roy
commited on
Commit
·
f63bba1
1
Parent(s):
59e423f
gogamza: summarization
Browse files- all_results.json +12 -12
- config.json +4 -7
- eval_results.json +8 -8
- pytorch_model.bin +1 -1
- special_tokens_map.json +1 -1
- tokenizer_config.json +2 -2
- train_results.json +4 -4
- trainer_state.json +850 -850
- training_args.bin +2 -2
all_results.json
CHANGED
|
@@ -1,18 +1,18 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"eval_gen_len": 20.0,
|
| 4 |
-
"eval_loss": 1.
|
| 5 |
-
"eval_rouge1": 22.
|
| 6 |
-
"eval_rouge2":
|
| 7 |
-
"eval_rougeL": 22.
|
| 8 |
-
"eval_rougeLsum": 22.
|
| 9 |
-
"eval_runtime": 163.
|
| 10 |
"eval_samples": 7008,
|
| 11 |
-
"eval_samples_per_second": 42.
|
| 12 |
-
"eval_steps_per_second": 2.
|
| 13 |
-
"train_loss": 1.
|
| 14 |
-
"train_runtime":
|
| 15 |
"train_samples": 56760,
|
| 16 |
-
"train_samples_per_second":
|
| 17 |
-
"train_steps_per_second": 2.
|
| 18 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"eval_gen_len": 20.0,
|
| 4 |
+
"eval_loss": 1.9633301496505737,
|
| 5 |
+
"eval_rouge1": 22.6551,
|
| 6 |
+
"eval_rouge2": 6.1328,
|
| 7 |
+
"eval_rougeL": 22.457,
|
| 8 |
+
"eval_rougeLsum": 22.4619,
|
| 9 |
+
"eval_runtime": 163.8551,
|
| 10 |
"eval_samples": 7008,
|
| 11 |
+
"eval_samples_per_second": 42.77,
|
| 12 |
+
"eval_steps_per_second": 2.673,
|
| 13 |
+
"train_loss": 1.581618417182931,
|
| 14 |
+
"train_runtime": 14068.2834,
|
| 15 |
"train_samples": 56760,
|
| 16 |
+
"train_samples_per_second": 40.346,
|
| 17 |
+
"train_steps_per_second": 2.522
|
| 18 |
}
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "gogamza/kobart-
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"add_bias_logits": false,
|
|
@@ -9,7 +9,7 @@
|
|
| 9 |
],
|
| 10 |
"attention_dropout": 0.0,
|
| 11 |
"author": "Heewon Jeon([email protected])",
|
| 12 |
-
"bos_token_id":
|
| 13 |
"classif_dropout": 0.1,
|
| 14 |
"classifier_dropout": 0.1,
|
| 15 |
"d_model": 768,
|
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"decoder_ffn_dim": 3072,
|
| 18 |
"decoder_layerdrop": 0.0,
|
| 19 |
"decoder_layers": 6,
|
| 20 |
-
"decoder_start_token_id":
|
| 21 |
"do_blenderbot_90_layernorm": false,
|
| 22 |
"dropout": 0.1,
|
| 23 |
"encoder_attention_heads": 16,
|
|
@@ -27,15 +27,13 @@
|
|
| 27 |
"eos_token_id": 1,
|
| 28 |
"extra_pos_embeddings": 2,
|
| 29 |
"force_bos_token_to_be_generated": false,
|
| 30 |
-
"forced_eos_token_id":
|
| 31 |
-
"gradient_checkpointing": false,
|
| 32 |
"id2label": {
|
| 33 |
"0": "NEGATIVE",
|
| 34 |
"1": "POSITIVE"
|
| 35 |
},
|
| 36 |
"init_std": 0.02,
|
| 37 |
"is_encoder_decoder": true,
|
| 38 |
-
"kobart_version": 2.0,
|
| 39 |
"label2id": {
|
| 40 |
"NEGATIVE": 0,
|
| 41 |
"POSITIVE": 1
|
|
@@ -48,7 +46,6 @@
|
|
| 48 |
"pad_token_id": 3,
|
| 49 |
"scale_embedding": false,
|
| 50 |
"static_position_embeddings": false,
|
| 51 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 52 |
"torch_dtype": "float32",
|
| 53 |
"transformers_version": "4.25.0",
|
| 54 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "gogamza/kobart-summarization",
|
| 3 |
"activation_dropout": 0.0,
|
| 4 |
"activation_function": "gelu",
|
| 5 |
"add_bias_logits": false,
|
|
|
|
| 9 |
],
|
| 10 |
"attention_dropout": 0.0,
|
| 11 |
"author": "Heewon Jeon([email protected])",
|
| 12 |
+
"bos_token_id": 0,
|
| 13 |
"classif_dropout": 0.1,
|
| 14 |
"classifier_dropout": 0.1,
|
| 15 |
"d_model": 768,
|
|
|
|
| 17 |
"decoder_ffn_dim": 3072,
|
| 18 |
"decoder_layerdrop": 0.0,
|
| 19 |
"decoder_layers": 6,
|
| 20 |
+
"decoder_start_token_id": 2,
|
| 21 |
"do_blenderbot_90_layernorm": false,
|
| 22 |
"dropout": 0.1,
|
| 23 |
"encoder_attention_heads": 16,
|
|
|
|
| 27 |
"eos_token_id": 1,
|
| 28 |
"extra_pos_embeddings": 2,
|
| 29 |
"force_bos_token_to_be_generated": false,
|
| 30 |
+
"forced_eos_token_id": 2,
|
|
|
|
| 31 |
"id2label": {
|
| 32 |
"0": "NEGATIVE",
|
| 33 |
"1": "POSITIVE"
|
| 34 |
},
|
| 35 |
"init_std": 0.02,
|
| 36 |
"is_encoder_decoder": true,
|
|
|
|
| 37 |
"label2id": {
|
| 38 |
"NEGATIVE": 0,
|
| 39 |
"POSITIVE": 1
|
|
|
|
| 46 |
"pad_token_id": 3,
|
| 47 |
"scale_embedding": false,
|
| 48 |
"static_position_embeddings": false,
|
|
|
|
| 49 |
"torch_dtype": "float32",
|
| 50 |
"transformers_version": "4.25.0",
|
| 51 |
"use_cache": true,
|
eval_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"eval_gen_len": 20.0,
|
| 4 |
-
"eval_loss": 1.
|
| 5 |
-
"eval_rouge1": 22.
|
| 6 |
-
"eval_rouge2":
|
| 7 |
-
"eval_rougeL": 22.
|
| 8 |
-
"eval_rougeLsum": 22.
|
| 9 |
-
"eval_runtime": 163.
|
| 10 |
"eval_samples": 7008,
|
| 11 |
-
"eval_samples_per_second": 42.
|
| 12 |
-
"eval_steps_per_second": 2.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
"eval_gen_len": 20.0,
|
| 4 |
+
"eval_loss": 1.9633301496505737,
|
| 5 |
+
"eval_rouge1": 22.6551,
|
| 6 |
+
"eval_rouge2": 6.1328,
|
| 7 |
+
"eval_rougeL": 22.457,
|
| 8 |
+
"eval_rougeLsum": 22.4619,
|
| 9 |
+
"eval_runtime": 163.8551,
|
| 10 |
"eval_samples": 7008,
|
| 11 |
+
"eval_samples_per_second": 42.77,
|
| 12 |
+
"eval_steps_per_second": 2.673
|
| 13 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 495652819
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adeb720df850151ba963293c94b7cf8baa672095f397cf43b7a36c00d531d665
|
| 3 |
size 495652819
|
special_tokens_map.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "
|
| 3 |
"eos_token": "</s>",
|
| 4 |
"mask_token": "<mask>",
|
| 5 |
"pad_token": "<pad>",
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
"eos_token": "</s>",
|
| 4 |
"mask_token": "<mask>",
|
| 5 |
"pad_token": "<pad>",
|
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"model_max_length": 1000000000000000019884624838656,
|
| 3 |
-
"name_or_path": "gogamza/kobart-
|
| 4 |
-
"special_tokens_map_file": "/opt/ml/
|
| 5 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 6 |
"use_fast": true
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"model_max_length": 1000000000000000019884624838656,
|
| 3 |
+
"name_or_path": "gogamza/kobart-summarization",
|
| 4 |
+
"special_tokens_map_file": "/opt/ml/.cache/huggingface/hub/models--gogamza--kobart-summarization/snapshots/8a63d6913edc0e16a902e3fa8b688a134f0dd776/special_tokens_map.json",
|
| 5 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 6 |
"use_fast": true
|
| 7 |
}
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
-
"train_loss": 1.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 56760,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second": 2.
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 10.0,
|
| 3 |
+
"train_loss": 1.581618417182931,
|
| 4 |
+
"train_runtime": 14068.2834,
|
| 5 |
"train_samples": 56760,
|
| 6 |
+
"train_samples_per_second": 40.346,
|
| 7 |
+
"train_steps_per_second": 2.522
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 1.
|
| 3 |
-
"best_model_checkpoint": "/
|
| 4 |
"epoch": 10.0,
|
| 5 |
"global_step": 35480,
|
| 6 |
"is_hyper_param_search": false,
|
|
@@ -9,2357 +9,2357 @@
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.03,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 2.
|
| 14 |
"step": 100
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.06,
|
| 18 |
-
"learning_rate": 2.
|
| 19 |
-
"loss": 2.
|
| 20 |
"step": 200
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.08,
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 2.
|
| 26 |
"step": 300
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.11,
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 2.
|
| 32 |
"step": 400
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.14,
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 2.
|
| 38 |
"step": 500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.17,
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 2.
|
| 44 |
"step": 600
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.2,
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 2.
|
| 50 |
"step": 700
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.23,
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 2.
|
| 56 |
"step": 800
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.25,
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 2.
|
| 62 |
"step": 900
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.28,
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 2.
|
| 68 |
"step": 1000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.31,
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 2.
|
| 74 |
"step": 1100
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.34,
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 2.
|
| 80 |
"step": 1200
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.37,
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 2.
|
| 86 |
"step": 1300
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.39,
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 2.
|
| 92 |
"step": 1400
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.42,
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 2.
|
| 98 |
"step": 1500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.45,
|
| 102 |
-
"learning_rate": 4.
|
| 103 |
-
"loss": 2.
|
| 104 |
"step": 1600
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.48,
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 2.
|
| 110 |
"step": 1700
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.51,
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 2.
|
| 116 |
"step": 1800
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.54,
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 2.
|
| 122 |
"step": 1900
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.56,
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 2.
|
| 128 |
"step": 2000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.56,
|
| 132 |
"eval_gen_len": 20.0,
|
| 133 |
-
"eval_loss":
|
| 134 |
-
"eval_rouge1": 21.
|
| 135 |
-
"eval_rouge2": 5.
