Training in progress, epoch 12, checkpoint
Browse files- checkpoint-14160/adapter_config.json +1 -1
- checkpoint-14160/adapter_model.bin +3 -0
- checkpoint-14160/added_tokens.json +3 -3
- checkpoint-14160/optimizer.pt +2 -2
- checkpoint-14160/rng_state_0.pth +1 -1
- checkpoint-14160/rng_state_1.pth +1 -1
- checkpoint-14160/rng_state_2.pth +1 -1
- checkpoint-14160/rng_state_3.pth +1 -1
- checkpoint-14160/special_tokens_map.json +4 -12
- checkpoint-14160/tokenizer.json +0 -0
- checkpoint-14160/tokenizer.model +3 -0
- checkpoint-14160/tokenizer_config.json +17 -20
- checkpoint-14160/trainer_state.json +390 -545
- checkpoint-14160/training_args.bin +2 -2
checkpoint-14160/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-14160/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ce09b678789155f5bd6ccb43127a68056e2986fe1c29da5b63b924bdaae1fa
|
| 3 |
+
size 143269386
|
checkpoint-14160/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-14160/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 sha256:9d688463df585a5cbd47ddad2914eece48fad7b230070fb1c4b2290e3bb269a7
|
| 3 |
+
size 286585234
|
checkpoint-14160/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 sha256:5290d89b2be52508dc6adc67028a07d532fd3473c458323c1a5152fa3128a513
|
| 3 |
size 15024
|
checkpoint-14160/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:b0cfc76bc5c5acd3c4a678728b4b666c4b689ea3a420573b7cbd16bf0976ad0c
|
| 3 |
size 15024
|
checkpoint-14160/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 sha256:5b4dde63bf548099eaf38768e08b2638774a5a93fa44d740e778d26afa377e01
|
| 3 |
size 15024
|
checkpoint-14160/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 sha256:5c37e80f6116e819dd18cfae74585670e849427590ddd7c4cc88171a9c87225a
|
| 3 |
size 15024
|
checkpoint-14160/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-14160/tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-14160/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-14160/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-14160/trainer_state.json
CHANGED
|
@@ -9,1207 +9,1052 @@
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
-
"epoch": 0.
|
| 13 |
-
"grad_norm": 0.5307241678237915,
|
| 14 |
"learning_rate": 3e-05,
|
| 15 |
-
"loss":
|
| 16 |
"step": 100
|
| 17 |
},
|
| 18 |
{
|
| 19 |
-
"epoch": 0.
|
| 20 |
-
"grad_norm": 0.6362708210945129,
|
| 21 |
"learning_rate": 3e-05,
|
| 22 |
-
"loss": 1.
|
| 23 |
"step": 200
|
| 24 |
},
|
| 25 |
{
|
| 26 |
-
"epoch": 0.
|
| 27 |
-
"grad_norm": 0.3823029696941376,
|
| 28 |
"learning_rate": 3e-05,
|
| 29 |
-
"loss": 1.
|
| 30 |
"step": 300
|
| 31 |
},
|
| 32 |
{
|
| 33 |
-
"epoch": 0.
|
| 34 |
-
"grad_norm": 0.43036168813705444,
|
| 35 |
"learning_rate": 3e-05,
|
| 36 |
-
"loss": 1.
|
| 37 |
"step": 400
|
| 38 |
},
|
| 39 |
{
|
| 40 |
-
"epoch": 0.
|
| 41 |
-
"grad_norm": 0.5922847390174866,
|
| 42 |
"learning_rate": 3e-05,
|
| 43 |
-
"loss": 1.
|
| 44 |
"step": 500
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch": 0.
|
| 48 |
-
"grad_norm": 0.40470582246780396,
|
| 49 |
"learning_rate": 3e-05,
|
| 50 |
-
"loss": 1.
|
| 51 |
"step": 600
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch": 0.
|
| 55 |
-
"grad_norm": 0.49739205837249756,
|
| 56 |
"learning_rate": 3e-05,
|
| 57 |
-
"loss": 1.
|
| 58 |
"step": 700
|
| 59 |
},
|
| 60 |
{
|
| 61 |
-
"epoch": 0.
|
| 62 |
-
"grad_norm": 0.43984296917915344,
|
| 63 |
"learning_rate": 3e-05,
|
| 64 |
-
"loss": 1.
|
| 65 |
"step": 800
|
| 66 |
},
|
| 67 |
{
|
| 68 |
-
"epoch": 0.
|
| 69 |
-
"grad_norm": 0.4566909968852997,
|
| 70 |
"learning_rate": 3e-05,
|
| 71 |
-
"loss": 1.
|
| 72 |
"step": 900
|
| 73 |
},
|
| 74 |
{
|
| 75 |
-
"epoch": 0.
|
| 76 |
-
"grad_norm": 0.4243898093700409,
|
| 77 |
"learning_rate": 3e-05,
|
| 78 |
-
"loss": 1.
|
| 79 |
"step": 1000
|
| 80 |
},
|
| 81 |
{
|
| 82 |
-
"epoch": 0
|
| 83 |
-
"eval_accuracy": 0.
|
| 84 |
-
"eval_loss":
|
| 85 |
-
"eval_runtime":
|
| 86 |
-
"eval_samples_per_second":
|
| 87 |
-
"eval_steps_per_second":
|
| 88 |
"step": 1089
|
| 89 |
},
|
| 90 |
{
|
| 91 |
-
"epoch": 0
|
| 92 |
-
"eval_exact_match":
|
| 93 |
-
"eval_f1":
|
| 94 |
"step": 1089
|
| 95 |
},
|
| 96 |
{
|
| 97 |
-
"epoch": 1.
|
| 98 |
-
"grad_norm": 0.47265738248825073,
|
| 99 |
"learning_rate": 3e-05,
|
| 100 |
-
"loss": 1.
|
| 101 |
"step": 1100
|
| 102 |
},
|
| 103 |
{
|
| 104 |
-
"epoch": 1.
|
| 105 |
-
"grad_norm": 0.6015958189964294,
|
| 106 |
"learning_rate": 3e-05,
|
| 107 |
-
"loss": 1.
|
| 108 |
"step": 1200
|
| 109 |
},
|
| 110 |
{
|
| 111 |
-
"epoch": 1.
|
| 112 |
-
"grad_norm": 0.5499740242958069,
|
| 113 |
"learning_rate": 3e-05,
|
| 114 |
-
"loss": 1.
|
| 115 |
"step": 1300
|
| 116 |
},
|
| 117 |
{
|
| 118 |
-
"epoch": 1.
|
| 119 |
-
"grad_norm": 0.5272372961044312,
|
| 120 |
"learning_rate": 3e-05,
|
| 121 |
-
"loss": 1.
|
| 122 |
"step": 1400
|
| 123 |
},
|
| 124 |
{
|
| 125 |
-
"epoch": 1.
|
| 126 |
-
"grad_norm": 0.5437406897544861,
|
| 127 |
"learning_rate": 3e-05,
|
| 128 |
-
"loss": 1.
|
| 129 |
"step": 1500
|
| 130 |
},
|
| 131 |
{
|
| 132 |
-
"epoch": 1.
|
| 133 |
-
"grad_norm": 0.5464481115341187,
|
| 134 |
"learning_rate": 3e-05,
|
| 135 |
-
"loss": 1.
|
| 136 |
"step": 1600
|
| 137 |
},
|
| 138 |
{
|
| 139 |
-
"epoch": 1.
|
| 140 |
-
"grad_norm": 0.6755242347717285,
|
| 141 |
"learning_rate": 3e-05,
|
| 142 |
-
"loss": 1.
|
| 143 |
"step": 1700
|
| 144 |
},
|
| 145 |
{
|
| 146 |
-
"epoch": 1.
|
| 147 |
-
"grad_norm": 0.5893722176551819,
|
| 148 |
"learning_rate": 3e-05,
|
| 149 |
-
"loss": 1.
|
| 150 |
"step": 1800
|
| 151 |
},
|
| 152 |
{
|
| 153 |
-
"epoch": 1.
|
| 154 |
-
"grad_norm": 0.5930923223495483,
|
| 155 |
"learning_rate": 3e-05,
|
| 156 |
-
"loss": 1.
|
| 157 |
"step": 1900
|
| 158 |
},
|
| 159 |
{
|
| 160 |
-
"epoch": 1.
|
| 161 |
-
"grad_norm": 0.5917518734931946,
|
| 162 |
"learning_rate": 3e-05,
|
| 163 |
-
"loss": 1.
|
| 164 |
"step": 2000
|
| 165 |
},
|
| 166 |
{
|
| 167 |
-
"epoch": 1.
|
| 168 |
-
"grad_norm": 0.6680920124053955,
|
| 169 |
"learning_rate": 3e-05,
|
| 170 |
-
"loss": 1.
|
| 171 |
"step": 2100
|
| 172 |
},
|
| 173 |
{
|
| 174 |
-
"epoch":
|
| 175 |
-
"eval_accuracy": 0.
|
| 176 |
-
"eval_loss":
|
| 177 |
-
"eval_runtime":
|
| 178 |
-
"eval_samples_per_second":
|
| 179 |
-
"eval_steps_per_second":
|
| 180 |
"step": 2178
|
| 181 |
},
|
| 182 |
{
|
| 183 |
-
"epoch":
|
| 184 |
-
"eval_exact_match":
|
| 185 |
-
"eval_f1":
|
| 186 |
"step": 2178
|
| 187 |
},
|
| 188 |
{
|
| 189 |
-
"epoch": 2.
|
| 190 |
-
"grad_norm": 0.6736780405044556,
|
| 191 |
"learning_rate": 3e-05,
|
| 192 |
-
"loss": 1.
|
| 193 |
"step": 2200
|
| 194 |
},
|
| 195 |
{
|
| 196 |
-
"epoch": 2.
|
| 197 |
-
"grad_norm": 0.7276094555854797,
|
| 198 |
"learning_rate": 3e-05,
|
| 199 |
-
"loss": 1.
|
| 200 |
"step": 2300
|
| 201 |
},
|
| 202 |
{
|
| 203 |
-
"epoch": 2.
|
| 204 |
-
"grad_norm": 0.7279476523399353,
|
| 205 |
"learning_rate": 3e-05,
|
| 206 |
-
"loss": 1.
|
| 207 |
"step": 2400
|
| 208 |
},
|
| 209 |
{
|
| 210 |
-
"epoch": 2.
|
| 211 |
-
"grad_norm": 0.7652662992477417,
|
| 212 |
"learning_rate": 3e-05,
|
| 213 |
-
"loss": 1.
|
| 214 |
"step": 2500
|
| 215 |
},
|
| 216 |
{
|
| 217 |
-
"epoch": 2.
|
| 218 |
-
"grad_norm": 0.6291841268539429,
|
| 219 |
"learning_rate": 3e-05,
|
| 220 |
-
"loss": 1.
|
| 221 |
"step": 2600
|
| 222 |
},
|
| 223 |
{
|
| 224 |
-
"epoch": 2.
|
| 225 |
-
"grad_norm": 0.7375943660736084,
|
| 226 |
"learning_rate": 3e-05,
|
| 227 |
-
"loss": 1.
|
| 228 |
"step": 2700
|
| 229 |
},
|
| 230 |
{
|
| 231 |
-
"epoch": 2.
|
| 232 |
-
"grad_norm": 0.7475445866584778,
|
| 233 |
"learning_rate": 3e-05,
|
| 234 |
-
"loss": 1.
|
| 235 |
"step": 2800
|
| 236 |
},
|
| 237 |
{
|
| 238 |
-
"epoch": 2.
|
| 239 |
-
"grad_norm": 5.488095283508301,
|
| 240 |
"learning_rate": 3e-05,
|
| 241 |
-
"loss": 1.
|
| 242 |
"step": 2900
|
| 243 |
},
|
| 244 |
{
|
| 245 |
-
"epoch": 2.
|
| 246 |
-
"grad_norm": 11046773.0,
|
| 247 |
"learning_rate": 3e-05,
|
| 248 |
-
"loss":
|
| 249 |
"step": 3000
|
| 250 |
},
|
| 251 |
{
|
| 252 |
-
"epoch": 2.
