 23.0,
|
| 601 |
+
"eval_accuracy": 0.5847692307692308,
|
| 602 |
+
"eval_loss": 2.000843048095703,
|
| 603 |
+
"eval_runtime": 4.4158,
|
| 604 |
+
"eval_samples_per_second": 113.229,
|
| 605 |
+
"eval_steps_per_second": 14.267,
|
| 606 |
"step": 4312
|
| 607 |
},
|
| 608 |
{
|
| 609 |
+
"epoch": 23.0,
|
| 610 |
+
"eval_exact_match": 14.4,
|
| 611 |
+
"eval_f1": 23.444285714285712,
|
| 612 |
"step": 4312
|
| 613 |
},
|
| 614 |
{
|
| 615 |
+
"epoch": 23.47,
|
|
|
|
| 616 |
"learning_rate": 0.0005,
|
| 617 |
+
"loss": 0.4268,
|
| 618 |
"step": 4400
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 24.0,
|
|
|
|
| 622 |
"learning_rate": 0.0005,
|
| 623 |
+
"loss": 0.4438,
|
| 624 |
"step": 4500
|
| 625 |
},
|
| 626 |
{
|
| 627 |
"epoch": 24.0,
|
| 628 |
+
"eval_accuracy": 0.5877435897435898,
|
| 629 |
+
"eval_loss": 2.018592596054077,
|
| 630 |
+
"eval_runtime": 4.2112,
|
| 631 |
+
"eval_samples_per_second": 118.731,
|
| 632 |
+
"eval_steps_per_second": 14.96,
|
| 633 |
"step": 4500
|
| 634 |
},
|
| 635 |
{
|
| 636 |
"epoch": 24.0,
|
| 637 |
+
"eval_exact_match": 16.0,
|
| 638 |
+
"eval_f1": 24.778412698412712,
|
| 639 |
"step": 4500
|
| 640 |
},
|
| 641 |
{
|
| 642 |
+
"epoch": 24.53,
|
|
|
|
| 643 |
"learning_rate": 0.0005,
|
| 644 |
+
"loss": 0.4233,
|
| 645 |
"step": 4600
|
| 646 |
},
|
| 647 |
{
|
| 648 |
+
"epoch": 25.0,
|
| 649 |
+
"eval_accuracy": 0.5862564102564103,
|
| 650 |
+
"eval_loss": 2.04520320892334,
|
| 651 |
+
"eval_runtime": 4.1216,
|
| 652 |
+
"eval_samples_per_second": 121.312,
|
| 653 |
+
"eval_steps_per_second": 15.285,
|
| 654 |
"step": 4687
|
| 655 |
},
|
| 656 |
{
|
| 657 |
+
"epoch": 25.0,
|
| 658 |
+
"eval_exact_match": 14.6,
|
| 659 |
+
"eval_f1": 22.220476190476194,
|
| 660 |
"step": 4687
|
| 661 |
},
|
| 662 |
{
|
| 663 |
+
"epoch": 25.07,
|
|
|
|
| 664 |
"learning_rate": 0.0005,
|
| 665 |
+
"loss": 0.4388,
|
| 666 |
"step": 4700
|
| 667 |
},
|
| 668 |
{
|
| 669 |
"epoch": 25.6,
|
|
|
|
| 670 |
"learning_rate": 0.0005,
|
| 671 |
+
"loss": 0.4237,
|
| 672 |
"step": 4800
|
| 673 |
},
|
| 674 |
{
|
| 675 |
"epoch": 26.0,
|
| 676 |
+
"eval_accuracy": 0.5842564102564103,
|
| 677 |
+
"eval_loss": 2.0520122051239014,
|
| 678 |
+
"eval_runtime": 4.2989,
|
| 679 |
+
"eval_samples_per_second": 116.31,
|
| 680 |
+
"eval_steps_per_second": 14.655,
|
| 681 |
"step": 4875
|
| 682 |
},
|
| 683 |
{
|
| 684 |
"epoch": 26.0,
|
| 685 |
+
"eval_exact_match": 15.8,
|
| 686 |
+
"eval_f1": 24.92222222222223,
|
| 687 |
"step": 4875
|
| 688 |
},
|
| 689 |
{
|
| 690 |
+
"epoch": 26.13,
|
|
|
|
| 691 |
"learning_rate": 0.0005,
|
| 692 |
+
"loss": 0.4362,
|
| 693 |
"step": 4900
|
| 694 |
},
|
| 695 |
{
|