|
| 136 |
-
"eval_rougeL": 21.
|
| 137 |
-
"eval_rougeLsum": 21.
|
| 138 |
-
"eval_runtime": 165.
|
| 139 |
-
"eval_samples_per_second": 42.
|
| 140 |
-
"eval_steps_per_second": 2.
|
| 141 |
"step": 2000
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.59,
|
| 145 |
-
"learning_rate":
|
| 146 |
-
"loss": 2.
|
| 147 |
"step": 2100
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.62,
|
| 151 |
-
"learning_rate":
|
| 152 |
-
"loss": 2.
|
| 153 |
"step": 2200
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.65,
|
| 157 |
-
"learning_rate":
|
| 158 |
-
"loss": 2.
|
| 159 |
"step": 2300
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.68,
|
| 163 |
-
"learning_rate":
|
| 164 |
-
"loss": 2.
|
| 165 |
"step": 2400
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.7,
|
| 169 |
-
"learning_rate": 1.
|
| 170 |
-
"loss": 2.
|
| 171 |
"step": 2500
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.73,
|
| 175 |
-
"learning_rate":
|
| 176 |
-
"loss": 2.
|
| 177 |
"step": 2600
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.76,
|
| 181 |
-
"learning_rate":
|
| 182 |
-
"loss": 2.
|
| 183 |
"step": 2700
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 0.79,
|
| 187 |
-
"learning_rate": 4.
|
| 188 |
-
"loss": 2.
|
| 189 |
"step": 2800
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 0.82,
|
| 193 |
-
"learning_rate":
|
| 194 |
-
"loss": 2.
|
| 195 |
"step": 2900
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.85,
|
| 199 |
-
"learning_rate":
|
| 200 |
-
"loss": 2.
|
| 201 |
"step": 3000
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 0.87,
|
| 205 |
-
"learning_rate":
|
| 206 |
-
"loss": 2.
|
| 207 |
"step": 3100
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.9,
|
| 211 |
-
"learning_rate": 4.
|
| 212 |
-
"loss": 2.
|
| 213 |
"step": 3200
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.93,
|
| 217 |
-
"learning_rate":
|
| 218 |
-
"loss": 2.
|
| 219 |
"step": 3300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.96,
|
| 223 |
-
"learning_rate":
|
| 224 |
-
"loss": 2.
|
| 225 |
"step": 3400
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 0.99,
|
| 229 |
-
"learning_rate":
|
| 230 |
-
"loss": 2.
|
| 231 |
"step": 3500
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 1.01,
|
| 235 |
-
"learning_rate":
|
| 236 |
-
"loss":
|
| 237 |
"step": 3600
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 1.04,
|
| 241 |
-
"learning_rate":
|
| 242 |
-
"loss":
|
| 243 |
"step": 3700
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 1.07,
|
| 247 |
-
"learning_rate":
|
| 248 |
-
"loss":
|
| 249 |
"step": 3800
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 1.1,
|
| 253 |
-
"learning_rate":
|
| 254 |
-
"loss":
|
| 255 |
"step": 3900
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 1.13,
|
| 259 |
-
"learning_rate":
|
| 260 |
-
"loss":
|
| 261 |
"step": 4000
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 1.13,
|
| 265 |
"eval_gen_len": 20.0,
|
| 266 |
-
"eval_loss":
|
| 267 |
-
"eval_rouge1": 21.
|
| 268 |
-
"eval_rouge2": 5.
|
| 269 |
-
"eval_rougeL": 21.
|
| 270 |
-
"eval_rougeLsum": 21.
|
| 271 |
-
"eval_runtime":
|
| 272 |
-
"eval_samples_per_second":
|
| 273 |
-
"eval_steps_per_second": 2.
|
| 274 |
"step": 4000
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 1.16,
|
| 278 |
-
"learning_rate":
|
| 279 |
-
"loss":
|
| 280 |
"step": 4100
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 1.18,
|
| 284 |
-
"learning_rate":
|
| 285 |
-
"loss":
|
| 286 |
"step": 4200
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 1.21,
|
| 290 |
-
"learning_rate":
|
| 291 |
-
"loss":
|
| 292 |
"step": 4300
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 1.24,
|
| 296 |
-
"learning_rate":
|
| 297 |
-
"loss":
|
| 298 |
"step": 4400
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 1.27,
|
| 302 |
-
"learning_rate":
|
| 303 |
-
"loss":
|
| 304 |
"step": 4500
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.3,
|
| 308 |
-
"learning_rate":
|
| 309 |
-
"loss": 1.
|
| 310 |
"step": 4600
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 1.32,
|
| 314 |
-
"learning_rate": 2.
|
| 315 |
-
"loss": 1.
|
| 316 |
"step": 4700
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 1.35,
|
| 320 |
-
"learning_rate":
|
| 321 |
-
"loss": 1.
|
| 322 |
"step": 4800
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 1.38,
|
| 326 |
-
"learning_rate":
|
| 327 |
-
"loss":
|
| 328 |
"step": 4900
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 1.41,
|
| 332 |
-
"learning_rate":
|
| 333 |
-
"loss": 1.
|
| 334 |
"step": 5000
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 1.44,
|
| 338 |
-
"learning_rate":
|
| 339 |
-
"loss":
|
| 340 |
"step": 5100
|
| 341 |
},
|
| 342 |
{
|
| 343 |
"epoch": 1.47,
|
| 344 |
-
"learning_rate":
|
| 345 |
-
"loss":
|
| 346 |
"step": 5200
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.49,
|
| 350 |
-
"learning_rate":
|
| 351 |
-
"loss": 1.
|
| 352 |
"step": 5300
|
| 353 |
},
|
| 354 |
{
|
| 355 |
"epoch": 1.52,
|
| 356 |
-
"learning_rate":
|
| 357 |
-
"loss": 1.
|
| 358 |
"step": 5400
|
| 359 |
},
|
| 360 |
{
|
| 361 |
"epoch": 1.55,
|
| 362 |
-
"learning_rate":
|
| 363 |
-
"loss": 1.
|
| 364 |
"step": 5500
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"epoch": 1.58,
|
| 368 |
-
"learning_rate":
|
| 369 |
-
"loss": 1.
|
| 370 |
"step": 5600
|
| 371 |
},
|
| 372 |
{
|
| 373 |
"epoch": 1.61,
|
| 374 |
-
"learning_rate": 4.
|
| 375 |
-
"loss": 1.
|
| 376 |
"step": 5700
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 1.63,
|
| 380 |
-
"learning_rate":
|
| 381 |
-
"loss": 1.
|
| 382 |
"step": 5800
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"epoch": 1.66,
|
| 386 |
-
"learning_rate":
|
| 387 |
-
"loss": 1.
|
| 388 |
"step": 5900
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.69,
|
| 392 |
-
"learning_rate":
|
| 393 |
-
"loss": 1.
|
| 394 |
"step": 6000
|
| 395 |
},
|
| 396 |
{
|
| 397 |
"epoch": 1.69,
|
| 398 |
"eval_gen_len": 20.0,
|
| 399 |
-
"eval_loss": 1.
|
| 400 |
-
"eval_rouge1":
|
| 401 |
-
"eval_rouge2":
|
| 402 |
-
"eval_rougeL":
|
| 403 |
-
"eval_rougeLsum":
|
| 404 |
-
"eval_runtime":
|
| 405 |
-
"eval_samples_per_second":
|
| 406 |
-
"eval_steps_per_second": 2.
|
| 407 |
"step": 6000
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 1.72,
|
| 411 |
-
"learning_rate":
|
| 412 |
-
"loss": 1.
|
| 413 |
"step": 6100
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 1.75,
|
| 417 |
-
"learning_rate":
|
| 418 |
-
"loss": 1.
|
| 419 |
"step": 6200
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 1.78,
|
| 423 |
-
"learning_rate":
|
| 424 |
-
"loss": 1.
|
| 425 |
"step": 6300
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 1.8,
|
| 429 |
-
"learning_rate": 4.
|
| 430 |
-
"loss": 1.
|
| 431 |
"step": 6400
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 1.83,
|
| 435 |
-
"learning_rate": 4.
|
| 436 |
-
"loss":
|
| 437 |
"step": 6500
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 1.86,
|
| 441 |
-
"learning_rate":
|
| 442 |
-
"loss":
|
| 443 |
"step": 6600
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 1.89,
|
| 447 |
-
"learning_rate":
|
| 448 |
-
"loss":
|
| 449 |
"step": 6700
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 1.92,
|
| 453 |
-
"learning_rate":
|
| 454 |
-
"loss":
|
| 455 |
"step": 6800
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"epoch": 1.94,
|
| 459 |
-
"learning_rate":
|
| 460 |
-
"loss":
|
| 461 |
"step": 6900
|
| 462 |
},
|
| 463 |
{
|
| 464 |
"epoch": 1.97,
|
| 465 |
-
"learning_rate":
|
| 466 |
-
"loss":
|
| 467 |
"step": 7000
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 2.0,
|
| 471 |
-
"learning_rate":
|
| 472 |
-
"loss":
|
| 473 |
"step": 7100
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 2.03,
|
| 477 |
-
"learning_rate":
|
| 478 |
-
"loss": 1.
|
| 479 |
"step": 7200
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 2.06,
|
| 483 |
-
"learning_rate":
|
| 484 |
-
"loss": 1.
|
| 485 |
"step": 7300
|
| 486 |
},
|
| 487 |
{
|
| 488 |
"epoch": 2.09,
|
| 489 |
-
"learning_rate":
|
| 490 |
-
"loss": 1.
|
| 491 |
"step": 7400
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 2.11,
|
| 495 |
-
"learning_rate":
|
| 496 |
-
"loss": 1.
|
| 497 |
"step": 7500
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 2.14,
|
| 501 |
-
"learning_rate":
|
| 502 |
-
"loss": 1.
|
| 503 |
"step": 7600
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 2.17,
|
| 507 |
-
"learning_rate":
|
| 508 |
-
"loss": 1.
|
| 509 |
"step": 7700
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 2.2,
|
| 513 |
-
"learning_rate":
|
| 514 |
-
"loss": 1.
|
| 515 |
"step": 7800
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 2.23,
|
| 519 |
-
"learning_rate":
|
| 520 |
-
"loss": 1.
|
| 521 |
"step": 7900
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 2.25,
|
| 525 |
-
"learning_rate":
|
| 526 |
-
"loss": 1.
|
| 527 |
"step": 8000
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 2.25,
|
| 531 |
"eval_gen_len": 20.0,
|
| 532 |
-
"eval_loss":
|
| 533 |
-
"eval_rouge1":
|
| 534 |
-
"eval_rouge2": 5.
|
| 535 |
-
"eval_rougeL": 21.
|
| 536 |
-
"eval_rougeLsum": 21.