|
| 253 |
-
"grad_norm": 9348.0419921875,
|
| 254 |
"learning_rate": 3e-05,
|
| 255 |
-
"loss":
|
| 256 |
"step": 3100
|
| 257 |
},
|
| 258 |
{
|
| 259 |
-
"epoch": 2.
|
| 260 |
-
"grad_norm": 42427.7578125,
|
| 261 |
"learning_rate": 3e-05,
|
| 262 |
-
"loss":
|
| 263 |
"step": 3200
|
| 264 |
},
|
| 265 |
{
|
| 266 |
-
"epoch":
|
| 267 |
-
"eval_accuracy": 0.
|
| 268 |
-
"eval_loss":
|
| 269 |
-
"eval_runtime":
|
| 270 |
-
"eval_samples_per_second":
|
| 271 |
-
"eval_steps_per_second":
|
| 272 |
"step": 3267
|
| 273 |
},
|
| 274 |
{
|
| 275 |
-
"epoch":
|
| 276 |
-
"eval_exact_match":
|
| 277 |
-
"eval_f1":
|
| 278 |
"step": 3267
|
| 279 |
},
|
| 280 |
{
|
| 281 |
-
"epoch": 3.
|
| 282 |
-
"grad_norm": 69864.046875,
|
| 283 |
"learning_rate": 3e-05,
|
| 284 |
-
"loss":
|
| 285 |
"step": 3300
|
| 286 |
},
|
| 287 |
{
|
| 288 |
-
"epoch": 3.
|
| 289 |
-
"grad_norm": 763.395263671875,
|
| 290 |
"learning_rate": 3e-05,
|
| 291 |
-
"loss":
|
| 292 |
"step": 3400
|
| 293 |
},
|
| 294 |
{
|
| 295 |
-
"epoch": 3.
|
| 296 |
-
"grad_norm": 297052.0625,
|
| 297 |
"learning_rate": 3e-05,
|
| 298 |
-
"loss":
|
| 299 |
"step": 3500
|
| 300 |
},
|
| 301 |
{
|
| 302 |
-
"epoch": 3.
|
| 303 |
-
"grad_norm": 327590.21875,
|
| 304 |
"learning_rate": 3e-05,
|
| 305 |
-
"loss":
|
| 306 |
"step": 3600
|
| 307 |
},
|
| 308 |
{
|
| 309 |
-
"epoch": 3.
|
| 310 |
-
"grad_norm": 35.1007080078125,
|
| 311 |
"learning_rate": 3e-05,
|
| 312 |
-
"loss":
|
| 313 |
"step": 3700
|
| 314 |
},
|
| 315 |
{
|
| 316 |
-
"epoch": 3.
|
| 317 |
-
"grad_norm": 709.9918823242188,
|
| 318 |
"learning_rate": 3e-05,
|
| 319 |
-
"loss":
|
| 320 |
"step": 3800
|
| 321 |
},
|
| 322 |
{
|
| 323 |
-
"epoch": 3.
|
| 324 |
-
"grad_norm": 5584611.5,
|
| 325 |
"learning_rate": 3e-05,
|
| 326 |
-
"loss":
|
| 327 |
"step": 3900
|
| 328 |
},
|
| 329 |
{
|
| 330 |
-
"epoch": 3.
|
| 331 |
-
"grad_norm": 684474.4375,
|
| 332 |
"learning_rate": 3e-05,
|
| 333 |
-
"loss":
|
| 334 |
"step": 4000
|
| 335 |
},
|
| 336 |
{
|
| 337 |
-
"epoch": 3.
|
| 338 |
-
"grad_norm": 137445040.0,
|
| 339 |
"learning_rate": 3e-05,
|
| 340 |
-
"loss":
|
| 341 |
"step": 4100
|
| 342 |
},
|
| 343 |
{
|
| 344 |
-
"epoch": 3.
|
| 345 |
-
"grad_norm": 15619359.0,
|
| 346 |
"learning_rate": 3e-05,
|
| 347 |
-
"loss":
|
| 348 |
"step": 4200
|
| 349 |
},
|
| 350 |
{
|
| 351 |
-
"epoch": 3.
|
| 352 |
-
"grad_norm": 252526384.0,
|
| 353 |
"learning_rate": 3e-05,
|
| 354 |
-
"loss":
|
| 355 |
"step": 4300
|
| 356 |
},
|
| 357 |
{
|
| 358 |
"epoch": 4.0,
|
| 359 |
-
"eval_accuracy": 0.
|
| 360 |
-
"eval_loss":
|
| 361 |
-
"eval_runtime":
|
| 362 |
-
"eval_samples_per_second":
|
| 363 |
-
"eval_steps_per_second":
|
| 364 |
"step": 4357
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"epoch": 4.0,
|
| 368 |
-
"eval_exact_match":
|
| 369 |
-
"eval_f1":
|
| 370 |
"step": 4357
|
| 371 |
},
|
| 372 |
{
|
| 373 |
-
"epoch": 4.
|
| 374 |
-
"grad_norm": 96136593408.0,
|
| 375 |
"learning_rate": 3e-05,
|
| 376 |
-
"loss":
|
| 377 |
"step": 4400
|
| 378 |
},
|
| 379 |
{
|
| 380 |
-
"epoch": 4.
|
| 381 |
-
"grad_norm": 1025443364864.0,
|
| 382 |
"learning_rate": 3e-05,
|
| 383 |
-
"loss":
|
| 384 |
"step": 4500
|
| 385 |
},
|
| 386 |
{
|
| 387 |
-
"epoch": 4.
|
| 388 |
-
"grad_norm": 265109962752.0,
|
| 389 |
"learning_rate": 3e-05,
|
| 390 |
-
"loss":
|
| 391 |
"step": 4600
|
| 392 |
},
|
| 393 |
{
|
| 394 |
-
"epoch": 4.
|
| 395 |
-
"grad_norm": 3019844.25,
|
| 396 |
"learning_rate": 3e-05,
|
| 397 |
-
"loss":
|
| 398 |
"step": 4700
|
| 399 |
},
|
| 400 |
{
|
| 401 |
-
"epoch": 4.
|
| 402 |
-
"grad_norm": 118806648.0,
|
| 403 |
"learning_rate": 3e-05,
|
| 404 |
-
"loss":
|
| 405 |
"step": 4800
|
| 406 |
},
|
| 407 |
{
|
| 408 |
-
"epoch": 4.
|
| 409 |
-
"grad_norm": 14.5001859664917,
|
| 410 |
"learning_rate": 3e-05,
|
| 411 |
-
"loss":
|
| 412 |
"step": 4900
|
| 413 |
},
|
| 414 |
{
|
| 415 |
-
"epoch": 4.
|
| 416 |
-
"grad_norm": 11.577363014221191,
|
| 417 |
"learning_rate": 3e-05,
|
| 418 |
-
"loss":
|
| 419 |
"step": 5000
|
| 420 |
},
|
| 421 |
{
|
| 422 |
-
"epoch": 4.
|
| 423 |
-
"grad_norm": 6.0267863273620605,
|
| 424 |
"learning_rate": 3e-05,
|
| 425 |
-
"loss":
|
| 426 |
"step": 5100
|
| 427 |
},
|
| 428 |
{
|
| 429 |
-
"epoch": 4.
|
| 430 |
-
"grad_norm": 99.47637176513672,
|
| 431 |
"learning_rate": 3e-05,
|
| 432 |
-
"loss":
|
| 433 |
"step": 5200
|
| 434 |
},
|
| 435 |
{
|
| 436 |
-
"epoch": 4.
|
| 437 |
-
"grad_norm": 4.200494766235352,
|
| 438 |
"learning_rate": 3e-05,
|
| 439 |
-
"loss":
|
| 440 |
"step": 5300
|
| 441 |
},
|
| 442 |
{
|
| 443 |
-
"epoch": 4.
|
| 444 |
-
"grad_norm": 43.855430603027344,
|
| 445 |
"learning_rate": 3e-05,
|
| 446 |
-
"loss":
|
| 447 |
"step": 5400
|
| 448 |
},
|
| 449 |
{
|
| 450 |
-
"epoch":
|
| 451 |
-
"eval_accuracy": 0.
|
| 452 |
-
"eval_loss":
|
| 453 |
-
"eval_runtime":
|
| 454 |
-
"eval_samples_per_second":
|
| 455 |
-
"eval_steps_per_second":
|
| 456 |
"step": 5446
|
| 457 |
},
|
| 458 |
{
|
| 459 |
-
"epoch":
|
| 460 |
-
"eval_exact_match":
|
| 461 |
-
"eval_f1":
|
| 462 |
"step": 5446
|
| 463 |
},
|
| 464 |
{
|
| 465 |
-
"epoch": 5.
|
| 466 |
-
"grad_norm": 751.8612060546875,
|
| 467 |
"learning_rate": 3e-05,
|
| 468 |
-
"loss":
|
| 469 |
"step": 5500
|
| 470 |
},
|
| 471 |
{
|
| 472 |
-
"epoch": 5.
|
| 473 |
-
"grad_norm": 40140.3828125,
|
| 474 |
"learning_rate": 3e-05,
|
| 475 |
-
"loss":
|
| 476 |
"step": 5600
|
| 477 |
},
|
| 478 |
{
|
| 479 |
-
"epoch": 5.
|
| 480 |
-
"grad_norm": 468036.75,
|
| 481 |
"learning_rate": 3e-05,
|
| 482 |
-
"loss":
|
| 483 |
"step": 5700
|
| 484 |
},
|
| 485 |
{
|
| 486 |
-
"epoch": 5.
|
| 487 |
-
"grad_norm": 51365.5390625,
|
| 488 |
"learning_rate": 3e-05,
|
| 489 |
-
"loss":
|
| 490 |
"step": 5800
|
| 491 |
},
|
| 492 |
{
|
| 493 |
-
"epoch": 5.
|
| 494 |
-
"grad_norm": 4080417.5,
|
| 495 |
"learning_rate": 3e-05,
|
| 496 |
-
"loss":
|
| 497 |
"step": 5900
|
| 498 |
},
|
| 499 |
{
|
| 500 |
-
"epoch": 5.
|
| 501 |
-
"grad_norm": 1536171.625,
|
| 502 |
"learning_rate": 3e-05,
|
| 503 |
-
"loss":
|
| 504 |
"step": 6000
|
| 505 |
},
|
| 506 |
{
|
| 507 |
-
"epoch": 5.
|
| 508 |
-
"grad_norm": 42693244.0,
|
| 509 |
"learning_rate": 3e-05,
|
| 510 |
-
"loss":
|
| 511 |
"step": 6100
|
| 512 |
},
|
| 513 |
{
|
| 514 |
-
"epoch": 5.
|
| 515 |
-
"grad_norm": 776647.25,
|
| 516 |
"learning_rate": 3e-05,
|
| 517 |
-
"loss":
|
| 518 |
"step": 6200
|
| 519 |
},
|
| 520 |
{
|
| 521 |
-
"epoch": 5.
|
| 522 |
-
"grad_norm": 153013.40625,
|
| 523 |
"learning_rate": 3e-05,
|
| 524 |
-
"loss":
|
| 525 |
"step": 6300
|
| 526 |
},
|
| 527 |
{
|
| 528 |
-
"epoch": 5.
|
| 529 |
-
"grad_norm": 94984.4140625,
|
| 530 |
"learning_rate": 3e-05,
|
| 531 |
-
"loss":
|
| 532 |
"step": 6400
|
| 533 |
},
|
| 534 |
{
|
| 535 |
-
"epoch": 5.
|
| 536 |
-
"grad_norm": 33103526.0,
|
| 537 |
"learning_rate": 3e-05,
|
| 538 |
-
"loss":
|
| 539 |
"step": 6500
|
| 540 |
},
|
| 541 |
{
|
| 542 |
-
"epoch":
|
| 543 |
-
"eval_accuracy": 0.
|
| 544 |
-
"eval_loss":
|
| 545 |
-
"eval_runtime":
|
| 546 |
-
"eval_samples_per_second":
|
| 547 |
-
"eval_steps_per_second":
|
| 548 |
"step": 6535
|
| 549 |
},
|
| 550 |
{
|
| 551 |
-
"epoch":
|
| 552 |
-
"eval_exact_match":
|
| 553 |
-
"eval_f1":
|
| 554 |
"step": 6535
|
| 555 |
},
|
| 556 |
{
|
| 557 |
-
"epoch": 6.