| 696 |
+
"epoch": 26.67,
|
|
|
|
| 697 |
"learning_rate": 0.0005,
|
| 698 |
+
"loss": 0.4289,
|
| 699 |
"step": 5000
|
| 700 |
},
|
| 701 |
{
|
| 702 |
+
"epoch": 27.0,
|
| 703 |
+
"eval_accuracy": 0.5827692307692308,
|
| 704 |
+
"eval_loss": 2.0817410945892334,
|
| 705 |
+
"eval_runtime": 4.4121,
|
| 706 |
+
"eval_samples_per_second": 113.325,
|
| 707 |
+
"eval_steps_per_second": 14.279,
|
| 708 |
"step": 5062
|
| 709 |
},
|
| 710 |
{
|
| 711 |
+
"epoch": 27.0,
|
| 712 |
+
"eval_exact_match": 13.6,
|
| 713 |
+
"eval_f1": 21.646507936507945,
|
| 714 |
"step": 5062
|
| 715 |
},
|
| 716 |
{
|
| 717 |
"epoch": 27.2,
|
|
|
|
| 718 |
"learning_rate": 0.0005,
|
| 719 |
+
"loss": 0.4335,
|
| 720 |
"step": 5100
|
| 721 |
},
|
| 722 |
{
|
| 723 |
+
"epoch": 27.73,
|
|
|
|
| 724 |
"learning_rate": 0.0005,
|
| 725 |
+
"loss": 0.4325,
|
| 726 |
"step": 5200
|
| 727 |
},
|
| 728 |
{
|
| 729 |
"epoch": 28.0,
|
| 730 |
+
"eval_accuracy": 0.5833333333333334,
|
| 731 |
+
"eval_loss": 2.0512030124664307,
|
| 732 |
+
"eval_runtime": 4.214,
|
| 733 |
+
"eval_samples_per_second": 118.653,
|
| 734 |
+
"eval_steps_per_second": 14.95,
|
| 735 |
"step": 5250
|
| 736 |
},
|
| 737 |
{
|
| 738 |
"epoch": 28.0,
|
| 739 |
+
"eval_exact_match": 14.4,
|
| 740 |
+
"eval_f1": 23.620476190476197,
|
| 741 |
"step": 5250
|
| 742 |
},
|
| 743 |
{
|
| 744 |
+
"epoch": 28.27,
|
|
|
|
| 745 |
"learning_rate": 0.0005,
|
| 746 |
+
"loss": 0.4325,
|
| 747 |
"step": 5300
|
| 748 |
},
|
| 749 |
{
|
| 750 |
"epoch": 28.8,
|
|
|
|
| 751 |
"learning_rate": 0.0005,
|
| 752 |
+
"loss": 0.4329,
|
| 753 |
"step": 5400
|
| 754 |
},
|
| 755 |
{
|
| 756 |
+
"epoch": 29.0,
|
| 757 |
+
"eval_accuracy": 0.5827692307692308,
|
| 758 |
+
"eval_loss": 2.090564250946045,
|
| 759 |
+
"eval_runtime": 4.1103,
|
| 760 |
+
"eval_samples_per_second": 121.646,
|
| 761 |
+
"eval_steps_per_second": 15.327,
|
| 762 |
"step": 5437
|
| 763 |
},
|
| 764 |
{
|
| 765 |
+
"epoch": 29.0,
|
| 766 |
+
"eval_exact_match": 14.0,
|
| 767 |
+
"eval_f1": 22.421443001443002,
|
| 768 |
"step": 5437
|
| 769 |
},
|
| 770 |
{
|
| 771 |
+
"epoch": 29.33,
|
|
|
|
| 772 |
"learning_rate": 0.0005,
|
| 773 |
+
"loss": 0.4245,
|
| 774 |
"step": 5500
|
| 775 |
},
|
| 776 |
{
|
| 777 |
+
"epoch": 29.87,
|
|
|
|
| 778 |
"learning_rate": 0.0005,
|
| 779 |
+
"loss": 0.4314,
|
| 780 |
"step": 5600
|
| 781 |
},
|
| 782 |
{
|
| 783 |
"epoch": 30.0,
|
| 784 |
+
"eval_accuracy": 0.5824102564102565,
|
| 785 |
+
"eval_loss": 2.040344715118408,
|
| 786 |
+
"eval_runtime": 4.4139,
|
| 787 |
+
"eval_samples_per_second": 113.279,
|
| 788 |
+
"eval_steps_per_second": 14.273,
|
| 789 |
"step": 5625
|
| 790 |
},
|
| 791 |
{
|