|
| 537 |
-
"eval_runtime":
|
| 538 |
-
"eval_samples_per_second":
|
| 539 |
-
"eval_steps_per_second": 2.
|
| 540 |
"step": 8000
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 2.28,
|
| 544 |
-
"learning_rate":
|
| 545 |
-
"loss": 1.
|
| 546 |
"step": 8100
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 2.31,
|
| 550 |
-
"learning_rate":
|
| 551 |
-
"loss": 1.
|
| 552 |
"step": 8200
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 2.34,
|
| 556 |
-
"learning_rate":
|
| 557 |
-
"loss": 1.
|
| 558 |
"step": 8300
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 2.37,
|
| 562 |
-
"learning_rate":
|
| 563 |
-
"loss": 1.
|
| 564 |
"step": 8400
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 2.4,
|
| 568 |
-
"learning_rate":
|
| 569 |
-
"loss": 1.
|
| 570 |
"step": 8500
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 2.42,
|
| 574 |
-
"learning_rate":
|
| 575 |
-
"loss": 1.
|
| 576 |
"step": 8600
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 2.45,
|
| 580 |
-
"learning_rate":
|
| 581 |
-
"loss": 1.
|
| 582 |
"step": 8700
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 2.48,
|
| 586 |
-
"learning_rate":
|
| 587 |
-
"loss": 1.
|
| 588 |
"step": 8800
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 2.51,
|
| 592 |
-
"learning_rate":
|
| 593 |
-
"loss": 1.
|
| 594 |
"step": 8900
|
| 595 |
},
|
| 596 |
{
|
| 597 |
"epoch": 2.54,
|
| 598 |
-
"learning_rate":
|
| 599 |
-
"loss": 1.
|
| 600 |
"step": 9000
|
| 601 |
},
|
| 602 |
{
|
| 603 |
"epoch": 2.56,
|
| 604 |
-
"learning_rate":
|
| 605 |
-
"loss": 1.
|
| 606 |
"step": 9100
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 2.59,
|
| 610 |
-
"learning_rate":
|
| 611 |
-
"loss": 1.
|
| 612 |
"step": 9200
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 2.62,
|
| 616 |
-
"learning_rate":
|
| 617 |
-
"loss": 1.
|
| 618 |
"step": 9300
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 2.65,
|
| 622 |
-
"learning_rate":
|
| 623 |
-
"loss": 1.
|
| 624 |
"step": 9400
|
| 625 |
},
|
| 626 |
{
|
| 627 |
"epoch": 2.68,
|
| 628 |
-
"learning_rate": 2.
|
| 629 |
-
"loss": 1.
|
| 630 |
"step": 9500
|
| 631 |
},
|
| 632 |
{
|
| 633 |
"epoch": 2.71,
|
| 634 |
-
"learning_rate":
|
| 635 |
-
"loss": 1.
|
| 636 |
"step": 9600
|
| 637 |
},
|
| 638 |
{
|
| 639 |
"epoch": 2.73,
|
| 640 |
-
"learning_rate":
|
| 641 |
-
"loss": 1.
|
| 642 |
"step": 9700
|
| 643 |
},
|
| 644 |
{
|
| 645 |
"epoch": 2.76,
|
| 646 |
-
"learning_rate":
|
| 647 |
-
"loss": 1.
|
| 648 |
"step": 9800
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 2.79,
|
| 652 |
-
"learning_rate":
|
| 653 |
-
"loss": 1.
|
| 654 |
"step": 9900
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 2.82,
|
| 658 |
-
"learning_rate":
|
| 659 |
-
"loss": 1.
|
| 660 |
"step": 10000
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 2.82,
|
| 664 |
"eval_gen_len": 20.0,
|
| 665 |
-
"eval_loss": 1.
|
| 666 |
-
"eval_rouge1": 22.
|
| 667 |
-
"eval_rouge2":
|
| 668 |
-
"eval_rougeL": 22.
|
| 669 |
-
"eval_rougeLsum": 22.
|
| 670 |
-
"eval_runtime":
|
| 671 |
-
"eval_samples_per_second":
|
| 672 |
-
"eval_steps_per_second": 2.
|
| 673 |
"step": 10000
|
| 674 |
},
|
| 675 |
{
|
| 676 |
"epoch": 2.85,
|
| 677 |
-
"learning_rate": 1.
|
| 678 |
-
"loss": 1.
|
| 679 |
"step": 10100
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"epoch": 2.87,
|
| 683 |
-
"learning_rate": 1.
|
| 684 |
-
"loss": 1.
|
| 685 |
"step": 10200
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 2.9,
|
| 689 |
-
"learning_rate":
|
| 690 |
-
"loss": 1.
|
| 691 |
"step": 10300
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 2.93,
|
| 695 |
-
"learning_rate":
|
| 696 |
-
"loss": 1.
|
| 697 |
"step": 10400
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 2.96,
|
| 701 |
-
"learning_rate":
|
| 702 |
-
"loss": 1.
|
| 703 |
"step": 10500
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 2.99,
|
| 707 |
-
"learning_rate":
|
| 708 |
-
"loss": 1.
|
| 709 |
"step": 10600
|
| 710 |
},
|
| 711 |
{
|
| 712 |
"epoch": 3.02,
|
| 713 |
-
"learning_rate":
|
| 714 |
-
"loss": 1.
|
| 715 |
"step": 10700
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 3.04,
|
| 719 |
-
"learning_rate":
|
| 720 |
-
"loss": 1.
|
| 721 |
"step": 10800
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 3.07,
|
| 725 |
-
"learning_rate":
|
| 726 |
-
"loss": 1.
|
| 727 |
"step": 10900
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 3.1,
|
| 731 |
-
"learning_rate":
|
| 732 |
-
"loss": 1.
|
| 733 |
"step": 11000
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 3.13,
|
| 737 |
-
"learning_rate":
|
| 738 |
-
"loss": 1.
|
| 739 |
"step": 11100
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 3.16,
|
| 743 |
-
"learning_rate":
|
| 744 |
-
"loss": 1.
|
| 745 |
"step": 11200
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 3.18,
|
| 749 |
-
"learning_rate":
|
| 750 |
-
"loss": 1.
|
| 751 |
"step": 11300
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"epoch": 3.21,
|
| 755 |
-
"learning_rate":
|
| 756 |
-
"loss": 1.
|
| 757 |
"step": 11400
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 3.24,
|
| 761 |
-
"learning_rate": 4.
|
| 762 |
-
"loss": 1.
|
| 763 |
"step": 11500
|
| 764 |
},
|
| 765 |
{
|
| 766 |
"epoch": 3.27,
|
| 767 |
-
"learning_rate":
|
| 768 |
-
"loss": 1.
|
| 769 |
"step": 11600
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 3.3,
|
| 773 |
-
"learning_rate":
|
| 774 |
-
"loss": 1.
|
| 775 |
"step": 11700
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 3.33,
|
| 779 |
-
"learning_rate":
|
| 780 |
-
"loss": 1.
|
| 781 |
"step": 11800
|
| 782 |
},
|
| 783 |
{
|
| 784 |
"epoch": 3.35,
|
| 785 |
-
"learning_rate":
|
| 786 |
-
"loss": 1.
|
| 787 |
"step": 11900
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 3.38,
|
| 791 |
-
"learning_rate":
|
| 792 |
-
"loss": 1.
|
| 793 |
"step": 12000
|
| 794 |
},
|
| 795 |
{
|
| 796 |
"epoch": 3.38,
|
| 797 |
"eval_gen_len": 20.0,
|
| 798 |
-
"eval_loss":
|
| 799 |
-
"eval_rouge1":
|
| 800 |
-
"eval_rouge2": 5.
|
| 801 |
-
"eval_rougeL": 21.
|
| 802 |
-
"eval_rougeLsum": 21.
|
| 803 |
-
"eval_runtime":
|
| 804 |
-
"eval_samples_per_second":
|
| 805 |
-
"eval_steps_per_second": 2.
|
| 806 |
"step": 12000
|
| 807 |
},
|
| 808 |
{
|
| 809 |
"epoch": 3.41,
|
| 810 |
-
"learning_rate":
|
| 811 |
-
"loss": 1.
|
| 812 |
"step": 12100
|
| 813 |
},
|
| 814 |
{
|
| 815 |
"epoch": 3.44,
|
| 816 |
-
"learning_rate":
|
| 817 |
-
"loss": 1.
|
| 818 |
"step": 12200
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 3.47,
|
| 822 |
-
"learning_rate":
|
| 823 |
-
"loss": 1.
|
| 824 |
"step": 12300
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 3.49,
|
| 828 |
-
"learning_rate":
|
| 829 |
-
"loss": 1.
|
| 830 |
"step": 12400
|
| 831 |
},
|
| 832 |
{
|
| 833 |
"epoch": 3.52,
|
| 834 |
-
"learning_rate":
|
| 835 |
-
"loss": 1.
|
| 836 |
"step": 12500
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 3.55,
|
| 840 |
-
"learning_rate":
|
| 841 |
-
"loss": 1.
|
| 842 |
"step": 12600
|
| 843 |
},
|
| 844 |
{
|
| 845 |
"epoch": 3.58,
|
| 846 |
-
"learning_rate":
|
| 847 |
-
"loss": 1.
|
| 848 |
"step": 12700
|
| 849 |
},
|
| 850 |
{
|
| 851 |
"epoch": 3.61,
|
| 852 |
-
"learning_rate": 4.
|
| 853 |
-
"loss": 1.
|
| 854 |
"step": 12800
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 3.64,
|
| 858 |
-
"learning_rate": 4.
|
| 859 |
-
"loss": 1.
|
| 860 |
"step": 12900
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 3.66,
|
| 864 |
-
"learning_rate": 4.
|
| 865 |
-
"loss": 1.
|
| 866 |
"step": 13000
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 3.69,
|
| 870 |
-
"learning_rate": 4.
|
| 871 |
-
"loss": 1.
|
| 872 |
"step": 13100
|
| 873 |
},
|
| 874 |
{
|
| 875 |
"epoch": 3.72,
|
| 876 |
-
"learning_rate": 4.
|
| 877 |
-
"loss": 1.
|
| 878 |
"step": 13200
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 3.75,
|
| 882 |
-
"learning_rate":
|
| 883 |
-
"loss": 1.
|
| 884 |
"step": 13300
|
| 885 |
},
|
| 886 |
{
|
| 887 |
"epoch": 3.78,
|
| 888 |
-
"learning_rate":
|
| 889 |
-
"loss": 1.
|
| 890 |
"step": 13400
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 3.8,
|
| 894 |
-
"learning_rate":
|
| 895 |
-
"loss": 1.
|
| 896 |
"step": 13500
|
| 897 |
},
|
| 898 |
{
|
| 899 |
"epoch": 3.83,
|
| 900 |
-
"learning_rate":
|
| 901 |
-
"loss": 1.