|
| 558 |
-
"grad_norm": 33229708.0,
|
| 559 |
"learning_rate": 3e-05,
|
| 560 |
-
"loss":
|
| 561 |
"step": 6600
|
| 562 |
},
|
| 563 |
{
|
| 564 |
-
"epoch": 6.
|
| 565 |
-
"grad_norm": 769951168.0,
|
| 566 |
"learning_rate": 3e-05,
|
| 567 |
-
"loss":
|
| 568 |
"step": 6700
|
| 569 |
},
|
| 570 |
{
|
| 571 |
-
"epoch": 6.
|
| 572 |
-
"grad_norm": 2425211904.0,
|
| 573 |
"learning_rate": 3e-05,
|
| 574 |
-
"loss":
|
| 575 |
"step": 6800
|
| 576 |
},
|
| 577 |
{
|
| 578 |
-
"epoch": 6.
|
| 579 |
-
"grad_norm": 5989025710080.0,
|
| 580 |
"learning_rate": 3e-05,
|
| 581 |
-
"loss":
|
| 582 |
"step": 6900
|
| 583 |
},
|
| 584 |
{
|
| 585 |
-
"epoch": 6.
|
| 586 |
-
"grad_norm": 175022960.0,
|
| 587 |
"learning_rate": 3e-05,
|
| 588 |
-
"loss":
|
| 589 |
"step": 7000
|
| 590 |
},
|
| 591 |
{
|
| 592 |
-
"epoch": 6.
|
| 593 |
-
"grad_norm": 6010.58642578125,
|
| 594 |
"learning_rate": 3e-05,
|
| 595 |
-
"loss":
|
| 596 |
"step": 7100
|
| 597 |
},
|
| 598 |
{
|
| 599 |
-
"epoch": 6.
|
| 600 |
-
"grad_norm": 1003.8111572265625,
|
| 601 |
"learning_rate": 3e-05,
|
| 602 |
-
"loss":
|
| 603 |
"step": 7200
|
| 604 |
},
|
| 605 |
{
|
| 606 |
-
"epoch": 6.
|
| 607 |
-
"grad_norm": 4030.06787109375,
|
| 608 |
"learning_rate": 3e-05,
|
| 609 |
-
"loss":
|
| 610 |
"step": 7300
|
| 611 |
},
|
| 612 |
{
|
| 613 |
-
"epoch": 6.
|
| 614 |
-
"grad_norm": 59434.1640625,
|
| 615 |
"learning_rate": 3e-05,
|
| 616 |
-
"loss":
|
| 617 |
"step": 7400
|
| 618 |
},
|
| 619 |
{
|
| 620 |
-
"epoch": 6.
|
| 621 |
-
"grad_norm": 66880.4609375,
|
| 622 |
"learning_rate": 3e-05,
|
| 623 |
-
"loss":
|
| 624 |
"step": 7500
|
| 625 |
},
|
| 626 |
{
|
| 627 |
-
"epoch": 6.
|
| 628 |
-
"grad_norm": 4376.875,
|
| 629 |
"learning_rate": 3e-05,
|
| 630 |
-
"loss":
|
| 631 |
"step": 7600
|
| 632 |
},
|
| 633 |
{
|
| 634 |
-
"epoch":
|
| 635 |
-
"eval_accuracy": 0.
|
| 636 |
-
"eval_loss":
|
| 637 |
-
"eval_runtime":
|
| 638 |
-
"eval_samples_per_second":
|
| 639 |
-
"eval_steps_per_second":
|
| 640 |
"step": 7624
|
| 641 |
},
|
| 642 |
{
|
| 643 |
-
"epoch":
|
| 644 |
-
"eval_exact_match":
|
| 645 |
-
"eval_f1":
|
| 646 |
"step": 7624
|
| 647 |
},
|
| 648 |
{
|
| 649 |
-
"epoch": 7.
|
| 650 |
-
"grad_norm": 1153324.75,
|
| 651 |
"learning_rate": 3e-05,
|
| 652 |
-
"loss":
|
| 653 |
"step": 7700
|
| 654 |
},
|
| 655 |
{
|
| 656 |
-
"epoch": 7.
|
| 657 |
-
"grad_norm": 184950352.0,
|
| 658 |
"learning_rate": 3e-05,
|
| 659 |
-
"loss":
|
| 660 |
"step": 7800
|
| 661 |
},
|
| 662 |
{
|
| 663 |
-
"epoch": 7.
|
| 664 |
-
"grad_norm": 153754730496.0,
|
| 665 |
"learning_rate": 3e-05,
|
| 666 |
-
"loss":
|
| 667 |
"step": 7900
|
| 668 |
},
|
| 669 |
{
|
| 670 |
-
"epoch": 7.
|
| 671 |
-
"grad_norm": 1028478208.0,
|
| 672 |
"learning_rate": 3e-05,
|
| 673 |
-
"loss":
|
| 674 |
"step": 8000
|
| 675 |
},
|
| 676 |
{
|
| 677 |
-
"epoch": 7.
|
| 678 |
-
"grad_norm": 168327040.0,
|
| 679 |
"learning_rate": 3e-05,
|
| 680 |
-
"loss":
|
| 681 |
"step": 8100
|
| 682 |
},
|
| 683 |
{
|
| 684 |
-
"epoch": 7.
|
| 685 |
-
"grad_norm": 1722198784.0,
|
| 686 |
"learning_rate": 3e-05,
|
| 687 |
-
"loss":
|
| 688 |
"step": 8200
|
| 689 |
},
|
| 690 |
{
|
| 691 |
-
"epoch": 7.
|
| 692 |
-
"grad_norm": 159030912.0,
|
| 693 |
"learning_rate": 3e-05,
|
| 694 |
-
"loss":
|
| 695 |
"step": 8300
|
| 696 |
},
|
| 697 |
{
|
| 698 |
-
"epoch": 7.
|
| 699 |
-
"grad_norm": 196888912.0,
|
| 700 |
"learning_rate": 3e-05,
|
| 701 |
-
"loss":
|
| 702 |
"step": 8400
|
| 703 |
},
|
| 704 |
{
|
| 705 |
-
"epoch": 7.
|
| 706 |
-
"grad_norm": 6131166720.0,
|
| 707 |
"learning_rate": 3e-05,
|
| 708 |
-
"loss":
|
| 709 |
"step": 8500
|
| 710 |
},
|
| 711 |
{
|
| 712 |
-
"epoch": 7.
|
| 713 |
-
"grad_norm": 2235290880.0,
|
| 714 |
"learning_rate": 3e-05,
|
| 715 |
-
"loss":
|
| 716 |
"step": 8600
|
| 717 |
},
|
| 718 |
{
|
| 719 |
-
"epoch": 7.
|
| 720 |
-
"grad_norm": 477273.15625,
|
| 721 |
"learning_rate": 3e-05,
|
| 722 |
-
"loss":
|
| 723 |
"step": 8700
|
| 724 |
},
|
| 725 |
{
|
| 726 |
"epoch": 8.0,
|
| 727 |
-
"eval_accuracy": 0.
|
| 728 |
-
"eval_loss":
|
| 729 |
-
"eval_runtime":
|
| 730 |
-
"eval_samples_per_second":
|
| 731 |
-
"eval_steps_per_second":
|
| 732 |
"step": 8714
|
| 733 |
},
|
| 734 |
{
|
| 735 |
"epoch": 8.0,
|
| 736 |
-
"eval_exact_match":
|
| 737 |
-
"eval_f1":
|
| 738 |
"step": 8714
|
| 739 |
},
|
| 740 |
{
|
| 741 |
-
"epoch": 8.
|
| 742 |
-
"grad_norm": 124264720.0,
|
| 743 |
"learning_rate": 3e-05,
|
| 744 |
-
"loss":
|
| 745 |
"step": 8800
|
| 746 |
},
|
| 747 |
{
|
| 748 |
-
"epoch": 8.
|
| 749 |
-
"grad_norm": 5402585.5,
|
| 750 |
"learning_rate": 3e-05,
|
| 751 |
-
"loss":
|
| 752 |
"step": 8900
|
| 753 |
},
|
| 754 |
{
|
| 755 |
-
"epoch": 8.
|
| 756 |
-
"grad_norm": 128002850816.0,
|
| 757 |
"learning_rate": 3e-05,
|
| 758 |
-
"loss":
|
| 759 |
"step": 9000
|
| 760 |
},
|
| 761 |
{
|
| 762 |
-
"epoch": 8.
|
| 763 |
-
"grad_norm": 2158333184.0,
|
| 764 |
"learning_rate": 3e-05,
|
| 765 |
-
"loss":
|
| 766 |
"step": 9100
|
| 767 |
},
|
| 768 |
{
|
| 769 |
-
"epoch": 8.
|
| 770 |
-
"grad_norm": 138844256.0,
|
| 771 |
"learning_rate": 3e-05,
|
| 772 |
-
"loss":
|
| 773 |
"step": 9200
|
| 774 |
},
|
| 775 |
{
|
| 776 |
-
"epoch": 8.
|
| 777 |
-
"grad_norm": 1801925.875,
|
| 778 |
"learning_rate": 3e-05,
|
| 779 |
-
"loss":
|
| 780 |
"step": 9300
|
| 781 |
},
|
| 782 |
{
|
| 783 |
-
"epoch": 8.
|
| 784 |
-
"grad_norm": 2586681856.0,
|
| 785 |
"learning_rate": 3e-05,
|
| 786 |
-
"loss":
|
| 787 |
"step": 9400
|
| 788 |
},
|
| 789 |
{
|
| 790 |
-
"epoch": 8.
|
| 791 |
-
"grad_norm": 164454704.0,
|
| 792 |
"learning_rate": 3e-05,
|
| 793 |
-
"loss":
|
| 794 |
"step": 9500
|
| 795 |
},
|
| 796 |
{
|
| 797 |
-
"epoch": 8.
|
| 798 |
-
"grad_norm": 1604157.5,
|
| 799 |
"learning_rate": 3e-05,
|
| 800 |
-
"loss":
|
| 801 |
"step": 9600
|
| 802 |
},
|
| 803 |
{
|
| 804 |
-
"epoch": 8.
|
| 805 |
-
"grad_norm": 845944.5,
|
| 806 |
"learning_rate": 3e-05,
|
| 807 |
-
"loss":
|
| 808 |
"step": 9700
|
| 809 |
},
|
| 810 |
{
|
| 811 |
-
"epoch":
|
| 812 |
-
"grad_norm": 123345.3125,
|
| 813 |
"learning_rate": 3e-05,
|
| 814 |
-
"loss":
|
| 815 |
"step": 9800
|
| 816 |
},
|
| 817 |
{
|
| 818 |
-
"epoch":
|
| 819 |
-
"eval_accuracy": 0.
|
| 820 |
-
"eval_loss":
|
| 821 |
-
"eval_runtime":
|
| 822 |
-
"eval_samples_per_second":
|
| 823 |
-
"eval_steps_per_second": 12.
|
| 824 |
"step": 9803
|
| 825 |
},
|
| 826 |
{
|
| 827 |
-
"epoch":
|
| 828 |
-
"eval_exact_match":
|
| 829 |
-
"eval_f1":
|
| 830 |
"step": 9803
|
| 831 |
},
|
| 832 |
{
|
| 833 |
-
"epoch": 9.
|
| 834 |
-
"grad_norm": 4543730.5,
|
| 835 |
"learning_rate": 3e-05,
|
| 836 |
-
"loss":
|
| 837 |
"step": 9900
|
| 838 |
},
|
| 839 |
{
|
| 840 |
-
"epoch": 9.
|
| 841 |
-
"grad_norm": 204568.890625,
|
| 842 |
"learning_rate": 3e-05,
|
| 843 |
-
"loss":
|
| 844 |
"step": 10000
|
| 845 |
},
|
| 846 |
{
|
| 847 |
-
"epoch": 9.
|
| 848 |
-
"grad_norm": 10227080.0,
|
| 849 |
"learning_rate": 3e-05,
|
| 850 |
-
"loss":
|
| 851 |
"step": 10100
|
| 852 |
},
|
| 853 |
{
|
| 854 |
-
"epoch": 9.