| 792 |
"epoch": 30.0,
|
| 793 |
+
"eval_exact_match": 14.2,
|
| 794 |
+
"eval_f1": 22.46904761904763,
|
| 795 |
"step": 5625
|
| 796 |
},
|
| 797 |
{
|
| 798 |
"epoch": 30.4,
|
|
|
|
| 799 |
"learning_rate": 0.0005,
|
| 800 |
+
"loss": 0.4204,
|
| 801 |
"step": 5700
|
| 802 |
},
|
| 803 |
{
|
| 804 |
+
"epoch": 30.93,
|
|
|
|
| 805 |
"learning_rate": 0.0005,
|
| 806 |
+
"loss": 0.431,
|
| 807 |
"step": 5800
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 31.0,
|
| 811 |
+
"eval_accuracy": 0.5824102564102565,
|
| 812 |
+
"eval_loss": 2.1193599700927734,
|
| 813 |
+
"eval_runtime": 4.2048,
|
| 814 |
+
"eval_samples_per_second": 118.913,
|
| 815 |
+
"eval_steps_per_second": 14.983,
|
| 816 |
"step": 5812
|
| 817 |
},
|
| 818 |
{
|
| 819 |
+
"epoch": 31.0,
|
| 820 |
+
"eval_exact_match": 13.8,
|
| 821 |
+
"eval_f1": 21.95365079365079,
|
| 822 |
"step": 5812
|
| 823 |
},
|
| 824 |
{
|
| 825 |
+
"epoch": 31.47,
|
|
|
|
| 826 |
"learning_rate": 0.0005,
|
| 827 |
+
"loss": 0.4171,
|
| 828 |
"step": 5900
|
| 829 |
},
|
| 830 |
{
|
| 831 |
"epoch": 32.0,
|
|
|
|
| 832 |
"learning_rate": 0.0005,
|
| 833 |
+
"loss": 0.4318,
|
| 834 |
"step": 6000
|
| 835 |
},
|
| 836 |
{
|
| 837 |
"epoch": 32.0,
|
| 838 |
+
"eval_accuracy": 0.5829230769230769,
|
| 839 |
+
"eval_loss": 2.0985310077667236,
|
| 840 |
+
"eval_runtime": 4.1086,
|
| 841 |
+
"eval_samples_per_second": 121.695,
|
| 842 |
+
"eval_steps_per_second": 15.334,
|
| 843 |
"step": 6000
|
| 844 |
},
|
| 845 |
{
|
| 846 |
"epoch": 32.0,
|
| 847 |
+
"eval_exact_match": 12.4,
|
| 848 |
+
"eval_f1": 23.018571428571445,
|
| 849 |
"step": 6000
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 32.53,
|
|
|
|
| 853 |
"learning_rate": 0.0005,
|
| 854 |
+
"loss": 0.414,
|
| 855 |
"step": 6100
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 33.0,
|
| 859 |
+
"eval_accuracy": 0.5804615384615385,
|
| 860 |
+
"eval_loss": 2.153252363204956,
|
| 861 |
+
"eval_runtime": 4.4979,
|
| 862 |
+
"eval_samples_per_second": 111.163,
|
| 863 |
+
"eval_steps_per_second": 14.007,
|
| 864 |
"step": 6187
|
| 865 |
},
|
| 866 |
{
|
| 867 |
+
"epoch": 33.0,
|
| 868 |
+
"eval_exact_match": 13.6,
|
| 869 |
+
"eval_f1": 22.67636363636364,
|
| 870 |
"step": 6187
|
| 871 |
},
|
| 872 |
{
|
| 873 |
+
"epoch": 33.07,
|
|
|
|
| 874 |
"learning_rate": 0.0005,
|
| 875 |
+
"loss": 0.4304,
|
| 876 |
"step": 6200
|
| 877 |
},
|
| 878 |
{
|
| 879 |
"epoch": 33.6,
|
|
|
|
| 880 |
"learning_rate": 0.0005,
|
| 881 |
+
"loss": 0.4214,
|
| 882 |
"step": 6300
|
| 883 |
},
|
| 884 |
{
|
| 885 |
"epoch": 34.0,
|
| 886 |
+
"eval_accuracy": 0.5779487179487179,
|
| 887 |
+
"eval_loss": 2.1918230056762695,
|
| 888 |