|
| 902 |
"step": 13600
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 3.86,
|
| 906 |
-
"learning_rate":
|
| 907 |
-
"loss": 1.
|
| 908 |
"step": 13700
|
| 909 |
},
|
| 910 |
{
|
| 911 |
"epoch": 3.89,
|
| 912 |
-
"learning_rate":
|
| 913 |
-
"loss": 1.
|
| 914 |
"step": 13800
|
| 915 |
},
|
| 916 |
{
|
| 917 |
"epoch": 3.92,
|
| 918 |
-
"learning_rate":
|
| 919 |
-
"loss": 1.
|
| 920 |
"step": 13900
|
| 921 |
},
|
| 922 |
{
|
| 923 |
"epoch": 3.95,
|
| 924 |
-
"learning_rate":
|
| 925 |
-
"loss": 1.
|
| 926 |
"step": 14000
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 3.95,
|
| 930 |
"eval_gen_len": 20.0,
|
| 931 |
-
"eval_loss":
|
| 932 |
-
"eval_rouge1":
|
| 933 |
-
"eval_rouge2": 5.
|
| 934 |
-
"eval_rougeL":
|
| 935 |
-
"eval_rougeLsum":
|
| 936 |
-
"eval_runtime":
|
| 937 |
-
"eval_samples_per_second": 42.
|
| 938 |
-
"eval_steps_per_second": 2.
|
| 939 |
"step": 14000
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 3.97,
|
| 943 |
-
"learning_rate":
|
| 944 |
-
"loss": 1.
|
| 945 |
"step": 14100
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 4.0,
|
| 949 |
-
"learning_rate":
|
| 950 |
-
"loss": 1.
|
| 951 |
"step": 14200
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 4.03,
|
| 955 |
-
"learning_rate":
|
| 956 |
-
"loss": 1.
|
| 957 |
"step": 14300
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 4.06,
|
| 961 |
-
"learning_rate":
|
| 962 |
-
"loss": 1.
|
| 963 |
"step": 14400
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 4.09,
|
| 967 |
-
"learning_rate":
|
| 968 |
-
"loss": 1.
|
| 969 |
"step": 14500
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 4.11,
|
| 973 |
-
"learning_rate":
|
| 974 |
-
"loss": 1.
|
| 975 |
"step": 14600
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 4.14,
|
| 979 |
-
"learning_rate":
|
| 980 |
-
"loss": 1.
|
| 981 |
"step": 14700
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 4.17,
|
| 985 |
-
"learning_rate":
|
| 986 |
-
"loss": 1.
|
| 987 |
"step": 14800
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 4.2,
|
| 991 |
-
"learning_rate":
|
| 992 |
-
"loss": 1.
|
| 993 |
"step": 14900
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 4.23,
|
| 997 |
-
"learning_rate":
|
| 998 |
-
"loss": 1.
|
| 999 |
"step": 15000
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 4.26,
|
| 1003 |
-
"learning_rate":
|
| 1004 |
-
"loss": 1.
|
| 1005 |
"step": 15100
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 4.28,
|
| 1009 |
-
"learning_rate":
|
| 1010 |
-
"loss": 1.
|
| 1011 |
"step": 15200
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 4.31,
|
| 1015 |
-
"learning_rate":
|
| 1016 |
-
"loss": 1.
|
| 1017 |
"step": 15300
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 4.34,
|
| 1021 |
-
"learning_rate":
|
| 1022 |
-
"loss": 1.
|
| 1023 |
"step": 15400
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 4.37,
|
| 1027 |
-
"learning_rate":
|
| 1028 |
-
"loss": 1.
|
| 1029 |
"step": 15500
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 4.4,
|
| 1033 |
-
"learning_rate":
|
| 1034 |
-
"loss": 1.
|
| 1035 |
"step": 15600
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 4.43,
|
| 1039 |
-
"learning_rate":
|
| 1040 |
-
"loss": 1.
|
| 1041 |
"step": 15700
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 4.45,
|
| 1045 |
-
"learning_rate":
|
| 1046 |
-
"loss": 1.
|
| 1047 |
"step": 15800
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 4.48,
|
| 1051 |
-
"learning_rate":
|
| 1052 |
-
"loss": 1.
|
| 1053 |
"step": 15900
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"epoch": 4.51,
|
| 1057 |
-
"learning_rate":
|
| 1058 |
-
"loss": 1.
|
| 1059 |
"step": 16000
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 4.51,
|
| 1063 |
"eval_gen_len": 20.0,
|
| 1064 |
-
"eval_loss": 2.
|
| 1065 |
-
"eval_rouge1": 22.
|
| 1066 |
-
"eval_rouge2": 5.
|
| 1067 |
-
"eval_rougeL":
|
| 1068 |
-
"eval_rougeLsum": 21.
|
| 1069 |
-
"eval_runtime":
|
| 1070 |
-
"eval_samples_per_second":
|
| 1071 |
-
"eval_steps_per_second": 2.
|
| 1072 |
"step": 16000
|
| 1073 |
},
|
| 1074 |
{
|
| 1075 |
"epoch": 4.54,
|
| 1076 |
-
"learning_rate":
|
| 1077 |
-
"loss": 1.
|
| 1078 |
"step": 16100
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 4.57,
|
| 1082 |
-
"learning_rate":
|
| 1083 |
-
"loss": 1.
|
| 1084 |
"step": 16200
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
"epoch": 4.59,
|
| 1088 |
-
"learning_rate":
|
| 1089 |
-
"loss": 1.
|
| 1090 |
"step": 16300
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
"epoch": 4.62,
|
| 1094 |
-
"learning_rate":
|
| 1095 |
-
"loss": 1.
|
| 1096 |
"step": 16400
|
| 1097 |
},
|
| 1098 |
{
|
| 1099 |
"epoch": 4.65,
|
| 1100 |
-
"learning_rate":
|
| 1101 |
-
"loss": 1.
|
| 1102 |
"step": 16500
|
| 1103 |
},
|
| 1104 |
{
|
| 1105 |
"epoch": 4.68,
|
| 1106 |
-
"learning_rate":
|
| 1107 |
-
"loss": 1.
|
| 1108 |
"step": 16600
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"epoch": 4.71,
|
| 1112 |
-
"learning_rate":
|
| 1113 |
-
"loss": 1.
|
| 1114 |
"step": 16700
|
| 1115 |
},
|
| 1116 |
{
|
| 1117 |
"epoch": 4.74,
|
| 1118 |
-
"learning_rate":
|
| 1119 |
-
"loss": 1.
|
| 1120 |
"step": 16800
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 4.76,
|
| 1124 |
-
"learning_rate":
|
| 1125 |
-
"loss": 1.
|
| 1126 |
"step": 16900
|
| 1127 |
},
|
| 1128 |
{
|
| 1129 |
"epoch": 4.79,
|
| 1130 |
-
"learning_rate":
|
| 1131 |
-
"loss": 1.
|
| 1132 |
"step": 17000
|
| 1133 |
},
|
| 1134 |
{
|
| 1135 |
"epoch": 4.82,
|
| 1136 |
-
"learning_rate":
|
| 1137 |
-
"loss": 1.
|
| 1138 |
"step": 17100
|
| 1139 |
},
|
| 1140 |
{
|
| 1141 |
"epoch": 4.85,
|
| 1142 |
-
"learning_rate":
|
| 1143 |
-
"loss": 1.
|
| 1144 |
"step": 17200
|
| 1145 |
},
|
| 1146 |
{
|
| 1147 |
"epoch": 4.88,
|
| 1148 |
-
"learning_rate":
|
| 1149 |
-
"loss": 1.
|
| 1150 |
"step": 17300
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 4.9,
|
| 1154 |
-
"learning_rate":
|
| 1155 |
-
"loss": 1.
|
| 1156 |
"step": 17400
|
| 1157 |
},
|
| 1158 |
{
|
| 1159 |
"epoch": 4.93,
|
| 1160 |
-
"learning_rate":
|
| 1161 |
-
"loss": 1.
|
| 1162 |
"step": 17500
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 4.96,
|
| 1166 |
-
"learning_rate":
|
| 1167 |
-
"loss": 1.
|
| 1168 |
"step": 17600
|
| 1169 |
},
|
| 1170 |
{
|
| 1171 |
"epoch": 4.99,
|
| 1172 |
-
"learning_rate":
|
| 1173 |
-
"loss": 1.
|
| 1174 |
"step": 17700
|
| 1175 |
},
|
| 1176 |
{
|
| 1177 |
"epoch": 5.02,
|
| 1178 |
-
"learning_rate":
|
| 1179 |
-
"loss": 1.
|
| 1180 |
"step": 17800
|
| 1181 |
},
|
| 1182 |
{
|
| 1183 |
"epoch": 5.05,
|
| 1184 |
-
"learning_rate":
|
| 1185 |
-
"loss": 1.
|
| 1186 |
"step": 17900
|
| 1187 |
},
|
| 1188 |
{
|
| 1189 |
"epoch": 5.07,
|
| 1190 |
-
"learning_rate":
|
| 1191 |
-
"loss": 1.
|
| 1192 |
"step": 18000
|
| 1193 |
},
|
| 1194 |
{
|
| 1195 |
"epoch": 5.07,
|
| 1196 |
"eval_gen_len": 20.0,
|
| 1197 |
-
"eval_loss": 2.
|
| 1198 |
-
"eval_rouge1": 21.
|
| 1199 |
-
"eval_rouge2": 5.
|
| 1200 |
-
"eval_rougeL": 21.
|
| 1201 |
-
"eval_rougeLsum": 21.
|
| 1202 |
-
"eval_runtime":
|
| 1203 |
-
"eval_samples_per_second":
|
| 1204 |
-
"eval_steps_per_second": 2.
|
| 1205 |
"step": 18000
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 5.1,
|
| 1209 |
-
"learning_rate":
|
| 1210 |
-
"loss": 1.
|
| 1211 |
"step": 18100
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
"epoch": 5.13,
|
| 1215 |
-
"learning_rate":
|
| 1216 |
-
"loss": 1.
|
| 1217 |
"step": 18200
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
"epoch": 5.16,
|
| 1221 |
-
"learning_rate":
|
| 1222 |
-
"loss": 1.
|
| 1223 |
"step": 18300
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
"epoch": 5.19,
|
| 1227 |
-
"learning_rate":
|
| 1228 |
-
"loss": 1.
|
| 1229 |
"step": 18400
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
"epoch": 5.21,
|
| 1233 |
-
"learning_rate":
|
| 1234 |
-
"loss": 1.
|
| 1235 |
"step": 18500
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
"epoch": 5.24,
|
| 1239 |
-
"learning_rate":
|
| 1240 |
-
"loss": 1.