|
| 855 |
-
"grad_norm": 20528.154296875,
|
| 856 |
"learning_rate": 3e-05,
|
| 857 |
-
"loss":
|
| 858 |
"step": 10200
|
| 859 |
},
|
| 860 |
{
|
| 861 |
-
"epoch": 9.
|
| 862 |
-
"grad_norm": 33088.14453125,
|
| 863 |
"learning_rate": 3e-05,
|
| 864 |
-
"loss":
|
| 865 |
"step": 10300
|
| 866 |
},
|
| 867 |
{
|
| 868 |
-
"epoch": 9.
|
| 869 |
-
"grad_norm": 24437.92578125,
|
| 870 |
"learning_rate": 3e-05,
|
| 871 |
-
"loss":
|
| 872 |
"step": 10400
|
| 873 |
},
|
| 874 |
{
|
| 875 |
-
"epoch": 9.
|
| 876 |
-
"grad_norm": 3420.399658203125,
|
| 877 |
"learning_rate": 3e-05,
|
| 878 |
-
"loss":
|
| 879 |
"step": 10500
|
| 880 |
},
|
| 881 |
{
|
| 882 |
-
"epoch": 9.
|
| 883 |
-
"grad_norm": 405.9403381347656,
|
| 884 |
"learning_rate": 3e-05,
|
| 885 |
-
"loss":
|
| 886 |
"step": 10600
|
| 887 |
},
|
| 888 |
{
|
| 889 |
-
"epoch": 9.
|
| 890 |
-
"grad_norm": 3901.121337890625,
|
| 891 |
"learning_rate": 3e-05,
|
| 892 |
-
"loss":
|
| 893 |
"step": 10700
|
| 894 |
},
|
| 895 |
{
|
| 896 |
-
"epoch": 9.
|
| 897 |
-
"grad_norm": 1741.5684814453125,
|
| 898 |
"learning_rate": 3e-05,
|
| 899 |
-
"loss":
|
| 900 |
"step": 10800
|
| 901 |
},
|
| 902 |
{
|
| 903 |
-
"epoch":
|
| 904 |
-
"eval_accuracy": 0.
|
| 905 |
-
"eval_loss":
|
| 906 |
-
"eval_runtime":
|
| 907 |
-
"eval_samples_per_second":
|
| 908 |
-
"eval_steps_per_second":
|
| 909 |
"step": 10892
|
| 910 |
},
|
| 911 |
{
|
| 912 |
-
"epoch":
|
| 913 |
"eval_exact_match": 0.0,
|
| 914 |
-
"eval_f1":
|
| 915 |
"step": 10892
|
| 916 |
},
|
| 917 |
{
|
| 918 |
-
"epoch": 10.
|
| 919 |
-
"grad_norm": 9326.337890625,
|
| 920 |
"learning_rate": 3e-05,
|
| 921 |
-
"loss":
|
| 922 |
"step": 10900
|
| 923 |
},
|
| 924 |
{
|
| 925 |
-
"epoch": 10.
|
| 926 |
-
"grad_norm": 12598.7568359375,
|
| 927 |
"learning_rate": 3e-05,
|
| 928 |
-
"loss":
|
| 929 |
"step": 11000
|
| 930 |
},
|
| 931 |
{
|
| 932 |
-
"epoch": 10.
|
| 933 |
-
"grad_norm": 6.796374797821045,
|
| 934 |
"learning_rate": 3e-05,
|
| 935 |
-
"loss":
|
| 936 |
"step": 11100
|
| 937 |
},
|
| 938 |
{
|
| 939 |
-
"epoch": 10.
|
| 940 |
-
"grad_norm": 29789.6171875,
|
| 941 |
"learning_rate": 3e-05,
|
| 942 |
-
"loss":
|
| 943 |
"step": 11200
|
| 944 |
},
|
| 945 |
{
|
| 946 |
-
"epoch": 10.
|
| 947 |
-
"grad_norm": 213.58909606933594,
|
| 948 |
"learning_rate": 3e-05,
|
| 949 |
-
"loss":
|
| 950 |
"step": 11300
|
| 951 |
},
|
| 952 |
{
|
| 953 |
-
"epoch": 10.
|
| 954 |
-
"grad_norm": 1166033.5,
|
| 955 |
"learning_rate": 3e-05,
|
| 956 |
-
"loss":
|
| 957 |
"step": 11400
|
| 958 |
},
|
| 959 |
{
|
| 960 |
-
"epoch": 10.
|
| 961 |
-
"grad_norm": 3554672.25,
|
| 962 |
"learning_rate": 3e-05,
|
| 963 |
-
"loss":
|
| 964 |
"step": 11500
|
| 965 |
},
|
| 966 |
{
|
| 967 |
-
"epoch": 10.
|
| 968 |
-
"grad_norm": 10.04858684539795,
|
| 969 |
"learning_rate": 3e-05,
|
| 970 |
-
"loss":
|
| 971 |
"step": 11600
|
| 972 |
},
|
| 973 |
{
|
| 974 |
-
"epoch": 10.
|
| 975 |
-
"grad_norm": 860045.8125,
|
| 976 |
"learning_rate": 3e-05,
|
| 977 |
-
"loss":
|
| 978 |
"step": 11700
|
| 979 |
},
|
| 980 |
{
|
| 981 |
-
"epoch": 10.
|
| 982 |
-
"grad_norm": 3906973.0,
|
| 983 |
"learning_rate": 3e-05,
|
| 984 |
-
"loss":
|
| 985 |
"step": 11800
|
| 986 |
},
|
| 987 |
{
|
| 988 |
-
"epoch": 10.
|
| 989 |
-
"grad_norm": 4682.72265625,
|
| 990 |
"learning_rate": 3e-05,
|
| 991 |
-
"loss":
|
| 992 |
"step": 11900
|
| 993 |
},
|
| 994 |
{
|
| 995 |
-
"epoch":
|
| 996 |
-
"eval_accuracy": 0.
|
| 997 |
-
"eval_loss":
|
| 998 |
-
"eval_runtime":
|
| 999 |
-
"eval_samples_per_second":
|
| 1000 |
-
"eval_steps_per_second":
|
| 1001 |
"step": 11981
|
| 1002 |
},
|
| 1003 |
{
|
| 1004 |
-
"epoch":
|
| 1005 |
"eval_exact_match": 0.0,
|
| 1006 |
-
"eval_f1": 0.
|
| 1007 |
"step": 11981
|
| 1008 |
},
|
| 1009 |
{
|
| 1010 |
-
"epoch": 11.
|
| 1011 |
-
"grad_norm": 1283400.375,
|
| 1012 |
"learning_rate": 3e-05,
|
| 1013 |
-
"loss":
|
| 1014 |
"step": 12000
|
| 1015 |
},
|
| 1016 |
{
|
| 1017 |
-
"epoch": 11.
|
| 1018 |
-
"grad_norm": 26411734.0,
|
| 1019 |
"learning_rate": 3e-05,
|
| 1020 |
-
"loss":
|
| 1021 |
"step": 12100
|
| 1022 |
},
|
| 1023 |
{
|
| 1024 |
-
"epoch": 11.
|
| 1025 |
-
"grad_norm": 16718.0234375,
|
| 1026 |
"learning_rate": 3e-05,
|
| 1027 |
-
"loss":
|
| 1028 |
"step": 12200
|
| 1029 |
},
|
| 1030 |
{
|
| 1031 |
-
"epoch": 11.
|
| 1032 |
-
"grad_norm": 848.5704956054688,
|
| 1033 |
"learning_rate": 3e-05,
|
| 1034 |
-
"loss":
|
| 1035 |
"step": 12300
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
-
"epoch": 11.
|
| 1039 |
-
"grad_norm": 156.42295837402344,
|
| 1040 |
"learning_rate": 3e-05,
|
| 1041 |
-
"loss":
|
| 1042 |
"step": 12400
|
| 1043 |
},
|
| 1044 |
{
|
| 1045 |
-
"epoch": 11.
|
| 1046 |
-
"grad_norm": 24240020.0,
|
| 1047 |
"learning_rate": 3e-05,
|
| 1048 |
-
"loss":
|
| 1049 |
"step": 12500
|
| 1050 |
},
|
| 1051 |
{
|
| 1052 |
-
"epoch": 11.
|
| 1053 |
-
"grad_norm": 60810556.0,
|
| 1054 |
"learning_rate": 3e-05,
|
| 1055 |
-
"loss":
|
| 1056 |
"step": 12600
|
| 1057 |
},
|
| 1058 |
{
|
| 1059 |
-
"epoch": 11.
|
| 1060 |
-
"grad_norm": 4.380503717183488e+16,
|
| 1061 |
"learning_rate": 3e-05,
|
| 1062 |
-
"loss":
|
| 1063 |
"step": 12700
|
| 1064 |
},
|
| 1065 |
{
|
| 1066 |
-
"epoch": 11.
|
| 1067 |
-
"grad_norm": 79782666567680.0,
|
| 1068 |
"learning_rate": 3e-05,
|
| 1069 |
-
"loss":
|
| 1070 |
"step": 12800
|
| 1071 |
},
|
| 1072 |
{
|
| 1073 |
-
"epoch": 11.
|
| 1074 |
-
"grad_norm": 100421464.0,
|
| 1075 |
"learning_rate": 3e-05,
|
| 1076 |
-
"loss":
|
| 1077 |
"step": 12900
|
| 1078 |
},
|
| 1079 |
{
|
| 1080 |
-
"epoch": 11.
|
| 1081 |
-
"grad_norm": 335482.3125,
|
| 1082 |
"learning_rate": 3e-05,
|
| 1083 |
-
"loss":
|
| 1084 |
"step": 13000
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
"epoch": 12.0,
|
| 1088 |
-
"eval_accuracy": 0.
|
| 1089 |
-
"eval_loss":
|
| 1090 |
-
"eval_runtime":
|
| 1091 |
-
"eval_samples_per_second":
|
| 1092 |
-
"eval_steps_per_second":
|
| 1093 |
"step": 13071
|
| 1094 |
},
|
| 1095 |
{
|
| 1096 |
"epoch": 12.0,
|
| 1097 |
"eval_exact_match": 0.0,
|
| 1098 |
-
"eval_f1": 0.
|
| 1099 |
"step": 13071
|
| 1100 |
},
|
| 1101 |
{
|
| 1102 |
-
"epoch": 12.
|
| 1103 |
-
"grad_norm": 34611664.0,
|
| 1104 |
"learning_rate": 3e-05,
|
| 1105 |
-
"loss":
|
| 1106 |
"step": 13100
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
-
"epoch": 12.
|
| 1110 |
-
"grad_norm": 136696896.0,
|
| 1111 |
"learning_rate": 3e-05,
|
| 1112 |
-
"loss":
|
| 1113 |
"step": 13200
|
| 1114 |
},
|
| 1115 |
{
|
| 1116 |
-
"epoch": 12.
|
| 1117 |
-
"grad_norm": 7467604992.0,
|
| 1118 |
"learning_rate": 3e-05,
|
| 1119 |
-
"loss":
|
| 1120 |
"step": 13300
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
-
"epoch": 12.
|
| 1124 |
-
"grad_norm": 903450752.0,
|
| 1125 |
"learning_rate": 3e-05,
|
| 1126 |
-
"loss":
|
| 1127 |
"step": 13400
|
| 1128 |
},
|
| 1129 |
{
|
| 1130 |
-
"epoch": 12.
|
| 1131 |
-
"grad_norm": 389607488.0,
|
| 1132 |
"learning_rate": 3e-05,
|
| 1133 |
-
"loss":
|
| 1134 |
"step": 13500
|
| 1135 |
},
|
| 1136 |
{
|
| 1137 |
-
"epoch": 12.
|
| 1138 |
-
"grad_norm": 7033111040.0,
|
| 1139 |
"learning_rate": 3e-05,
|
| 1140 |
-
"loss":
|
| 1141 |
"step": 13600
|
| 1142 |
},
|
| 1143 |
{
|
| 1144 |
-
"epoch": 12.