+
"eval_runtime": 4.2094,
|
| 889 |
+
"eval_samples_per_second": 118.781,
|
| 890 |
+
"eval_steps_per_second": 14.966,
|
| 891 |
"step": 6375
|
| 892 |
},
|
| 893 |
{
|
| 894 |
"epoch": 34.0,
|
| 895 |
+
"eval_exact_match": 12.6,
|
| 896 |
+
"eval_f1": 19.036190476190484,
|
| 897 |
"step": 6375
|
| 898 |
},
|
| 899 |
{
|
| 900 |
+
"epoch": 34.13,
|
|
|
|
| 901 |
"learning_rate": 0.0005,
|
| 902 |
+
"loss": 0.4306,
|
| 903 |
"step": 6400
|
| 904 |
},
|
| 905 |
{
|
| 906 |
+
"epoch": 34.67,
|
|
|
|
| 907 |
"learning_rate": 0.0005,
|
| 908 |
+
"loss": 0.4264,
|
| 909 |
"step": 6500
|
| 910 |
},
|
| 911 |
{
|
| 912 |
+
"epoch": 35.0,
|
| 913 |
+
"eval_accuracy": 0.5774358974358974,
|
| 914 |
+
"eval_loss": 2.1834912300109863,
|
| 915 |
+
"eval_runtime": 4.4082,
|
| 916 |
+
"eval_samples_per_second": 113.425,
|
| 917 |
+
"eval_steps_per_second": 14.292,
|
| 918 |
"step": 6562
|
| 919 |
},
|
| 920 |
{
|
| 921 |
+
"epoch": 35.0,
|
| 922 |
+
"eval_exact_match": 12.8,
|
| 923 |
+
"eval_f1": 19.5436507936508,
|
| 924 |
"step": 6562
|
| 925 |
},
|
| 926 |
{
|
| 927 |
"epoch": 35.2,
|
|
|
|
| 928 |
"learning_rate": 0.0005,
|
| 929 |
+
"loss": 0.4317,
|
| 930 |
"step": 6600
|
| 931 |
},
|
| 932 |
{
|
| 933 |
+
"epoch": 35.73,
|
|
|
|
| 934 |
"learning_rate": 0.0005,
|
| 935 |
+
"loss": 0.4361,
|
| 936 |
"step": 6700
|
| 937 |
},
|
| 938 |
{
|
| 939 |
"epoch": 36.0,
|
| 940 |
+
"eval_accuracy": 0.577076923076923,
|
| 941 |
+
"eval_loss": 2.1864311695098877,
|
| 942 |
+
"eval_runtime": 4.848,
|
| 943 |
+
"eval_samples_per_second": 103.135,
|
| 944 |
+
"eval_steps_per_second": 12.995,
|
| 945 |
"step": 6750
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 36.0,
|
| 949 |
+
"eval_exact_match": 12.6,
|
| 950 |
+
"eval_f1": 20.181269841269845,
|
| 951 |
"step": 6750
|
| 952 |
},
|
| 953 |
{
|
| 954 |
+
"epoch": 36.27,
|
|
|
|
| 955 |
"learning_rate": 0.0005,
|
| 956 |
+
"loss": 0.4305,
|
| 957 |
"step": 6800
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 36.8,
|
|
|
|
| 961 |
"learning_rate": 0.0005,
|
| 962 |
+
"loss": 0.4369,
|
| 963 |
"step": 6900
|
| 964 |
},
|
| 965 |
{
|
| 966 |
+
"epoch": 37.0,
|
| 967 |
+
"eval_accuracy": 0.5760512820512821,
|
| 968 |
+
"eval_loss": 2.154608964920044,
|
| 969 |
+
"eval_runtime": 4.2045,
|
| 970 |
+
"eval_samples_per_second": 118.921,
|
| 971 |
+
"eval_steps_per_second": 14.984,
|
| 972 |
"step": 6937
|
| 973 |
},
|
| 974 |
{
|
| 975 |
+
"epoch": 37.0,
|
| 976 |
+
"eval_exact_match": 11.8,
|
| 977 |
+
"eval_f1": 19.080158730158743,
|
| 978 |
"step": 6937
|
| 979 |
},
|
| 980 |
{
|
| 981 |
+
"epoch": 37.33,
|
|
|
|
| 982 |
"learning_rate": 0.0005,
|
| 983 |
+
"loss": 0.4342,
|