|
| 1241 |
"step": 18600
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 5.27,
|
| 1245 |
-
"learning_rate":
|
| 1246 |
-
"loss": 1.
|
| 1247 |
"step": 18700
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
"epoch": 5.3,
|
| 1251 |
-
"learning_rate":
|
| 1252 |
-
"loss": 1.
|
| 1253 |
"step": 18800
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 5.33,
|
| 1257 |
-
"learning_rate": 2.
|
| 1258 |
-
"loss": 1.
|
| 1259 |
"step": 18900
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 5.36,
|
| 1263 |
-
"learning_rate": 2.
|
| 1264 |
-
"loss": 1.
|
| 1265 |
"step": 19000
|
| 1266 |
},
|
| 1267 |
{
|
| 1268 |
"epoch": 5.38,
|
| 1269 |
-
"learning_rate": 2.
|
| 1270 |
-
"loss": 1.
|
| 1271 |
"step": 19100
|
| 1272 |
},
|
| 1273 |
{
|
| 1274 |
"epoch": 5.41,
|
| 1275 |
-
"learning_rate":
|
| 1276 |
-
"loss": 1.
|
| 1277 |
"step": 19200
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
"epoch": 5.44,
|
| 1281 |
-
"learning_rate":
|
| 1282 |
-
"loss": 1.
|
| 1283 |
"step": 19300
|
| 1284 |
},
|
| 1285 |
{
|
| 1286 |
"epoch": 5.47,
|
| 1287 |
-
"learning_rate":
|
| 1288 |
-
"loss": 1.
|
| 1289 |
"step": 19400
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
"epoch": 5.5,
|
| 1293 |
-
"learning_rate":
|
| 1294 |
-
"loss": 1.
|
| 1295 |
"step": 19500
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 5.52,
|
| 1299 |
-
"learning_rate":
|
| 1300 |
-
"loss": 1.
|
| 1301 |
"step": 19600
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
"epoch": 5.55,
|
| 1305 |
-
"learning_rate":
|
| 1306 |
-
"loss": 1.
|
| 1307 |
"step": 19700
|
| 1308 |
},
|
| 1309 |
{
|
| 1310 |
"epoch": 5.58,
|
| 1311 |
-
"learning_rate":
|
| 1312 |
-
"loss": 1.
|
| 1313 |
"step": 19800
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 5.61,
|
| 1317 |
-
"learning_rate":
|
| 1318 |
-
"loss": 1.
|
| 1319 |
"step": 19900
|
| 1320 |
},
|
| 1321 |
{
|
| 1322 |
"epoch": 5.64,
|
| 1323 |
-
"learning_rate":
|
| 1324 |
-
"loss": 1.
|
| 1325 |
"step": 20000
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 5.64,
|
| 1329 |
"eval_gen_len": 20.0,
|
| 1330 |
-
"eval_loss": 2.
|
| 1331 |
-
"eval_rouge1":
|
| 1332 |
-
"eval_rouge2": 5.
|
| 1333 |
-
"eval_rougeL": 21.
|
| 1334 |
-
"eval_rougeLsum": 21.
|
| 1335 |
-
"eval_runtime":
|
| 1336 |
-
"eval_samples_per_second":
|
| 1337 |
-
"eval_steps_per_second": 2.
|
| 1338 |
"step": 20000
|
| 1339 |
},
|
| 1340 |
{
|
| 1341 |
"epoch": 5.67,
|
| 1342 |
-
"learning_rate":
|
| 1343 |
-
"loss": 1.
|
| 1344 |
"step": 20100
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 5.69,
|
| 1348 |
-
"learning_rate": 1.
|
| 1349 |
-
"loss": 1.
|
| 1350 |
"step": 20200
|
| 1351 |
},
|
| 1352 |
{
|
| 1353 |
"epoch": 5.72,
|
| 1354 |
-
"learning_rate": 1.
|
| 1355 |
-
"loss": 1.
|
| 1356 |
"step": 20300
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 5.75,
|
| 1360 |
-
"learning_rate": 1.
|
| 1361 |
-
"loss": 1.
|
| 1362 |
"step": 20400
|
| 1363 |
},
|
| 1364 |
{
|
| 1365 |
"epoch": 5.78,
|
| 1366 |
-
"learning_rate":
|
| 1367 |
-
"loss": 1.
|
| 1368 |
"step": 20500
|
| 1369 |
},
|
| 1370 |
{
|
| 1371 |
"epoch": 5.81,
|
| 1372 |
-
"learning_rate":
|
| 1373 |
-
"loss": 1.
|
| 1374 |
"step": 20600
|
| 1375 |
},
|
| 1376 |
{
|
| 1377 |
"epoch": 5.83,
|
| 1378 |
-
"learning_rate":
|
| 1379 |
-
"loss": 1.
|
| 1380 |
"step": 20700
|
| 1381 |
},
|
| 1382 |
{
|
| 1383 |
"epoch": 5.86,
|
| 1384 |
-
"learning_rate":
|
| 1385 |
-
"loss": 1.
|
| 1386 |
"step": 20800
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
"epoch": 5.89,
|
| 1390 |
-
"learning_rate":
|
| 1391 |
-
"loss": 1.
|
| 1392 |
"step": 20900
|
| 1393 |
},
|
| 1394 |
{
|
| 1395 |
"epoch": 5.92,
|
| 1396 |
-
"learning_rate":
|
| 1397 |
-
"loss": 1.
|
| 1398 |
"step": 21000
|
| 1399 |
},
|
| 1400 |
{
|
| 1401 |
"epoch": 5.95,
|
| 1402 |
-
"learning_rate":
|
| 1403 |
-
"loss": 1.
|
| 1404 |
"step": 21100
|
| 1405 |
},
|
| 1406 |
{
|
| 1407 |
"epoch": 5.98,
|
| 1408 |
-
"learning_rate":
|
| 1409 |
-
"loss": 1.
|
| 1410 |
"step": 21200
|
| 1411 |
},
|
| 1412 |
{
|
| 1413 |
"epoch": 6.0,
|
| 1414 |
-
"learning_rate":
|
| 1415 |
-
"loss": 1.
|
| 1416 |
"step": 21300
|
| 1417 |
},
|
| 1418 |
{
|
| 1419 |
"epoch": 6.03,
|
| 1420 |
-
"learning_rate":
|
| 1421 |
-
"loss": 1.
|
| 1422 |
"step": 21400
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
"epoch": 6.06,
|
| 1426 |
-
"learning_rate":
|
| 1427 |
-
"loss": 1.
|
| 1428 |
"step": 21500
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
"epoch": 6.09,
|
| 1432 |
-
"learning_rate":
|
| 1433 |
-
"loss": 1.
|
| 1434 |
"step": 21600
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"epoch": 6.12,
|
| 1438 |
-
"learning_rate":
|
| 1439 |
-
"loss": 1.
|
| 1440 |
"step": 21700
|
| 1441 |
},
|
| 1442 |
{
|
| 1443 |
"epoch": 6.14,
|
| 1444 |
-
"learning_rate":
|
| 1445 |
-
"loss": 1.
|
| 1446 |
"step": 21800
|
| 1447 |
},
|
| 1448 |
{
|
| 1449 |
"epoch": 6.17,
|
| 1450 |
-
"learning_rate":
|
| 1451 |
-
"loss": 1.
|
| 1452 |
"step": 21900
|
| 1453 |
},
|
| 1454 |
{
|
| 1455 |
"epoch": 6.2,
|
| 1456 |
-
"learning_rate":
|
| 1457 |
-
"loss": 1.
|
| 1458 |
"step": 22000
|
| 1459 |
},
|
| 1460 |
{
|
| 1461 |
"epoch": 6.2,
|
| 1462 |
"eval_gen_len": 20.0,
|
| 1463 |
-
"eval_loss": 2.
|
| 1464 |
-
"eval_rouge1":
|
| 1465 |
-
"eval_rouge2": 5.
|
| 1466 |
-
"eval_rougeL":
|
| 1467 |
-
"eval_rougeLsum":
|
| 1468 |
-
"eval_runtime":
|
| 1469 |
-
"eval_samples_per_second":
|
| 1470 |
-
"eval_steps_per_second": 2.
|
| 1471 |
"step": 22000
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 6.23,
|
| 1475 |
-
"learning_rate":
|
| 1476 |
-
"loss": 1.
|
| 1477 |
"step": 22100
|
| 1478 |
},
|
| 1479 |
{
|
| 1480 |
"epoch": 6.26,
|
| 1481 |
-
"learning_rate":
|
| 1482 |
-
"loss": 1.
|
| 1483 |
"step": 22200
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
"epoch": 6.29,
|
| 1487 |
-
"learning_rate":
|
| 1488 |
-
"loss": 1.
|
| 1489 |
"step": 22300
|
| 1490 |
},
|
| 1491 |
{
|
| 1492 |
"epoch": 6.31,
|
| 1493 |
-
"learning_rate":
|
| 1494 |
-
"loss": 1.
|
| 1495 |
"step": 22400
|
| 1496 |
},
|
| 1497 |
{
|
| 1498 |
"epoch": 6.34,
|
| 1499 |
-
"learning_rate":
|
| 1500 |
-
"loss": 1.
|
| 1501 |
"step": 22500
|
| 1502 |
},
|
| 1503 |
{
|
| 1504 |
"epoch": 6.37,
|
| 1505 |
-
"learning_rate":
|
| 1506 |
-
"loss": 1.
|
| 1507 |
"step": 22600
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
"epoch": 6.4,
|
| 1511 |
-
"learning_rate":
|
| 1512 |
-
"loss": 1.
|
| 1513 |
"step": 22700
|
| 1514 |
},
|
| 1515 |
{
|
| 1516 |
"epoch": 6.43,
|
| 1517 |
-
"learning_rate":
|
| 1518 |
-
"loss": 1.
|
| 1519 |
"step": 22800
|
| 1520 |
},
|
| 1521 |
{
|
| 1522 |
"epoch": 6.45,
|
| 1523 |
-
"learning_rate":
|
| 1524 |
-
"loss": 1.
|
| 1525 |
"step": 22900
|
| 1526 |
},
|
| 1527 |
{
|
| 1528 |
"epoch": 6.48,
|
| 1529 |
-
"learning_rate": 4.
|
| 1530 |
-
"loss": 1.
|
| 1531 |
"step": 23000
|
| 1532 |
},
|
| 1533 |
{
|
| 1534 |
"epoch": 6.51,
|
| 1535 |
-
"learning_rate": 4.
|
| 1536 |
-
"loss": 1.
|
| 1537 |
"step": 23100
|
| 1538 |
},
|
| 1539 |
{
|
| 1540 |
"epoch": 6.54,
|
| 1541 |
-
"learning_rate":
|
| 1542 |
-
"loss": 1.