|
| 1145 |
-
"grad_norm": 24849942.0,
|
| 1146 |
"learning_rate": 3e-05,
|
| 1147 |
-
"loss":
|
| 1148 |
"step": 13700
|
| 1149 |
},
|
| 1150 |
{
|
| 1151 |
-
"epoch": 12.
|
| 1152 |
-
"grad_norm": 20334586.0,
|
| 1153 |
"learning_rate": 3e-05,
|
| 1154 |
-
"loss":
|
| 1155 |
"step": 13800
|
| 1156 |
},
|
| 1157 |
{
|
| 1158 |
-
"epoch": 12.
|
| 1159 |
-
"grad_norm": 1128190848.0,
|
| 1160 |
"learning_rate": 3e-05,
|
| 1161 |
-
"loss":
|
| 1162 |
"step": 13900
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
-
"epoch": 12.
|
| 1166 |
-
"grad_norm": 26534666240.0,
|
| 1167 |
"learning_rate": 3e-05,
|
| 1168 |
-
"loss":
|
| 1169 |
"step": 14000
|
| 1170 |
},
|
| 1171 |
{
|
| 1172 |
-
"epoch": 12.
|
| 1173 |
-
"grad_norm": 1785278496768.0,
|
| 1174 |
"learning_rate": 3e-05,
|
| 1175 |
-
"loss":
|
| 1176 |
"step": 14100
|
| 1177 |
},
|
| 1178 |
{
|
| 1179 |
-
"epoch":
|
| 1180 |
-
"eval_accuracy": 0.
|
| 1181 |
-
"eval_loss":
|
| 1182 |
-
"eval_runtime":
|
| 1183 |
-
"eval_samples_per_second":
|
| 1184 |
-
"eval_steps_per_second":
|
| 1185 |
"step": 14160
|
| 1186 |
},
|
| 1187 |
{
|
| 1188 |
-
"epoch":
|
| 1189 |
"eval_exact_match": 0.0,
|
| 1190 |
-
"eval_f1": 0.
|
| 1191 |
"step": 14160
|
| 1192 |
}
|
| 1193 |
],
|
| 1194 |
"logging_steps": 100,
|
| 1195 |
"max_steps": 54450,
|
| 1196 |
-
"num_input_tokens_seen": 0,
|
| 1197 |
"num_train_epochs": 50,
|
| 1198 |
"save_steps": 500,
|
| 1199 |
-
"
|
| 1200 |
-
"TrainerControl": {
|
| 1201 |
-
"args": {
|
| 1202 |
-
"should_epoch_stop": false,
|
| 1203 |
-
"should_evaluate": false,
|
| 1204 |
-
"should_log": false,
|
| 1205 |
-
"should_save": true,
|
| 1206 |
-
"should_training_stop": false
|
| 1207 |
-
},
|
| 1208 |
-
"attributes": {}
|
| 1209 |
-
}
|
| 1210 |
-
},
|
| 1211 |
-
"total_flos": 9.769722546193695e+17,
|
| 1212 |
-
"train_batch_size": 1,
|
| 1213 |
"trial_name": null,
|
| 1214 |
"trial_params": null
|
| 1215 |
}
|
|
|
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
+
"epoch": 0.09,
|
|
|
|
| 13 |
"learning_rate": 3e-05,
|
| 14 |
+
"loss": 1.5477,
|
| 15 |
"step": 100
|
| 16 |
},
|
| 17 |
{
|
| 18 |
+
"epoch": 0.18,
|
|
|
|
| 19 |
"learning_rate": 3e-05,
|
| 20 |
+
"loss": 1.3248,
|
| 21 |
"step": 200
|
| 22 |
},
|
| 23 |
{
|
| 24 |
+
"epoch": 0.28,
|
|
|
|
| 25 |
"learning_rate": 3e-05,
|
| 26 |
+
"loss": 1.2394,
|
| 27 |
"step": 300
|
| 28 |
},
|
| 29 |
{
|
| 30 |
+
"epoch": 0.37,
|
|
|
|
| 31 |
"learning_rate": 3e-05,
|
| 32 |
+
"loss": 1.2549,
|
| 33 |
"step": 400
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 0.46,
|
|
|
|
| 37 |
"learning_rate": 3e-05,
|
| 38 |
+
"loss": 1.2163,
|
| 39 |
"step": 500
|
| 40 |
},
|
| 41 |
{
|
| 42 |
+
"epoch": 0.55,
|
|
|
|
| 43 |
"learning_rate": 3e-05,
|
| 44 |
+
"loss": 1.2202,
|
| 45 |
"step": 600
|
| 46 |
},
|
| 47 |
{
|
| 48 |
+
"epoch": 0.64,
|
|
|
|
| 49 |
"learning_rate": 3e-05,
|
| 50 |
+
"loss": 1.2099,
|
| 51 |
"step": 700
|
| 52 |
},
|
| 53 |
{
|
| 54 |
+
"epoch": 0.73,
|
|
|
|
| 55 |
"learning_rate": 3e-05,
|
| 56 |
+
"loss": 1.2213,
|
| 57 |
"step": 800
|
| 58 |
},
|
| 59 |
{
|
| 60 |
+
"epoch": 0.83,
|
|
|
|
| 61 |
"learning_rate": 3e-05,
|
| 62 |
+
"loss": 1.2203,
|
| 63 |
"step": 900
|
| 64 |
},
|
| 65 |
{
|
| 66 |
+
"epoch": 0.92,
|
|
|
|
| 67 |
"learning_rate": 3e-05,
|
| 68 |
+
"loss": 1.2166,
|
| 69 |
"step": 1000
|
| 70 |
},
|
| 71 |
{
|
| 72 |
+
"epoch": 1.0,
|
| 73 |
+
"eval_accuracy": 0.5925822784810126,
|
| 74 |
+
"eval_loss": 1.858124017715454,
|
| 75 |
+
"eval_runtime": 4.7843,
|
| 76 |
+
"eval_samples_per_second": 104.509,
|
| 77 |
+
"eval_steps_per_second": 13.168,
|
| 78 |
"step": 1089
|
| 79 |
},
|
| 80 |
{
|
| 81 |
+
"epoch": 1.0,
|
| 82 |
+
"eval_exact_match": 25.0,
|
| 83 |
+
"eval_f1": 33.90013632566266,
|
| 84 |
"step": 1089
|
| 85 |
},
|
| 86 |
{
|
| 87 |
+
"epoch": 1.01,
|
|
|
|
| 88 |
"learning_rate": 3e-05,
|
| 89 |
+
"loss": 1.2141,
|
| 90 |
"step": 1100
|
| 91 |
},
|
| 92 |
{
|
| 93 |
+
"epoch": 1.1,
|
|
|
|
| 94 |
"learning_rate": 3e-05,
|
| 95 |
+
"loss": 1.2178,
|
| 96 |
"step": 1200
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"epoch": 1.19,
|
|
|
|
| 100 |
"learning_rate": 3e-05,
|
| 101 |
+
"loss": 1.1986,
|
| 102 |
"step": 1300
|
| 103 |
},
|
| 104 |
{
|
| 105 |
+
"epoch": 1.29,
|
|
|
|
| 106 |
"learning_rate": 3e-05,
|
| 107 |
+
"loss": 1.1903,
|
| 108 |
"step": 1400
|
| 109 |
},
|
| 110 |
{
|
| 111 |
+
"epoch": 1.38,
|
|
|
|
| 112 |
"learning_rate": 3e-05,
|
| 113 |
+
"loss": 1.1925,
|
| 114 |
"step": 1500
|
| 115 |
},
|
| 116 |
{
|
| 117 |
+
"epoch": 1.47,
|
|
|
|
| 118 |
"learning_rate": 3e-05,
|
| 119 |
+
"loss": 1.1954,
|
| 120 |
"step": 1600
|
| 121 |
},
|
| 122 |
{
|
| 123 |
+
"epoch": 1.56,
|
|
|
|
| 124 |
"learning_rate": 3e-05,
|
| 125 |
+
"loss": 1.1859,
|
| 126 |
"step": 1700
|
| 127 |
},
|
| 128 |
{
|
| 129 |
+
"epoch": 1.65,
|
|
|
|
| 130 |
"learning_rate": 3e-05,
|
| 131 |
+
"loss": 1.1979,
|
| 132 |
"step": 1800
|
| 133 |
},
|
| 134 |
{
|
| 135 |
+
"epoch": 1.74,
|
|
|
|
| 136 |
"learning_rate": 3e-05,
|
| 137 |
+
"loss": 1.201,
|
| 138 |
"step": 1900
|
| 139 |
},
|
| 140 |
{
|
| 141 |
+
"epoch": 1.84,
|
|
|
|
| 142 |
"learning_rate": 3e-05,
|
| 143 |
+
"loss": 1.1871,
|
| 144 |
"step": 2000
|
| 145 |
},
|
| 146 |
{
|
| 147 |
+
"epoch": 1.93,
|
|
|
|
| 148 |
"learning_rate": 3e-05,
|
| 149 |
+
"loss": 1.1949,
|
| 150 |
"step": 2100
|
| 151 |
},
|
| 152 |
{
|
| 153 |
+
"epoch": 2.0,
|
| 154 |
+
"eval_accuracy": 0.5960506329113924,
|
| 155 |
+
"eval_loss": 1.834545373916626,
|
| 156 |
+
"eval_runtime": 4.5511,
|
| 157 |
+
"eval_samples_per_second": 109.863,
|
| 158 |
+
"eval_steps_per_second": 13.843,
|
| 159 |
"step": 2178
|
| 160 |
},
|
| 161 |
{
|
| 162 |
+
"epoch": 2.0,
|
| 163 |
+
"eval_exact_match": 25.2,
|
| 164 |
+
"eval_f1": 34.41373827926461,
|
| 165 |
"step": 2178
|
| 166 |
},
|
| 167 |
{
|
| 168 |
+
"epoch": 2.02,
|
|
|
|
| 169 |
"learning_rate": 3e-05,
|
| 170 |
+
"loss": 1.1775,
|
| 171 |
"step": 2200
|
| 172 |
},
|
| 173 |
{
|
| 174 |
+
"epoch": 2.11,
|
|
|
|
| 175 |
"learning_rate": 3e-05,
|
| 176 |
+
"loss": 1.1579,
|
| 177 |
"step": 2300
|
| 178 |
},
|
| 179 |
{
|
| 180 |
+
"epoch": 2.2,
|
|
|
|
| 181 |
"learning_rate": 3e-05,
|
| 182 |
+
"loss": 1.1678,
|
| 183 |
"step": 2400
|
| 184 |
},
|
| 185 |
{
|
| 186 |
+
"epoch": 2.3,
|
|
|
|
| 187 |
"learning_rate": 3e-05,
|
| 188 |
+
"loss": 1.1758,
|
| 189 |
"step": 2500
|
| 190 |
},
|
| 191 |
{
|
| 192 |
+
"epoch": 2.39,
|
|
|
|
| 193 |
"learning_rate": 3e-05,
|
| 194 |
+
"loss": 1.1374,
|
| 195 |
"step": 2600
|
| 196 |
},
|
| 197 |
{
|
| 198 |
+
"epoch": 2.48,
|
|
|
|
| 199 |
"learning_rate": 3e-05,
|
| 200 |
+
"loss": 1.16,
|
| 201 |
"step": 2700
|
| 202 |
},
|
| 203 |
{
|
| 204 |
+
"epoch": 2.57,
|
|
|
|
| 205 |
"learning_rate": 3e-05,
|
| 206 |
+
"loss": 1.1647,
|
| 207 |
"step": 2800
|
| 208 |
},
|
| 209 |
{
|
| 210 |
+
"epoch": 2.66,
|
|
|
|
| 211 |
"learning_rate": 3e-05,
|
| 212 |
+
"loss": 1.1579,
|
| 213 |
"step": 2900
|
| 214 |
},
|
| 215 |
{
|
| 216 |
+
"epoch": 2.75,
|
|
|
|
| 217 |
"learning_rate": 3e-05,
|
| 218 |
+
"loss": 1.1647,
|
| 219 |
"step": 3000
|
| 220 |
},
|
| 221 |
{
|
| 222 |
+
"epoch": 2.85,
|
|
|
|
| 223 |
"learning_rate": 3e-05,
|
| 224 |