| 984 |
"step": 7000
|
| 985 |
},
|
| 986 |
{
|
| 987 |
+
"epoch": 37.87,
|
|
|
|
| 988 |
"learning_rate": 0.0005,
|
| 989 |
+
"loss": 0.4362,
|
| 990 |
"step": 7100
|
| 991 |
},
|
| 992 |
{
|
| 993 |
"epoch": 38.0,
|
| 994 |
+
"eval_accuracy": 0.5752307692307692,
|
| 995 |
+
"eval_loss": 2.1422669887542725,
|
| 996 |
+
"eval_runtime": 4.3154,
|
| 997 |
+
"eval_samples_per_second": 115.864,
|
| 998 |
+
"eval_steps_per_second": 14.599,
|
| 999 |
"step": 7125
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 38.0,
|
| 1003 |
+
"eval_exact_match": 14.0,
|
| 1004 |
+
"eval_f1": 21.96587301587302,
|
| 1005 |
"step": 7125
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 38.4,
|
|
|
|
| 1009 |
"learning_rate": 0.0005,
|
| 1010 |
+
"loss": 0.422,
|
| 1011 |
"step": 7200
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
+
"epoch": 38.93,
|
|
|
|
| 1015 |
"learning_rate": 0.0005,
|
| 1016 |
+
"loss": 0.4322,
|
| 1017 |
"step": 7300
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
+
"epoch": 39.0,
|
| 1021 |
+
"eval_accuracy": 0.5777948717948718,
|
| 1022 |
+
"eval_loss": 2.1937992572784424,
|
| 1023 |
+
"eval_runtime": 4.4107,
|
| 1024 |
+
"eval_samples_per_second": 113.362,
|
| 1025 |
+
"eval_steps_per_second": 14.284,
|
| 1026 |
"step": 7312
|
| 1027 |
},
|
| 1028 |
{
|
| 1029 |
+
"epoch": 39.0,
|
| 1030 |
+
"eval_exact_match": 13.4,
|
| 1031 |
+
"eval_f1": 21.503650793650802,
|
| 1032 |
"step": 7312
|
| 1033 |
},
|
| 1034 |
{
|
| 1035 |
+
"epoch": 39.47,
|
|
|
|
| 1036 |
"learning_rate": 0.0005,
|
| 1037 |
+
"loss": 0.4176,
|
| 1038 |
"step": 7400
|
| 1039 |
},
|
| 1040 |
{
|
| 1041 |
"epoch": 40.0,
|
|
|
|
| 1042 |
"learning_rate": 0.0005,
|
| 1043 |
+
"loss": 0.4359,
|
| 1044 |
"step": 7500
|
| 1045 |
},
|
| 1046 |
{
|
| 1047 |
"epoch": 40.0,
|
| 1048 |
+
"eval_accuracy": 0.5752307692307692,
|
| 1049 |
+
"eval_loss": 2.199964761734009,
|
| 1050 |
+
"eval_runtime": 4.304,
|
| 1051 |
+
"eval_samples_per_second": 116.172,
|
| 1052 |
+
"eval_steps_per_second": 14.638,
|
| 1053 |
"step": 7500
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"epoch": 40.0,
|
| 1057 |
+
"eval_exact_match": 11.4,
|
| 1058 |
+
"eval_f1": 19.18937950937952,
|
| 1059 |
"step": 7500
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
+
"epoch": 40.53,
|
|
|
|
| 1063 |
"learning_rate": 0.0005,
|
| 1064 |
+
"loss": 0.4153,
|
| 1065 |
"step": 7600
|
| 1066 |
},
|
| 1067 |
{
|
| 1068 |
+
"epoch": 41.0,
|
| 1069 |
+
"eval_accuracy": 0.5751282051282052,
|
| 1070 |
+
"eval_loss": 2.2344131469726562,
|
| 1071 |
+
"eval_runtime": 4.4135,
|
| 1072 |
+
"eval_samples_per_second": 113.288,
|
| 1073 |
+
"eval_steps_per_second": 14.274,