|
| 1543 |
"step": 23200
|
| 1544 |
},
|
| 1545 |
{
|
| 1546 |
"epoch": 6.57,
|
| 1547 |
-
"learning_rate":
|
| 1548 |
-
"loss": 1.
|
| 1549 |
"step": 23300
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 6.6,
|
| 1553 |
-
"learning_rate":
|
| 1554 |
-
"loss": 1.
|
| 1555 |
"step": 23400
|
| 1556 |
},
|
| 1557 |
{
|
| 1558 |
"epoch": 6.62,
|
| 1559 |
-
"learning_rate":
|
| 1560 |
-
"loss": 1.
|
| 1561 |
"step": 23500
|
| 1562 |
},
|
| 1563 |
{
|
| 1564 |
"epoch": 6.65,
|
| 1565 |
-
"learning_rate":
|
| 1566 |
-
"loss": 1.
|
| 1567 |
"step": 23600
|
| 1568 |
},
|
| 1569 |
{
|
| 1570 |
"epoch": 6.68,
|
| 1571 |
-
"learning_rate":
|
| 1572 |
-
"loss": 1.
|
| 1573 |
"step": 23700
|
| 1574 |
},
|
| 1575 |
{
|
| 1576 |
"epoch": 6.71,
|
| 1577 |
-
"learning_rate":
|
| 1578 |
-
"loss": 1.
|
| 1579 |
"step": 23800
|
| 1580 |
},
|
| 1581 |
{
|
| 1582 |
"epoch": 6.74,
|
| 1583 |
-
"learning_rate":
|
| 1584 |
-
"loss": 1.
|
| 1585 |
"step": 23900
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
"epoch": 6.76,
|
| 1589 |
-
"learning_rate":
|
| 1590 |
-
"loss": 1.
|
| 1591 |
"step": 24000
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
"epoch": 6.76,
|
| 1595 |
"eval_gen_len": 20.0,
|
| 1596 |
-
"eval_loss": 2.
|
| 1597 |
-
"eval_rouge1": 21.
|
| 1598 |
-
"eval_rouge2": 5.
|
| 1599 |
-
"eval_rougeL": 21.
|
| 1600 |
-
"eval_rougeLsum": 21.
|
| 1601 |
-
"eval_runtime":
|
| 1602 |
-
"eval_samples_per_second": 42.
|
| 1603 |
-
"eval_steps_per_second": 2.
|
| 1604 |
"step": 24000
|
| 1605 |
},
|
| 1606 |
{
|
| 1607 |
"epoch": 6.79,
|
| 1608 |
-
"learning_rate":
|
| 1609 |
-
"loss": 1.
|
| 1610 |
"step": 24100
|
| 1611 |
},
|
| 1612 |
{
|
| 1613 |
"epoch": 6.82,
|
| 1614 |
-
"learning_rate":
|
| 1615 |
-
"loss": 1.
|
| 1616 |
"step": 24200
|
| 1617 |
},
|
| 1618 |
{
|
| 1619 |
"epoch": 6.85,
|
| 1620 |
-
"learning_rate":
|
| 1621 |
-
"loss": 1.
|
| 1622 |
"step": 24300
|
| 1623 |
},
|
| 1624 |
{
|
| 1625 |
"epoch": 6.88,
|
| 1626 |
-
"learning_rate":
|
| 1627 |
-
"loss": 1.
|
| 1628 |
"step": 24400
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
"epoch": 6.91,
|
| 1632 |
-
"learning_rate":
|
| 1633 |
-
"loss": 1.
|
| 1634 |
"step": 24500
|
| 1635 |
},
|
| 1636 |
{
|
| 1637 |
"epoch": 6.93,
|
| 1638 |
-
"learning_rate":
|
| 1639 |
-
"loss": 1.
|
| 1640 |
"step": 24600
|
| 1641 |
},
|
| 1642 |
{
|
| 1643 |
"epoch": 6.96,
|
| 1644 |
-
"learning_rate":
|
| 1645 |
-
"loss": 1.
|
| 1646 |
"step": 24700
|
| 1647 |
},
|
| 1648 |
{
|
| 1649 |
"epoch": 6.99,
|
| 1650 |
-
"learning_rate": 4.
|
| 1651 |
-
"loss": 1.
|
| 1652 |
"step": 24800
|
| 1653 |
},
|
| 1654 |
{
|
| 1655 |
"epoch": 7.02,
|
| 1656 |
-
"learning_rate":
|
| 1657 |
-
"loss": 1.
|
| 1658 |
"step": 24900
|
| 1659 |
},
|
| 1660 |
{
|
| 1661 |
"epoch": 7.05,
|
| 1662 |
-
"learning_rate":
|
| 1663 |
-
"loss": 1.
|
| 1664 |
"step": 25000
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
"epoch": 7.07,
|
| 1668 |
-
"learning_rate":
|
| 1669 |
-
"loss": 1.
|
| 1670 |
"step": 25100
|
| 1671 |
},
|
| 1672 |
{
|
| 1673 |
"epoch": 7.1,
|
| 1674 |
-
"learning_rate":
|
| 1675 |
-
"loss": 1.
|
| 1676 |
"step": 25200
|
| 1677 |
},
|
| 1678 |
{
|
| 1679 |
"epoch": 7.13,
|
| 1680 |
-
"learning_rate":
|
| 1681 |
-
"loss": 1.
|
| 1682 |
"step": 25300
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 7.16,
|
| 1686 |
-
"learning_rate":
|
| 1687 |
-
"loss": 1.
|
| 1688 |
"step": 25400
|
| 1689 |
},
|
| 1690 |
{
|
| 1691 |
"epoch": 7.19,
|
| 1692 |
-
"learning_rate":
|
| 1693 |
-
"loss": 1.
|
| 1694 |
"step": 25500
|
| 1695 |
},
|
| 1696 |
{
|
| 1697 |
"epoch": 7.22,
|
| 1698 |
-
"learning_rate": 4.
|
| 1699 |
-
"loss": 1.
|
| 1700 |
"step": 25600
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
"epoch": 7.24,
|
| 1704 |
-
"learning_rate": 4.
|
| 1705 |
-
"loss": 1.
|
| 1706 |
"step": 25700
|
| 1707 |
},
|
| 1708 |
{
|
| 1709 |
"epoch": 7.27,
|
| 1710 |
-
"learning_rate": 4.
|
| 1711 |
-
"loss": 1.
|
| 1712 |
"step": 25800
|
| 1713 |
},
|
| 1714 |
{
|
| 1715 |
"epoch": 7.3,
|
| 1716 |
-
"learning_rate": 4.
|
| 1717 |
-
"loss": 1.
|
| 1718 |
"step": 25900
|
| 1719 |
},
|
| 1720 |
{
|
| 1721 |
"epoch": 7.33,
|
| 1722 |
-
"learning_rate": 4.
|
| 1723 |
-
"loss": 1.
|
| 1724 |
"step": 26000
|
| 1725 |
},
|
| 1726 |
{
|
| 1727 |
"epoch": 7.33,
|
| 1728 |
"eval_gen_len": 20.0,
|
| 1729 |
-
"eval_loss": 2.
|
| 1730 |
-
"eval_rouge1": 21.
|
| 1731 |
-
"eval_rouge2": 5.
|
| 1732 |
-
"eval_rougeL": 21.
|
| 1733 |
-
"eval_rougeLsum": 21.
|
| 1734 |
-
"eval_runtime":
|
| 1735 |
-
"eval_samples_per_second":
|
| 1736 |
-
"eval_steps_per_second": 2.
|
| 1737 |
"step": 26000
|
| 1738 |
},
|
| 1739 |
{
|
| 1740 |
"epoch": 7.36,
|
| 1741 |
-
"learning_rate": 4.
|
| 1742 |
-
"loss": 1.
|
| 1743 |
"step": 26100
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 7.38,
|
| 1747 |
-
"learning_rate": 4.
|
| 1748 |
-
"loss": 1.
|
| 1749 |
"step": 26200
|
| 1750 |
},
|
| 1751 |
{
|
| 1752 |
"epoch": 7.41,
|
| 1753 |
-
"learning_rate": 4.
|
| 1754 |
-
"loss": 1.
|
| 1755 |
"step": 26300
|
| 1756 |
},
|
| 1757 |
{
|
| 1758 |
"epoch": 7.44,
|
| 1759 |
-
"learning_rate": 4.
|
| 1760 |
-
"loss": 1.
|
| 1761 |
"step": 26400
|
| 1762 |
},
|
| 1763 |
{
|
| 1764 |
"epoch": 7.47,
|
| 1765 |
-
"learning_rate": 4.
|
| 1766 |
-
"loss": 1.
|
| 1767 |
"step": 26500
|
| 1768 |
},
|
| 1769 |
{
|
| 1770 |
"epoch": 7.5,
|
| 1771 |
-
"learning_rate":
|
| 1772 |
-
"loss": 1.
|
| 1773 |
"step": 26600
|
| 1774 |
},
|
| 1775 |
{
|
| 1776 |
"epoch": 7.53,
|
| 1777 |
-
"learning_rate":
|
| 1778 |
-
"loss": 1.
|
| 1779 |
"step": 26700
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
"epoch": 7.55,
|
| 1783 |
-
"learning_rate":
|
| 1784 |
-
"loss": 1.
|
| 1785 |
"step": 26800
|
| 1786 |
},
|
| 1787 |
{
|
| 1788 |
"epoch": 7.58,
|
| 1789 |
-
"learning_rate":
|
| 1790 |
-
"loss": 1.
|
| 1791 |
"step": 26900
|
| 1792 |
},
|
| 1793 |
{
|
| 1794 |
"epoch": 7.61,
|
| 1795 |
-
"learning_rate":
|
| 1796 |
-
"loss": 1.
|
| 1797 |
"step": 27000
|
| 1798 |
},
|
| 1799 |
{
|
| 1800 |
"epoch": 7.64,
|
| 1801 |
-
"learning_rate":
|
| 1802 |
-
"loss": 1.
|
| 1803 |
"step": 27100
|
| 1804 |
},
|
| 1805 |
{
|
| 1806 |
"epoch": 7.67,
|
| 1807 |
-
"learning_rate":
|
| 1808 |
-
"loss": 1.
|
| 1809 |
"step": 27200
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
"epoch": 7.69,
|
| 1813 |
-
"learning_rate":
|
| 1814 |
-
"loss": 1.
|
| 1815 |
"step": 27300
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
"epoch": 7.72,
|
| 1819 |
-
"learning_rate":
|
| 1820 |
-
"loss": 1.
|
| 1821 |
"step": 27400
|
| 1822 |
},
|
| 1823 |
{
|
| 1824 |
"epoch": 7.75,
|
| 1825 |
-
"learning_rate":
|
| 1826 |
-
"loss": 1.