+
"loss": 1.1581,
|
| 225 |
"step": 3100
|
| 226 |
},
|
| 227 |
{
|
| 228 |
+
"epoch": 2.94,
|
|
|
|
| 229 |
"learning_rate": 3e-05,
|
| 230 |
+
"loss": 1.1542,
|
| 231 |
"step": 3200
|
| 232 |
},
|
| 233 |
{
|
| 234 |
+
"epoch": 3.0,
|
| 235 |
+
"eval_accuracy": 0.596379746835443,
|
| 236 |
+
"eval_loss": 1.8205524682998657,
|
| 237 |
+
"eval_runtime": 4.5724,
|
| 238 |
+
"eval_samples_per_second": 109.352,
|
| 239 |
+
"eval_steps_per_second": 13.778,
|
| 240 |
"step": 3267
|
| 241 |
},
|
| 242 |
{
|
| 243 |
+
"epoch": 3.0,
|
| 244 |
+
"eval_exact_match": 24.6,
|
| 245 |
+
"eval_f1": 34.42903485403487,
|
| 246 |
"step": 3267
|
| 247 |
},
|
| 248 |
{
|
| 249 |
+
"epoch": 3.03,
|
|
|
|
| 250 |
"learning_rate": 3e-05,
|
| 251 |
+
"loss": 1.1336,
|
| 252 |
"step": 3300
|
| 253 |
},
|
| 254 |
{
|
| 255 |
+
"epoch": 3.12,
|
|
|
|
| 256 |
"learning_rate": 3e-05,
|
| 257 |
+
"loss": 1.1112,
|
| 258 |
"step": 3400
|
| 259 |
},
|
| 260 |
{
|
| 261 |
+
"epoch": 3.21,
|
|
|
|
| 262 |
"learning_rate": 3e-05,
|
| 263 |
+
"loss": 1.123,
|
| 264 |
"step": 3500
|
| 265 |
},
|
| 266 |
{
|
| 267 |
+
"epoch": 3.31,
|
|
|
|
| 268 |
"learning_rate": 3e-05,
|
| 269 |
+
"loss": 1.1278,
|
| 270 |
"step": 3600
|
| 271 |
},
|
| 272 |
{
|
| 273 |
+
"epoch": 3.4,
|
|
|
|
| 274 |
"learning_rate": 3e-05,
|
| 275 |
+
"loss": 1.1226,
|
| 276 |
"step": 3700
|
| 277 |
},
|
| 278 |
{
|
| 279 |
+
"epoch": 3.49,
|
|
|
|
| 280 |
"learning_rate": 3e-05,
|
| 281 |
+
"loss": 1.1132,
|
| 282 |
"step": 3800
|
| 283 |
},
|
| 284 |
{
|
| 285 |
+
"epoch": 3.58,
|
|
|
|
| 286 |
"learning_rate": 3e-05,
|
| 287 |
+
"loss": 1.1075,
|
| 288 |
"step": 3900
|
| 289 |
},
|
| 290 |
{
|
| 291 |
+
"epoch": 3.67,
|
|
|
|
| 292 |
"learning_rate": 3e-05,
|
| 293 |
+
"loss": 1.128,
|
| 294 |
"step": 4000
|
| 295 |
},
|
| 296 |
{
|
| 297 |
+
"epoch": 3.76,
|
|
|
|
| 298 |
"learning_rate": 3e-05,
|
| 299 |
+
"loss": 1.1182,
|
| 300 |
"step": 4100
|
| 301 |
},
|
| 302 |
{
|
| 303 |
+
"epoch": 3.86,
|
|
|
|
| 304 |
"learning_rate": 3e-05,
|
| 305 |
+
"loss": 1.1288,
|
| 306 |
"step": 4200
|
| 307 |
},
|
| 308 |
{
|
| 309 |
+
"epoch": 3.95,
|
|
|
|
| 310 |
"learning_rate": 3e-05,
|
| 311 |
+
"loss": 1.1236,
|
| 312 |
"step": 4300
|
| 313 |
},
|
| 314 |
{
|
| 315 |
"epoch": 4.0,
|
| 316 |
+
"eval_accuracy": 0.600379746835443,
|
| 317 |
+
"eval_loss": 1.822967290878296,
|
| 318 |
+
"eval_runtime": 4.5641,
|
| 319 |
+
"eval_samples_per_second": 109.55,
|
| 320 |
+
"eval_steps_per_second": 13.803,
|
| 321 |
"step": 4357
|
| 322 |
},
|
| 323 |
{
|
| 324 |
"epoch": 4.0,
|
| 325 |
+
"eval_exact_match": 23.0,
|
| 326 |
+
"eval_f1": 32.55568709068711,
|
| 327 |
"step": 4357
|
| 328 |
},
|
| 329 |
{
|
| 330 |
+
"epoch": 4.04,
|
|
|
|
| 331 |
"learning_rate": 3e-05,
|
| 332 |
+
"loss": 1.1034,
|
| 333 |
"step": 4400
|
| 334 |
},
|
| 335 |
{
|
| 336 |
+
"epoch": 4.13,
|
|
|
|
| 337 |
"learning_rate": 3e-05,
|
| 338 |
+
"loss": 1.0822,
|
| 339 |
"step": 4500
|
| 340 |
},
|
| 341 |
{
|
| 342 |
+
"epoch": 4.22,
|
|
|
|
| 343 |
"learning_rate": 3e-05,
|
| 344 |
+
"loss": 1.0869,
|
| 345 |
"step": 4600
|
| 346 |
},
|
| 347 |
{
|
| 348 |
+
"epoch": 4.31,
|
|
|
|
| 349 |
"learning_rate": 3e-05,
|
| 350 |
+
"loss": 1.0813,
|
| 351 |
"step": 4700
|
| 352 |
},
|
| 353 |
{
|
| 354 |
+
"epoch": 4.41,
|
|
|
|
| 355 |
"learning_rate": 3e-05,
|
| 356 |
+
"loss": 1.081,
|
| 357 |
"step": 4800
|
| 358 |
},
|
| 359 |
{
|
| 360 |
+
"epoch": 4.5,
|
|
|
|
| 361 |
"learning_rate": 3e-05,
|
| 362 |
+
"loss": 1.1065,
|
| 363 |
"step": 4900
|
| 364 |
},
|
| 365 |
{
|
| 366 |
+
"epoch": 4.59,
|
|
|
|
| 367 |
"learning_rate": 3e-05,
|
| 368 |
+
"loss": 1.1018,
|
| 369 |
"step": 5000
|
| 370 |
},
|
| 371 |
{
|
| 372 |
+
"epoch": 4.68,
|
|
|
|
| 373 |
"learning_rate": 3e-05,
|
| 374 |
+
"loss": 1.0737,
|
| 375 |
"step": 5100
|
| 376 |
},
|
| 377 |
{
|
| 378 |
+
"epoch": 4.77,
|
|
|
|
| 379 |
"learning_rate": 3e-05,
|
| 380 |
+
"loss": 1.0823,
|
| 381 |
"step": 5200
|
| 382 |
},
|
| 383 |
{
|
| 384 |
+
"epoch": 4.87,
|
|
|
|
| 385 |
"learning_rate": 3e-05,
|
| 386 |
+
"loss": 1.0916,
|
| 387 |
"step": 5300
|
| 388 |
},
|
| 389 |
{
|
| 390 |
+
"epoch": 4.96,
|
|
|
|
| 391 |
"learning_rate": 3e-05,
|
| 392 |
+
"loss": 1.0989,
|
| 393 |
"step": 5400
|
| 394 |
},
|
| 395 |
{
|
| 396 |
+
"epoch": 5.0,
|
| 397 |
+
"eval_accuracy": 0.6035696202531645,
|
| 398 |
+
"eval_loss": 1.8370839357376099,
|
| 399 |
+
"eval_runtime": 4.3939,
|
| 400 |
+
"eval_samples_per_second": 113.795,
|
| 401 |
+
"eval_steps_per_second": 14.338,
|
| 402 |
"step": 5446
|
| 403 |
},
|
| 404 |
{
|
| 405 |
+
"epoch": 5.0,
|
| 406 |
+
"eval_exact_match": 23.8,
|
| 407 |
+
"eval_f1": 33.387894882894905,
|
| 408 |
"step": 5446
|
| 409 |
},
|
| 410 |
{
|
| 411 |
+
"epoch": 5.05,
|
|
|
|
| 412 |
"learning_rate": 3e-05,
|
| 413 |
+
"loss": 1.0542,
|
| 414 |
"step": 5500
|
| 415 |
},
|
| 416 |
{
|
| 417 |
+
"epoch": 5.14,
|
|
|
|
| 418 |
"learning_rate": 3e-05,
|
| 419 |
+
"loss": 1.0188,
|
| 420 |
"step": 5600
|
| 421 |
},
|
| 422 |
{
|
| 423 |
+
"epoch": 5.23,
|
|
|
|
| 424 |
"learning_rate": 3e-05,
|
| 425 |
+
"loss": 1.0364,
|
| 426 |
"step": 5700
|
| 427 |
},
|
| 428 |
{
|
| 429 |
+
"epoch": 5.32,
|
|
|
|
| 430 |
"learning_rate": 3e-05,
|
| 431 |
+
"loss": 1.0497,
|
| 432 |
"step": 5800
|
| 433 |
},
|
| 434 |
{
|
| 435 |
+
"epoch": 5.42,
|
|
|
|
| 436 |
"learning_rate": 3e-05,
|
| 437 |
+
"loss": 1.0561,
|
| 438 |
"step": 5900
|
| 439 |
},
|
| 440 |
{
|
| 441 |
+
"epoch": 5.51,
|
|
|
|
| 442 |
"learning_rate": 3e-05,
|
| 443 |
+
"loss": 1.0538,
|
| 444 |
"step": 6000
|
| 445 |
},
|
| 446 |
{
|
| 447 |
+
"epoch": 5.6,
|
|
|
|
| 448 |
"learning_rate": 3e-05,
|
| 449 |
+
"loss": 1.0574,
|
| 450 |
"step": 6100
|
| 451 |
},
|
| 452 |
{
|
| 453 |
+
"epoch": 5.69,
|
|
|
|
| 454 |
"learning_rate": 3e-05,
|
| 455 |
+
"loss": 1.0468,
|
| 456 |
"step": 6200
|
| 457 |
},
|
| 458 |
{
|
| 459 |
+
"epoch": 5.78,
|
|
|
|
| 460 |
"learning_rate": 3e-05,
|
| 461 |
+
"loss": 1.0524,
|
| 462 |
"step": 6300
|
| 463 |
},
|
| 464 |
{
|
| 465 |
+
"epoch": 5.88,
|
|
|
|
| 466 |
"learning_rate": 3e-05,
|
| 467 |
+
"loss": 1.0637,
|
| 468 |
"step": 6400
|
| 469 |
},
|
| 470 |
{
|
| 471 |
+
"epoch": 5.97,
|
|
|
|
| 472 |
"learning_rate": 3e-05,
|
| 473 |
+
"loss": 1.0543,
|
| 474 |
"step": 6500
|
| 475 |
},
|
| 476 |
{
|
| 477 |
+
"epoch": 6.0,
|
| 478 |
+
"eval_accuracy": 0.6021518987341772,
|
| 479 |
+
"eval_loss": 1.8654963970184326,
|
| 480 |
+
"eval_runtime": 4.5885,
|
| 481 |
+
"eval_samples_per_second": 108.969,
|
| 482 |
+
"eval_steps_per_second": 13.73,
|
| 483 |
"step": 6535
|
| 484 |
},
|
| 485 |
{
|
| 486 |
+
"epoch": 6.0,
|
| 487 |
+
"eval_exact_match": 23.4,
|
| 488 |
+
"eval_f1": 31.89286435786437,
|
| 489 |
"step": 6535
|
| 490 |
},
|
| 491 |
{
|
| 492 |
+
"epoch": 6.06,
|
|
|
|
| 493 |
"learning_rate": 3e-05,
|
| 494 |
+
"loss": 1.0225,
|
| 495 |
"step": 6600
|
| 496 |
},
|
| 497 |
{
|
| 498 |
+
"epoch": 6.15,
|
|
|
|
| 499 |
"learning_rate": 3e-05,
|
| 500 |
+
"loss": 1.0118,
|
| 501 |
"step": 6700
|
| 502 |
},
|
| 503 |
{
|
| 504 |
+
"epoch": 6.24,
|
|
|
|
| 505 |
"learning_rate": 3e-05,
|
| 506 |
+
"loss": 1.0165,
|
| 507 |
"step": 6800
|
| 508 |
},
|
| 509 |
{