|
| 1074 |
"step": 7687
|
| 1075 |
},
|
| 1076 |
{
|
| 1077 |
+
"epoch": 41.0,
|
| 1078 |
+
"eval_exact_match": 12.4,
|
| 1079 |
+
"eval_f1": 20.91698412698414,
|
| 1080 |
"step": 7687
|
| 1081 |
},
|
| 1082 |
{
|
| 1083 |
+
"epoch": 41.07,
|
|
|
|
| 1084 |
"learning_rate": 0.0005,
|
| 1085 |
+
"loss": 0.4299,
|
| 1086 |
"step": 7700
|
| 1087 |
},
|
| 1088 |
{
|
| 1089 |
"epoch": 41.6,
|
|
|
|
| 1090 |
"learning_rate": 0.0005,
|
| 1091 |
+
"loss": 0.4195,
|
| 1092 |
"step": 7800
|
| 1093 |
},
|
| 1094 |
{
|
| 1095 |
"epoch": 42.0,
|
| 1096 |
+
"eval_accuracy": 0.5746666666666667,
|
| 1097 |
+
"eval_loss": 2.2526309490203857,
|
| 1098 |
+
"eval_runtime": 4.8215,
|
| 1099 |
+
"eval_samples_per_second": 103.702,
|
| 1100 |
+
"eval_steps_per_second": 13.067,
|
| 1101 |
"step": 7875
|
| 1102 |
},
|
| 1103 |
{
|
| 1104 |
"epoch": 42.0,
|
| 1105 |
"eval_exact_match": 12.2,
|
| 1106 |
+
"eval_f1": 20.248888888888892,
|
| 1107 |
"step": 7875
|
| 1108 |
},
|
| 1109 |
{
|
| 1110 |
+
"epoch": 42.13,
|
|
|
|
| 1111 |
"learning_rate": 0.0005,
|
| 1112 |
+
"loss": 0.4281,
|
| 1113 |
"step": 7900
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
+
"epoch": 42.67,
|
|
|
|
| 1117 |
"learning_rate": 0.0005,
|
| 1118 |
+
"loss": 0.9164,
|
| 1119 |
"step": 8000
|
| 1120 |
},
|
| 1121 |
{
|
| 1122 |
+
"epoch": 43.0,
|
| 1123 |
+
"eval_accuracy": 0.5717435897435897,
|
| 1124 |
+
"eval_loss": 2.198516607284546,
|
| 1125 |
+
"eval_runtime": 4.1148,
|
| 1126 |
+
"eval_samples_per_second": 121.512,
|
| 1127 |
+
"eval_steps_per_second": 15.311,
|
| 1128 |
"step": 8062
|
| 1129 |
},
|
| 1130 |
{
|
| 1131 |
+
"epoch": 43.0,
|
| 1132 |
+
"eval_exact_match": 0.0,
|
| 1133 |
+
"eval_f1": 0.0,
|
| 1134 |
"step": 8062
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
"epoch": 43.2,
|
|
|
|
| 1138 |
"learning_rate": 0.0005,
|
| 1139 |
+
"loss": 0.4254,
|
| 1140 |
"step": 8100
|
| 1141 |
},
|
| 1142 |
{
|
| 1143 |
+
"epoch": 43.73,
|
|
|
|
| 1144 |
"learning_rate": 0.0005,
|
| 1145 |
+
"loss": 0.4295,
|
| 1146 |
"step": 8200
|
| 1147 |
},
|
| 1148 |
{
|
| 1149 |
"epoch": 44.0,
|
| 1150 |
+
"eval_accuracy": 0.5718461538461539,
|
| 1151 |
+
"eval_loss": 2.2145252227783203,
|
| 1152 |
+
"eval_runtime": 4.5366,
|
| 1153 |
+
"eval_samples_per_second": 110.215,
|
| 1154 |
+
"eval_steps_per_second": 13.887,
|
| 1155 |
"step": 8250
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
"epoch": 44.0,
|
| 1159 |
+
"eval_exact_match": 0.0,
|
| 1160 |
+
"eval_f1": 0.3637908496732027,
|
| 1161 |
"step": 8250
|
| 1162 |
},
|
| 1163 |
{
|
| 1164 |
+
"epoch": 44.27,
|
|
|
|
| 1165 |
"learning_rate": 0.0005,
|
| 1166 |
+
"loss": 0.4325,
|
| 1167 |
"step": 8300