|
| 1827 |
"step": 27500
|
| 1828 |
},
|
| 1829 |
{
|
| 1830 |
"epoch": 7.78,
|
| 1831 |
-
"learning_rate":
|
| 1832 |
-
"loss": 1.
|
| 1833 |
"step": 27600
|
| 1834 |
},
|
| 1835 |
{
|
| 1836 |
"epoch": 7.81,
|
| 1837 |
-
"learning_rate":
|
| 1838 |
-
"loss": 1.
|
| 1839 |
"step": 27700
|
| 1840 |
},
|
| 1841 |
{
|
| 1842 |
"epoch": 7.84,
|
| 1843 |
-
"learning_rate":
|
| 1844 |
-
"loss": 1.
|
| 1845 |
"step": 27800
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
"epoch": 7.86,
|
| 1849 |
-
"learning_rate":
|
| 1850 |
-
"loss": 1.
|
| 1851 |
"step": 27900
|
| 1852 |
},
|
| 1853 |
{
|
| 1854 |
"epoch": 7.89,
|
| 1855 |
-
"learning_rate":
|
| 1856 |
-
"loss": 1.
|
| 1857 |
"step": 28000
|
| 1858 |
},
|
| 1859 |
{
|
| 1860 |
"epoch": 7.89,
|
| 1861 |
"eval_gen_len": 20.0,
|
| 1862 |
-
"eval_loss": 2.
|
| 1863 |
-
"eval_rouge1":
|
| 1864 |
-
"eval_rouge2": 5.
|
| 1865 |
-
"eval_rougeL":
|
| 1866 |
-
"eval_rougeLsum":
|
| 1867 |
-
"eval_runtime":
|
| 1868 |
-
"eval_samples_per_second": 42.
|
| 1869 |
-
"eval_steps_per_second": 2.
|
| 1870 |
"step": 28000
|
| 1871 |
},
|
| 1872 |
{
|
| 1873 |
"epoch": 7.92,
|
| 1874 |
-
"learning_rate":
|
| 1875 |
-
"loss": 1.
|
| 1876 |
"step": 28100
|
| 1877 |
},
|
| 1878 |
{
|
| 1879 |
"epoch": 7.95,
|
| 1880 |
-
"learning_rate":
|
| 1881 |
-
"loss": 1.
|
| 1882 |
"step": 28200
|
| 1883 |
},
|
| 1884 |
{
|
| 1885 |
"epoch": 7.98,
|
| 1886 |
-
"learning_rate":
|
| 1887 |
-
"loss": 1.
|
| 1888 |
"step": 28300
|
| 1889 |
},
|
| 1890 |
{
|
| 1891 |
"epoch": 8.0,
|
| 1892 |
-
"learning_rate":
|
| 1893 |
-
"loss": 1.
|
| 1894 |
"step": 28400
|
| 1895 |
},
|
| 1896 |
{
|
| 1897 |
"epoch": 8.03,
|
| 1898 |
-
"learning_rate":
|
| 1899 |
-
"loss": 1.
|
| 1900 |
"step": 28500
|
| 1901 |
},
|
| 1902 |
{
|
| 1903 |
"epoch": 8.06,
|
| 1904 |
-
"learning_rate":
|
| 1905 |
-
"loss": 1.
|
| 1906 |
"step": 28600
|
| 1907 |
},
|
| 1908 |
{
|
| 1909 |
"epoch": 8.09,
|
| 1910 |
-
"learning_rate":
|
| 1911 |
-
"loss": 1.
|
| 1912 |
"step": 28700
|
| 1913 |
},
|
| 1914 |
{
|
| 1915 |
"epoch": 8.12,
|
| 1916 |
-
"learning_rate":
|
| 1917 |
-
"loss": 1.
|
| 1918 |
"step": 28800
|
| 1919 |
},
|
| 1920 |
{
|
| 1921 |
"epoch": 8.15,
|
| 1922 |
-
"learning_rate":
|
| 1923 |
-
"loss": 1.
|
| 1924 |
"step": 28900
|
| 1925 |
},
|
| 1926 |
{
|
| 1927 |
"epoch": 8.17,
|
| 1928 |
-
"learning_rate":
|
| 1929 |
-
"loss": 1.
|
| 1930 |
"step": 29000
|
| 1931 |
},
|
| 1932 |
{
|
| 1933 |
"epoch": 8.2,
|
| 1934 |
-
"learning_rate":
|
| 1935 |
-
"loss": 1.
|
| 1936 |
"step": 29100
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
"epoch": 8.23,
|
| 1940 |
-
"learning_rate":
|
| 1941 |
-
"loss": 1.
|
| 1942 |
"step": 29200
|
| 1943 |
},
|
| 1944 |
{
|
| 1945 |
"epoch": 8.26,
|
| 1946 |
-
"learning_rate":
|
| 1947 |
-
"loss": 1.
|
| 1948 |
"step": 29300
|
| 1949 |
},
|
| 1950 |
{
|
| 1951 |
"epoch": 8.29,
|
| 1952 |
-
"learning_rate":
|
| 1953 |
-
"loss": 1.
|
| 1954 |
"step": 29400
|
| 1955 |
},
|
| 1956 |
{
|
| 1957 |
"epoch": 8.31,
|
| 1958 |
-
"learning_rate":
|
| 1959 |
-
"loss": 1.
|
| 1960 |
"step": 29500
|
| 1961 |
},
|
| 1962 |
{
|
| 1963 |
"epoch": 8.34,
|
| 1964 |
-
"learning_rate":
|
| 1965 |
-
"loss": 1.
|
| 1966 |
"step": 29600
|
| 1967 |
},
|
| 1968 |
{
|
| 1969 |
"epoch": 8.37,
|
| 1970 |
-
"learning_rate":
|
| 1971 |
-
"loss": 1.
|
| 1972 |
"step": 29700
|
| 1973 |
},
|
| 1974 |
{
|
| 1975 |
"epoch": 8.4,
|
| 1976 |
-
"learning_rate":
|
| 1977 |
-
"loss": 1.
|
| 1978 |
"step": 29800
|
| 1979 |
},
|
| 1980 |
{
|
| 1981 |
"epoch": 8.43,
|
| 1982 |
-
"learning_rate":
|
| 1983 |
-
"loss": 1.
|
| 1984 |
"step": 29900
|
| 1985 |
},
|
| 1986 |
{
|
| 1987 |
"epoch": 8.46,
|
| 1988 |
-
"learning_rate":
|
| 1989 |
-
"loss": 1.
|
| 1990 |
"step": 30000
|
| 1991 |
},
|
| 1992 |
{
|
| 1993 |
"epoch": 8.46,
|
| 1994 |
"eval_gen_len": 20.0,
|
| 1995 |
-
"eval_loss": 2.
|
| 1996 |
-
"eval_rouge1": 20.
|
| 1997 |
-
"eval_rouge2": 5.
|
| 1998 |
-
"eval_rougeL": 20.
|
| 1999 |
-
"eval_rougeLsum": 20.
|
| 2000 |
-
"eval_runtime":
|
| 2001 |
-
"eval_samples_per_second":
|
| 2002 |
-
"eval_steps_per_second": 2.
|
| 2003 |
"step": 30000
|
| 2004 |
},
|
| 2005 |
{
|
| 2006 |
"epoch": 8.48,
|
| 2007 |
-
"learning_rate":
|
| 2008 |
-
"loss": 1.
|
| 2009 |
"step": 30100
|
| 2010 |
},
|
| 2011 |
{
|
| 2012 |
"epoch": 8.51,
|
| 2013 |
-
"learning_rate":
|
| 2014 |
-
"loss": 1.
|
| 2015 |
"step": 30200
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
"epoch": 8.54,
|
| 2019 |
-
"learning_rate":
|
| 2020 |
-
"loss": 1.
|
| 2021 |
"step": 30300
|
| 2022 |
},
|
| 2023 |
{
|
| 2024 |
"epoch": 8.57,
|
| 2025 |
-
"learning_rate":
|
| 2026 |
-
"loss": 1.
|
| 2027 |
"step": 30400
|
| 2028 |
},
|
| 2029 |
{
|
| 2030 |
"epoch": 8.6,
|
| 2031 |
-
"learning_rate":
|
| 2032 |
-
"loss": 1.
|
| 2033 |
"step": 30500
|
| 2034 |
},
|
| 2035 |
{
|
| 2036 |
"epoch": 8.62,
|
| 2037 |
-
"learning_rate":
|
| 2038 |
-
"loss": 1.
|
| 2039 |
"step": 30600
|
| 2040 |
},
|
| 2041 |
{
|
| 2042 |
"epoch": 8.65,
|
| 2043 |
-
"learning_rate":
|
| 2044 |
-
"loss": 1.
|
| 2045 |
"step": 30700
|
| 2046 |
},
|
| 2047 |
{
|
| 2048 |
"epoch": 8.68,
|
| 2049 |
-
"learning_rate":
|
| 2050 |
-
"loss": 1.
|
| 2051 |
"step": 30800
|
| 2052 |
},
|
| 2053 |
{
|
| 2054 |
"epoch": 8.71,
|
| 2055 |
-
"learning_rate":
|
| 2056 |
-
"loss": 1.
|
| 2057 |
"step": 30900
|
| 2058 |
},
|
| 2059 |
{
|
| 2060 |
"epoch": 8.74,
|
| 2061 |
-
"learning_rate":
|
| 2062 |
-
"loss": 1.
|
| 2063 |
"step": 31000
|
| 2064 |
},
|
| 2065 |
{
|
| 2066 |
"epoch": 8.77,
|
| 2067 |
-
"learning_rate":
|
| 2068 |
-
"loss": 1.
|
| 2069 |
"step": 31100
|
| 2070 |
},
|
| 2071 |
{
|
| 2072 |
"epoch": 8.79,
|
| 2073 |
-
"learning_rate":
|
| 2074 |
-
"loss": 1.
|
| 2075 |
"step": 31200
|
| 2076 |
},
|
| 2077 |
{
|
| 2078 |
"epoch": 8.82,
|
| 2079 |
-
"learning_rate":
|
| 2080 |
-
"loss": 1.
|
| 2081 |
"step": 31300
|
| 2082 |
},
|
| 2083 |
{
|
| 2084 |
"epoch": 8.85,
|
| 2085 |
-
"learning_rate":
|
| 2086 |
-
"loss": 1.
|
| 2087 |
"step": 31400
|
| 2088 |
},
|
| 2089 |
{
|
| 2090 |
"epoch": 8.88,
|
| 2091 |
-
"learning_rate":
|
| 2092 |
-
"loss": 1.
|
| 2093 |
"step": 31500
|
| 2094 |
},
|
| 2095 |
{
|
| 2096 |
"epoch": 8.91,
|
| 2097 |
-
"learning_rate":
|
| 2098 |
-
"loss": 1.