|
| 510 |
+
"epoch": 6.33,
|
|
|
|
| 511 |
"learning_rate": 3e-05,
|
| 512 |
+
"loss": 1.0042,
|
| 513 |
"step": 6900
|
| 514 |
},
|
| 515 |
{
|
| 516 |
+
"epoch": 6.43,
|
|
|
|
| 517 |
"learning_rate": 3e-05,
|
| 518 |
+
"loss": 1.0064,
|
| 519 |
"step": 7000
|
| 520 |
},
|
| 521 |
{
|
| 522 |
+
"epoch": 6.52,
|
|
|
|
| 523 |
"learning_rate": 3e-05,
|
| 524 |
+
"loss": 1.0245,
|
| 525 |
"step": 7100
|
| 526 |
},
|
| 527 |
{
|
| 528 |
+
"epoch": 6.61,
|
|
|
|
| 529 |
"learning_rate": 3e-05,
|
| 530 |
+
"loss": 1.0091,
|
| 531 |
"step": 7200
|
| 532 |
},
|
| 533 |
{
|
| 534 |
+
"epoch": 6.7,
|
|
|
|
| 535 |
"learning_rate": 3e-05,
|
| 536 |
+
"loss": 1.0259,
|
| 537 |
"step": 7300
|
| 538 |
},
|
| 539 |
{
|
| 540 |
+
"epoch": 6.79,
|
|
|
|
| 541 |
"learning_rate": 3e-05,
|
| 542 |
+
"loss": 1.0,
|
| 543 |
"step": 7400
|
| 544 |
},
|
| 545 |
{
|
| 546 |
+
"epoch": 6.89,
|
|
|
|
| 547 |
"learning_rate": 3e-05,
|
| 548 |
+
"loss": 0.995,
|
| 549 |
"step": 7500
|
| 550 |
},
|
| 551 |
{
|
| 552 |
+
"epoch": 6.98,
|
|
|
|
| 553 |
"learning_rate": 3e-05,
|
| 554 |
+
"loss": 1.0139,
|
| 555 |
"step": 7600
|
| 556 |
},
|
| 557 |
{
|
| 558 |
+
"epoch": 7.0,
|
| 559 |
+
"eval_accuracy": 0.592886075949367,
|
| 560 |
+
"eval_loss": 1.927990198135376,
|
| 561 |
+
"eval_runtime": 4.6988,
|
| 562 |
+
"eval_samples_per_second": 106.411,
|
| 563 |
+
"eval_steps_per_second": 13.408,
|
| 564 |
"step": 7624
|
| 565 |
},
|
| 566 |
{
|
| 567 |
+
"epoch": 7.0,
|
| 568 |
+
"eval_exact_match": 23.0,
|
| 569 |
+
"eval_f1": 32.51321067821068,
|
| 570 |
"step": 7624
|
| 571 |
},
|
| 572 |
{
|
| 573 |
+
"epoch": 7.07,
|
|
|
|
| 574 |
"learning_rate": 3e-05,
|
| 575 |
+
"loss": 0.9788,
|
| 576 |
"step": 7700
|
| 577 |
},
|
| 578 |
{
|
| 579 |
+
"epoch": 7.16,
|
|
|
|
| 580 |
"learning_rate": 3e-05,
|
| 581 |
+
"loss": 0.9597,
|
| 582 |
"step": 7800
|
| 583 |
},
|
| 584 |
{
|
| 585 |
+
"epoch": 7.25,
|
|
|
|
| 586 |
"learning_rate": 3e-05,
|
| 587 |
+
"loss": 0.9623,
|
| 588 |
"step": 7900
|
| 589 |
},
|
| 590 |
{
|
| 591 |
+
"epoch": 7.34,
|
|
|
|
| 592 |
"learning_rate": 3e-05,
|
| 593 |
+
"loss": 0.9815,
|
| 594 |
"step": 8000
|
| 595 |
},
|
| 596 |
{
|
| 597 |
+
"epoch": 7.44,
|
|
|
|
| 598 |
"learning_rate": 3e-05,
|
| 599 |
+
"loss": 0.9831,
|
| 600 |
"step": 8100
|
| 601 |
},
|
| 602 |
{
|
| 603 |
+
"epoch": 7.53,
|
|
|
|
| 604 |
"learning_rate": 3e-05,
|
| 605 |
+
"loss": 0.9762,
|
| 606 |
"step": 8200
|
| 607 |
},
|
| 608 |
{
|
| 609 |
+
"epoch": 7.62,
|
|
|
|
| 610 |
"learning_rate": 3e-05,
|
| 611 |
+
"loss": 0.9769,
|
| 612 |
"step": 8300
|
| 613 |
},
|
| 614 |
{
|
| 615 |
+
"epoch": 7.71,
|
|
|
|
| 616 |
"learning_rate": 3e-05,
|
| 617 |
+
"loss": 0.9882,
|
| 618 |
"step": 8400
|
| 619 |
},
|
| 620 |
{
|
| 621 |
+
"epoch": 7.8,
|
|
|
|
| 622 |
"learning_rate": 3e-05,
|
| 623 |
+
"loss": 0.9736,
|
| 624 |
"step": 8500
|
| 625 |
},
|
| 626 |
{
|
| 627 |
+
"epoch": 7.9,
|
|
|
|
| 628 |
"learning_rate": 3e-05,
|
| 629 |
+
"loss": 0.9764,
|
| 630 |
"step": 8600
|
| 631 |
},
|
| 632 |
{
|
| 633 |
+
"epoch": 7.99,
|
|
|
|
| 634 |
"learning_rate": 3e-05,
|
| 635 |
+
"loss": 0.9764,
|
| 636 |
"step": 8700
|
| 637 |
},
|
| 638 |
{
|
| 639 |
"epoch": 8.0,
|
| 640 |
+
"eval_accuracy": 0.5912658227848101,
|
| 641 |
+
"eval_loss": 1.991403579711914,
|
| 642 |
+
"eval_runtime": 4.6999,
|
| 643 |
+
"eval_samples_per_second": 106.385,
|
| 644 |
+
"eval_steps_per_second": 13.404,
|
| 645 |
"step": 8714
|
| 646 |
},
|
| 647 |
{
|
| 648 |
"epoch": 8.0,
|
| 649 |
+
"eval_exact_match": 20.8,
|
| 650 |
+
"eval_f1": 30.54087925962926,
|
| 651 |
"step": 8714
|
| 652 |
},
|
| 653 |
{
|
| 654 |
+
"epoch": 8.08,
|
|
|
|
| 655 |
"learning_rate": 3e-05,
|
| 656 |
+
"loss": 0.9509,
|
| 657 |
"step": 8800
|
| 658 |
},
|
| 659 |
{
|
| 660 |
+
"epoch": 8.17,
|
|
|
|
| 661 |
"learning_rate": 3e-05,
|
| 662 |
+
"loss": 0.9319,
|
| 663 |
"step": 8900
|
| 664 |
},
|
| 665 |
{
|
| 666 |
+
"epoch": 8.26,
|
|
|
|
| 667 |
"learning_rate": 3e-05,
|
| 668 |
+
"loss": 0.9254,
|
| 669 |
"step": 9000
|
| 670 |
},
|
| 671 |
{
|
| 672 |
+
"epoch": 8.35,
|
|
|
|
| 673 |
"learning_rate": 3e-05,
|
| 674 |
+
"loss": 0.9396,
|
| 675 |
"step": 9100
|
| 676 |
},
|
| 677 |
{
|
| 678 |
+
"epoch": 8.45,
|
|
|
|
| 679 |
"learning_rate": 3e-05,
|
| 680 |
+
"loss": 0.9439,
|
| 681 |
"step": 9200
|
| 682 |
},
|
| 683 |
{
|
| 684 |
+
"epoch": 8.54,
|
|
|
|
| 685 |
"learning_rate": 3e-05,
|
| 686 |
+
"loss": 0.9434,
|
| 687 |
"step": 9300
|
| 688 |
},
|
| 689 |
{
|
| 690 |
+
"epoch": 8.63,
|
|
|
|
| 691 |
"learning_rate": 3e-05,
|
| 692 |
+
"loss": 0.9283,
|
| 693 |
"step": 9400
|
| 694 |
},
|
| 695 |
{
|
| 696 |
+
"epoch": 8.72,
|
|
|
|
| 697 |
"learning_rate": 3e-05,
|
| 698 |
+
"loss": 0.9409,
|
| 699 |
"step": 9500
|
| 700 |
},
|
| 701 |
{
|
| 702 |
+
"epoch": 8.81,
|
|
|
|
| 703 |
"learning_rate": 3e-05,
|
| 704 |
+
"loss": 0.9474,
|
| 705 |
"step": 9600
|
| 706 |
},
|
| 707 |
{
|
| 708 |
+
"epoch": 8.91,
|
|
|
|
| 709 |
"learning_rate": 3e-05,
|
| 710 |
+
"loss": 0.9538,
|
| 711 |
"step": 9700
|
| 712 |
},
|
| 713 |
{
|
| 714 |
+
"epoch": 9.0,
|
|
|
|
| 715 |
"learning_rate": 3e-05,
|
| 716 |
+
"loss": 0.9351,
|
| 717 |
"step": 9800
|
| 718 |
},
|
| 719 |
{
|
| 720 |
+
"epoch": 9.0,
|
| 721 |
+
"eval_accuracy": 0.5909367088607594,
|
| 722 |
+
"eval_loss": 2.0564663410186768,
|
| 723 |
+
"eval_runtime": 4.8989,
|
| 724 |
+
"eval_samples_per_second": 102.064,
|
| 725 |
+
"eval_steps_per_second": 12.86,
|
| 726 |
"step": 9803
|
| 727 |
},
|
| 728 |
{
|
| 729 |
+
"epoch": 9.0,
|
| 730 |
+
"eval_exact_match": 20.2,
|
| 731 |
+
"eval_f1": 29.28648074148075,
|
| 732 |
"step": 9803
|
| 733 |
},
|
| 734 |
{
|
| 735 |
+
"epoch": 9.09,
|
|
|
|
| 736 |
"learning_rate": 3e-05,
|
| 737 |
+
"loss": 0.8896,
|
| 738 |
"step": 9900
|
| 739 |
},
|
| 740 |
{
|
| 741 |
+
"epoch": 9.18,
|
|
|
|
| 742 |
"learning_rate": 3e-05,
|
| 743 |
+
"loss": 0.8923,
|
| 744 |
"step": 10000
|
| 745 |
},
|
| 746 |
{
|
| 747 |
+
"epoch": 9.27,
|
|
|
|
| 748 |
"learning_rate": 3e-05,
|
| 749 |
+
"loss": 0.9074,
|
| 750 |
"step": 10100
|
| 751 |
},
|
| 752 |
{
|
| 753 |
+
"epoch": 9.36,
|
|
|
|
| 754 |
"learning_rate": 3e-05,
|
| 755 |
+
"loss": 0.905,
|
| 756 |
"step": 10200
|
| 757 |
},
|
| 758 |
{
|
| 759 |
+
"epoch": 9.46,
|
|
|
|
| 760 |
"learning_rate": 3e-05,
|
| 761 |
+
"loss": 0.8954,
|
| 762 |
"step": 10300
|
| 763 |
},
|
| 764 |
{
|
| 765 |
+
"epoch": 9.55,
|
|
|
|
| 766 |
"learning_rate": 3e-05,
|
| 767 |
+
"loss": 0.8953,
|
| 768 |
"step": 10400
|
| 769 |
},
|
| 770 |
{
|
| 771 |
+
"epoch": 9.64,
|
|
|
|
| 772 |
"learning_rate": 3e-05,
|
| 773 |
+
"loss": 0.8943,
|
| 774 |
"step": 10500
|
| 775 |
},
|
| 776 |
{
|
| 777 |
+
"epoch": 9.73,
|
|
|
|
| 778 |
"learning_rate": 3e-05,
|
| 779 |
+
"loss": 0.9173,
|
| 780 |
"step": 10600
|
| 781 |
},
|
| 782 |
{
|
| 783 |
+
"epoch": 9.82,
|
|
|
|
| 784 |
"learning_rate": 3e-05,
|
| 785 |
+
"loss": 0.9148,
|
| 786 |
"step": 10700
|
| 787 |
},
|
| 788 |
{
|
| 789 |
+
"epoch": 9.92,
|
|
|
|
| 790 |
"learning_rate": 3e-05,
|
| 791 |
+
"loss": 0.9177,
|
| 792 |
"step": 10800
|
| 793 |
},
|
| 794 |
{
|
| 795 |
+
"epoch": 10.0,
|
| 796 |
+
"eval_accuracy": 0.5891898734177216,
|
| 797 |