|
| 1168 |
},
|
| 1169 |
{
|
| 1170 |
"epoch": 44.8,
|
|
|
|
| 1171 |
"learning_rate": 0.0005,
|
| 1172 |
+
"loss": 0.4298,
|
| 1173 |
"step": 8400
|
| 1174 |
},
|
| 1175 |
{
|
| 1176 |
+
"epoch": 45.0,
|
| 1177 |
+
"eval_accuracy": 0.5714358974358974,
|
| 1178 |
+
"eval_loss": 2.2210655212402344,
|
| 1179 |
+
"eval_runtime": 4.1242,
|
| 1180 |
+
"eval_samples_per_second": 121.236,
|
| 1181 |
+
"eval_steps_per_second": 15.276,
|
| 1182 |
"step": 8437
|
| 1183 |
},
|
| 1184 |
{
|
| 1185 |
+
"epoch": 45.0,
|
| 1186 |
+
"eval_exact_match": 0.0,
|
| 1187 |
+
"eval_f1": 0.24738095238095234,
|
| 1188 |
"step": 8437
|
| 1189 |
},
|
| 1190 |
{
|
| 1191 |
+
"epoch": 45.33,
|
|
|
|
| 1192 |
"learning_rate": 0.0005,
|
| 1193 |
+
"loss": 0.424,
|
| 1194 |
"step": 8500
|
| 1195 |
},
|
| 1196 |
{
|
| 1197 |
+
"epoch": 45.87,
|
|
|
|
| 1198 |
"learning_rate": 0.0005,
|
| 1199 |
+
"loss": 0.4446,
|
| 1200 |
"step": 8600
|
| 1201 |
},
|
| 1202 |
{
|
| 1203 |
"epoch": 46.0,
|
| 1204 |
+
"eval_accuracy": 0.5703076923076923,
|
| 1205 |
+
"eval_loss": 2.2656009197235107,
|
| 1206 |
+
"eval_runtime": 4.4179,
|
| 1207 |
+
"eval_samples_per_second": 113.176,
|
| 1208 |
+
"eval_steps_per_second": 14.26,
|
| 1209 |
"step": 8625
|
| 1210 |
},
|
| 1211 |
{
|
| 1212 |
"epoch": 46.0,
|
| 1213 |
+
"eval_exact_match": 8.8,
|
| 1214 |
+
"eval_f1": 14.593650793650792,
|
| 1215 |
"step": 8625
|
| 1216 |
},
|
| 1217 |
{
|
| 1218 |
"epoch": 46.4,
|
|
|
|
| 1219 |
"learning_rate": 0.0005,
|
| 1220 |
+
"loss": 0.432,
|
| 1221 |
"step": 8700
|
| 1222 |
},
|
| 1223 |
{
|
| 1224 |
+
"epoch": 46.93,
|
|
|
|
| 1225 |
"learning_rate": 0.0005,
|
| 1226 |
+
"loss": 2.0935,
|
| 1227 |
"step": 8800
|
| 1228 |
},
|
| 1229 |
{
|
| 1230 |
+
"epoch": 47.0,
|
| 1231 |
+
"eval_accuracy": 0.508051282051282,
|
| 1232 |
+
"eval_loss": 2.6961801052093506,
|
| 1233 |
+
"eval_runtime": 4.1054,
|
| 1234 |
+
"eval_samples_per_second": 121.791,
|
| 1235 |
+
"eval_steps_per_second": 15.346,
|
| 1236 |
"step": 8812
|
| 1237 |
},
|
| 1238 |
{
|
| 1239 |
+
"epoch": 47.0,
|
| 1240 |
+
"eval_exact_match": 0.0,
|
| 1241 |
+
"eval_f1": 0.18556408527218912,
|
| 1242 |
"step": 8812
|
| 1243 |
}
|
| 1244 |
],
|
| 1245 |
"logging_steps": 100,
|
| 1246 |
"max_steps": 9350,
|
|
|
|
| 1247 |
"num_train_epochs": 50,
|
| 1248 |
"save_steps": 500,
|
| 1249 |
+
"total_flos": 3.2885388234194944e+17,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1250 |
"trial_name": null,
|
| 1251 |
"trial_params": null
|
| 1252 |
}
|
checkpoint-8812/training_args.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:aeaafcc180d545c4c7bc83b3ef040967ab10c6394ea7a4c1dc01fb190e8fc740
|
| 3 |
+
size 4728
|