+
"eval_loss": 2.124812126159668,
|
| 798 |
+
"eval_runtime": 4.5237,
|
| 799 |
+
"eval_samples_per_second": 110.528,
|
| 800 |
+
"eval_steps_per_second": 13.927,
|
| 801 |
"step": 10892
|
| 802 |
},
|
| 803 |
{
|
| 804 |
+
"epoch": 10.0,
|
| 805 |
"eval_exact_match": 0.0,
|
| 806 |
+
"eval_f1": 1.653482807812982,
|
| 807 |
"step": 10892
|
| 808 |
},
|
| 809 |
{
|
| 810 |
+
"epoch": 10.01,
|
|
|
|
| 811 |
"learning_rate": 3e-05,
|
| 812 |
+
"loss": 0.9157,
|
| 813 |
"step": 10900
|
| 814 |
},
|
| 815 |
{
|
| 816 |
+
"epoch": 10.1,
|
|
|
|
| 817 |
"learning_rate": 3e-05,
|
| 818 |
+
"loss": 0.8335,
|
| 819 |
"step": 11000
|
| 820 |
},
|
| 821 |
{
|
| 822 |
+
"epoch": 10.19,
|
|
|
|
| 823 |
"learning_rate": 3e-05,
|
| 824 |
+
"loss": 0.8485,
|
| 825 |
"step": 11100
|
| 826 |
},
|
| 827 |
{
|
| 828 |
+
"epoch": 10.28,
|
|
|
|
| 829 |
"learning_rate": 3e-05,
|
| 830 |
+
"loss": 0.8712,
|
| 831 |
"step": 11200
|
| 832 |
},
|
| 833 |
{
|
| 834 |
+
"epoch": 10.37,
|
|
|
|
| 835 |
"learning_rate": 3e-05,
|
| 836 |
+
"loss": 0.869,
|
| 837 |
"step": 11300
|
| 838 |
},
|
| 839 |
{
|
| 840 |
+
"epoch": 10.47,
|
|
|
|
| 841 |
"learning_rate": 3e-05,
|
| 842 |
+
"loss": 0.8655,
|
| 843 |
"step": 11400
|
| 844 |
},
|
| 845 |
{
|
| 846 |
+
"epoch": 10.56,
|
|
|
|
| 847 |
"learning_rate": 3e-05,
|
| 848 |
+
"loss": 0.8868,
|
| 849 |
"step": 11500
|
| 850 |
},
|
| 851 |
{
|
| 852 |
+
"epoch": 10.65,
|
|
|
|
| 853 |
"learning_rate": 3e-05,
|
| 854 |
+
"loss": 0.8775,
|
| 855 |
"step": 11600
|
| 856 |
},
|
| 857 |
{
|
| 858 |
+
"epoch": 10.74,
|
|
|
|
| 859 |
"learning_rate": 3e-05,
|
| 860 |
+
"loss": 0.8861,
|
| 861 |
"step": 11700
|
| 862 |
},
|
| 863 |
{
|
| 864 |
+
"epoch": 10.83,
|
|
|
|
| 865 |
"learning_rate": 3e-05,
|
| 866 |
+
"loss": 0.892,
|
| 867 |
"step": 11800
|
| 868 |
},
|
| 869 |
{
|
| 870 |
+
"epoch": 10.92,
|
|
|
|
| 871 |
"learning_rate": 3e-05,
|
| 872 |
+
"loss": 0.8872,
|
| 873 |
"step": 11900
|
| 874 |
},
|
| 875 |
{
|
| 876 |
+
"epoch": 11.0,
|
| 877 |
+
"eval_accuracy": 0.5874683544303797,
|
| 878 |
+
"eval_loss": 2.2181763648986816,
|
| 879 |
+
"eval_runtime": 4.6178,
|
| 880 |
+
"eval_samples_per_second": 108.277,
|
| 881 |
+
"eval_steps_per_second": 13.643,
|
| 882 |
"step": 11981
|
| 883 |
},
|
| 884 |
{
|
| 885 |
+
"epoch": 11.0,
|
| 886 |
"eval_exact_match": 0.0,
|
| 887 |
+
"eval_f1": 0.014945652173913042,
|
| 888 |
"step": 11981
|
| 889 |
},
|
| 890 |
{
|
| 891 |
+
"epoch": 11.02,
|
|
|
|
| 892 |
"learning_rate": 3e-05,
|
| 893 |
+
"loss": 0.8808,
|
| 894 |
"step": 12000
|
| 895 |
},
|
| 896 |
{
|
| 897 |
+
"epoch": 11.11,
|
|
|
|
| 898 |
"learning_rate": 3e-05,
|
| 899 |
+
"loss": 0.8145,
|
| 900 |
"step": 12100
|
| 901 |
},
|
| 902 |
{
|
| 903 |
+
"epoch": 11.2,
|
|
|
|
| 904 |
"learning_rate": 3e-05,
|
| 905 |
+
"loss": 0.8301,
|
| 906 |
"step": 12200
|
| 907 |
},
|
| 908 |
{
|
| 909 |
+
"epoch": 11.29,
|
|
|
|
| 910 |
"learning_rate": 3e-05,
|
| 911 |
+
"loss": 0.8281,
|
| 912 |
"step": 12300
|
| 913 |
},
|
| 914 |
{
|
| 915 |
+
"epoch": 11.38,
|
|
|
|
| 916 |
"learning_rate": 3e-05,
|
| 917 |
+
"loss": 0.8464,
|
| 918 |
"step": 12400
|
| 919 |
},
|
| 920 |
{
|
| 921 |
+
"epoch": 11.48,
|
|
|
|
| 922 |
"learning_rate": 3e-05,
|
| 923 |
+
"loss": 0.8547,
|
| 924 |
"step": 12500
|
| 925 |
},
|
| 926 |
{
|
| 927 |
+
"epoch": 11.57,
|
|
|
|
| 928 |
"learning_rate": 3e-05,
|
| 929 |
+
"loss": 0.8424,
|
| 930 |
"step": 12600
|
| 931 |
},
|
| 932 |
{
|
| 933 |
+
"epoch": 11.66,
|
|
|
|
| 934 |
"learning_rate": 3e-05,
|
| 935 |
+
"loss": 0.8452,
|
| 936 |
"step": 12700
|
| 937 |
},
|
| 938 |
{
|
| 939 |
+
"epoch": 11.75,
|
|
|
|
| 940 |
"learning_rate": 3e-05,
|
| 941 |
+
"loss": 0.8528,
|
| 942 |
"step": 12800
|
| 943 |
},
|
| 944 |
{
|
| 945 |
+
"epoch": 11.84,
|
|
|
|
| 946 |
"learning_rate": 3e-05,
|
| 947 |
+
"loss": 0.862,
|
| 948 |
"step": 12900
|
| 949 |
},
|
| 950 |
{
|
| 951 |
+
"epoch": 11.93,
|
|
|
|
| 952 |
"learning_rate": 3e-05,
|
| 953 |
+
"loss": 0.8458,
|
| 954 |
"step": 13000
|
| 955 |
},
|
| 956 |
{
|
| 957 |
"epoch": 12.0,
|
| 958 |
+
"eval_accuracy": 0.5862784810126582,
|
| 959 |
+
"eval_loss": 2.286332130432129,
|
| 960 |
+
"eval_runtime": 4.5481,
|
| 961 |
+
"eval_samples_per_second": 109.935,
|
| 962 |
+
"eval_steps_per_second": 13.852,
|
| 963 |
"step": 13071
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 12.0,
|
| 967 |
"eval_exact_match": 0.0,
|
| 968 |
+
"eval_f1": 0.05640597466324206,
|
| 969 |
"step": 13071
|
| 970 |
},
|
| 971 |
{
|
| 972 |
+
"epoch": 12.03,
|
|
|
|
| 973 |
"learning_rate": 3e-05,
|
| 974 |
+
"loss": 0.8407,
|
| 975 |
"step": 13100
|
| 976 |
},
|
| 977 |
{
|
| 978 |
+
"epoch": 12.12,
|
|
|
|
| 979 |
"learning_rate": 3e-05,
|
| 980 |
+
"loss": 0.8103,
|
| 981 |
"step": 13200
|
| 982 |
},
|
| 983 |
{
|
| 984 |
+
"epoch": 12.21,
|
|
|
|
| 985 |
"learning_rate": 3e-05,
|
| 986 |
+
"loss": 0.8044,
|
| 987 |
"step": 13300
|
| 988 |
},
|
| 989 |
{
|
| 990 |
+
"epoch": 12.3,
|
|
|
|
| 991 |
"learning_rate": 3e-05,
|
| 992 |
+
"loss": 0.819,
|
| 993 |
"step": 13400
|
| 994 |
},
|
| 995 |
{
|
| 996 |
+
"epoch": 12.39,
|
|
|
|
| 997 |
"learning_rate": 3e-05,
|
| 998 |
+
"loss": 0.7983,
|
| 999 |
"step": 13500
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
+
"epoch": 12.49,
|
|
|
|
| 1003 |
"learning_rate": 3e-05,
|
| 1004 |
+
"loss": 0.8057,
|
| 1005 |
"step": 13600
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
+
"epoch": 12.58,
|
|
|
|
| 1009 |
"learning_rate": 3e-05,
|
| 1010 |
+
"loss": 0.8133,
|
| 1011 |
"step": 13700
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
+
"epoch": 12.67,
|
|
|
|
| 1015 |
"learning_rate": 3e-05,
|
| 1016 |
+
"loss": 0.8267,
|
| 1017 |
"step": 13800
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
+
"epoch": 12.76,
|
|
|
|
| 1021 |
"learning_rate": 3e-05,
|
| 1022 |
+
"loss": 0.8082,
|
| 1023 |
"step": 13900
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
+
"epoch": 12.85,
|
|
|
|
| 1027 |
"learning_rate": 3e-05,
|
| 1028 |
+
"loss": 0.8316,
|
| 1029 |
"step": 14000
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
+
"epoch": 12.94,
|
|
|
|
| 1033 |
"learning_rate": 3e-05,
|
| 1034 |
+
"loss": 0.8148,
|
| 1035 |
"step": 14100
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
+
"epoch": 13.0,
|
| 1039 |
+
"eval_accuracy": 0.5842278481012658,
|
| 1040 |
+
"eval_loss": 2.352457284927368,
|
| 1041 |
+
"eval_runtime": 4.464,
|
| 1042 |
+
"eval_samples_per_second": 112.008,
|
| 1043 |
+
"eval_steps_per_second": 14.113,
|
| 1044 |
"step": 14160
|
| 1045 |
},
|
| 1046 |
{
|
| 1047 |
+
"epoch": 13.0,
|
| 1048 |
"eval_exact_match": 0.0,
|
| 1049 |
+
"eval_f1": 0.08618200930627685,
|
| 1050 |
"step": 14160
|
| 1051 |
}
|
| 1052 |
],
|
| 1053 |
"logging_steps": 100,
|
| 1054 |
"max_steps": 54450,
|
|
|
|
| 1055 |
"num_train_epochs": 50,
|
| 1056 |
"save_steps": 500,
|
| 1057 |
+
"total_flos": 2.6655158384166175e+18,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1058 |
"trial_name": null,
|
| 1059 |
"trial_params": null
|
| 1060 |
}
|
checkpoint-14160/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 sha256:990ba0ec6800794569e1f142d0a98c1c27c344ee04644eb9619680965b92e617
|
| 3 |
+
size 4728
|