|
| 2099 |
"step": 31600
|
| 2100 |
},
|
| 2101 |
{
|
| 2102 |
"epoch": 8.93,
|
| 2103 |
-
"learning_rate":
|
| 2104 |
-
"loss": 1.
|
| 2105 |
"step": 31700
|
| 2106 |
},
|
| 2107 |
{
|
| 2108 |
"epoch": 8.96,
|
| 2109 |
-
"learning_rate":
|
| 2110 |
-
"loss": 1.
|
| 2111 |
"step": 31800
|
| 2112 |
},
|
| 2113 |
{
|
| 2114 |
"epoch": 8.99,
|
| 2115 |
-
"learning_rate":
|
| 2116 |
-
"loss": 1.
|
| 2117 |
"step": 31900
|
| 2118 |
},
|
| 2119 |
{
|
| 2120 |
"epoch": 9.02,
|
| 2121 |
-
"learning_rate":
|
| 2122 |
-
"loss":
|
| 2123 |
"step": 32000
|
| 2124 |
},
|
| 2125 |
{
|
| 2126 |
"epoch": 9.02,
|
| 2127 |
"eval_gen_len": 20.0,
|
| 2128 |
-
"eval_loss": 2.
|
| 2129 |
-
"eval_rouge1": 20.
|
| 2130 |
-
"eval_rouge2": 5.
|
| 2131 |
-
"eval_rougeL": 20.
|
| 2132 |
-
"eval_rougeLsum": 20.
|
| 2133 |
-
"eval_runtime":
|
| 2134 |
-
"eval_samples_per_second":
|
| 2135 |
-
"eval_steps_per_second": 2.
|
| 2136 |
"step": 32000
|
| 2137 |
},
|
| 2138 |
{
|
| 2139 |
"epoch": 9.05,
|
| 2140 |
-
"learning_rate":
|
| 2141 |
-
"loss":
|
| 2142 |
"step": 32100
|
| 2143 |
},
|
| 2144 |
{
|
| 2145 |
"epoch": 9.08,
|
| 2146 |
-
"learning_rate":
|
| 2147 |
-
"loss":
|
| 2148 |
"step": 32200
|
| 2149 |
},
|
| 2150 |
{
|
| 2151 |
"epoch": 9.1,
|
| 2152 |
-
"learning_rate":
|
| 2153 |
-
"loss":
|
| 2154 |
"step": 32300
|
| 2155 |
},
|
| 2156 |
{
|
| 2157 |
"epoch": 9.13,
|
| 2158 |
-
"learning_rate":
|
| 2159 |
-
"loss":
|
| 2160 |
"step": 32400
|
| 2161 |
},
|
| 2162 |
{
|
| 2163 |
"epoch": 9.16,
|
| 2164 |
-
"learning_rate":
|
| 2165 |
-
"loss":
|
| 2166 |
"step": 32500
|
| 2167 |
},
|
| 2168 |
{
|
| 2169 |
"epoch": 9.19,
|
| 2170 |
-
"learning_rate":
|
| 2171 |
-
"loss":
|
| 2172 |
"step": 32600
|
| 2173 |
},
|
| 2174 |
{
|
| 2175 |
"epoch": 9.22,
|
| 2176 |
-
"learning_rate":
|
| 2177 |
-
"loss":
|
| 2178 |
"step": 32700
|
| 2179 |
},
|
| 2180 |
{
|
| 2181 |
"epoch": 9.24,
|
| 2182 |
-
"learning_rate":
|
| 2183 |
-
"loss":
|
| 2184 |
"step": 32800
|
| 2185 |
},
|
| 2186 |
{
|
| 2187 |
"epoch": 9.27,
|
| 2188 |
-
"learning_rate":
|
| 2189 |
-
"loss":
|
| 2190 |
"step": 32900
|
| 2191 |
},
|
| 2192 |
{
|
| 2193 |
"epoch": 9.3,
|
| 2194 |
-
"learning_rate":
|
| 2195 |
-
"loss":
|
| 2196 |
"step": 33000
|
| 2197 |
},
|
| 2198 |
{
|
| 2199 |
"epoch": 9.33,
|
| 2200 |
-
"learning_rate":
|
| 2201 |
-
"loss":
|
| 2202 |
"step": 33100
|
| 2203 |
},
|
| 2204 |
{
|
| 2205 |
"epoch": 9.36,
|
| 2206 |
-
"learning_rate":
|
| 2207 |
-
"loss":
|
| 2208 |
"step": 33200
|
| 2209 |
},
|
| 2210 |
{
|
| 2211 |
"epoch": 9.39,
|
| 2212 |
-
"learning_rate":
|
| 2213 |
-
"loss":
|
| 2214 |
"step": 33300
|
| 2215 |
},
|
| 2216 |
{
|
| 2217 |
"epoch": 9.41,
|
| 2218 |
-
"learning_rate":
|
| 2219 |
-
"loss":
|
| 2220 |
"step": 33400
|
| 2221 |
},
|
| 2222 |
{
|
| 2223 |
"epoch": 9.44,
|
| 2224 |
-
"learning_rate":
|
| 2225 |
-
"loss":
|
| 2226 |
"step": 33500
|
| 2227 |
},
|
| 2228 |
{
|
| 2229 |
"epoch": 9.47,
|
| 2230 |
-
"learning_rate":
|
| 2231 |
-
"loss":
|
| 2232 |
"step": 33600
|
| 2233 |
},
|
| 2234 |
{
|
| 2235 |
"epoch": 9.5,
|
| 2236 |
-
"learning_rate":
|
| 2237 |
-
"loss":
|
| 2238 |
"step": 33700
|
| 2239 |
},
|
| 2240 |
{
|
| 2241 |
"epoch": 9.53,
|
| 2242 |
-
"learning_rate":
|
| 2243 |
-
"loss":
|
| 2244 |
"step": 33800
|
| 2245 |
},
|
| 2246 |
{
|
| 2247 |
"epoch": 9.55,
|
| 2248 |
-
"learning_rate":
|
| 2249 |
-
"loss":
|
| 2250 |
"step": 33900
|
| 2251 |
},
|
| 2252 |
{
|
| 2253 |
"epoch": 9.58,
|
| 2254 |
-
"learning_rate":
|
| 2255 |
-
"loss":
|
| 2256 |
"step": 34000
|
| 2257 |
},
|
| 2258 |
{
|
| 2259 |
"epoch": 9.58,
|
| 2260 |
"eval_gen_len": 20.0,
|
| 2261 |
-
"eval_loss": 2.
|
| 2262 |
-
"eval_rouge1": 21.
|
| 2263 |
-
"eval_rouge2": 5.
|
| 2264 |
-
"eval_rougeL":
|
| 2265 |
-
"eval_rougeLsum":
|
| 2266 |
-
"eval_runtime":
|
| 2267 |
-
"eval_samples_per_second":
|
| 2268 |
-
"eval_steps_per_second": 2.
|
| 2269 |
"step": 34000
|
| 2270 |
},
|
| 2271 |
{
|
| 2272 |
"epoch": 9.61,
|
| 2273 |
-
"learning_rate":
|
| 2274 |
-
"loss":
|
| 2275 |
"step": 34100
|
| 2276 |
},
|
| 2277 |
{
|
| 2278 |
"epoch": 9.64,
|
| 2279 |
-
"learning_rate":
|
| 2280 |
-
"loss":
|
| 2281 |
"step": 34200
|
| 2282 |
},
|
| 2283 |
{
|
| 2284 |
"epoch": 9.67,
|
| 2285 |
-
"learning_rate":
|
| 2286 |
-
"loss":
|
| 2287 |
"step": 34300
|
| 2288 |
},
|
| 2289 |
{
|
| 2290 |
"epoch": 9.7,
|
| 2291 |
-
"learning_rate":
|
| 2292 |
-
"loss":
|
| 2293 |
"step": 34400
|
| 2294 |
},
|
| 2295 |
{
|
| 2296 |
"epoch": 9.72,
|
| 2297 |
-
"learning_rate":
|
| 2298 |
-
"loss":
|
| 2299 |
"step": 34500
|
| 2300 |
},
|
| 2301 |
{
|
| 2302 |
"epoch": 9.75,
|
| 2303 |
-
"learning_rate":
|
| 2304 |
-
"loss":
|
| 2305 |
"step": 34600
|
| 2306 |
},
|
| 2307 |
{
|
| 2308 |
"epoch": 9.78,
|
| 2309 |
-
"learning_rate":
|
| 2310 |
-
"loss":
|
| 2311 |
"step": 34700
|
| 2312 |
},
|
| 2313 |
{
|
| 2314 |
"epoch": 9.81,
|
| 2315 |
-
"learning_rate":
|
| 2316 |
-
"loss":
|
| 2317 |
"step": 34800
|
| 2318 |
},
|
| 2319 |
{
|
| 2320 |
"epoch": 9.84,
|
| 2321 |
-
"learning_rate":
|
| 2322 |
-
"loss":
|
| 2323 |
"step": 34900
|
| 2324 |
},
|
| 2325 |
{
|
| 2326 |
"epoch": 9.86,
|
| 2327 |
-
"learning_rate":
|
| 2328 |
-
"loss":
|
| 2329 |
"step": 35000
|
| 2330 |
},
|
| 2331 |
{
|
| 2332 |
"epoch": 9.89,
|
| 2333 |
-
"learning_rate":
|
| 2334 |
-
"loss":
|
| 2335 |
"step": 35100
|
| 2336 |
},
|
| 2337 |
{
|
| 2338 |
"epoch": 9.92,
|
| 2339 |
-
"learning_rate":
|
| 2340 |
-
"loss":
|
| 2341 |
"step": 35200
|
| 2342 |
},
|
| 2343 |
{
|
| 2344 |
"epoch": 9.95,
|
| 2345 |
-
"learning_rate":
|
| 2346 |
-
"loss":
|
| 2347 |
"step": 35300
|
| 2348 |
},
|
| 2349 |
{
|
| 2350 |
"epoch": 9.98,
|
| 2351 |
-
"learning_rate":
|
| 2352 |
-
"loss":
|
| 2353 |
"step": 35400
|
| 2354 |
},
|
| 2355 |
{
|
| 2356 |
"epoch": 10.0,
|
| 2357 |
"step": 35480,
|
| 2358 |
"total_flos": 2.3762843604025344e+17,
|
| 2359 |
-
"train_loss": 1.
|
| 2360 |
-
"train_runtime":
|
| 2361 |
-
"train_samples_per_second":
|
| 2362 |
-
"train_steps_per_second": 2.
|
| 2363 |
}
|
| 2364 |
],
|
| 2365 |
"max_steps": 35480,
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 1.9633301496505737,
|
| 3 |
+
"best_model_checkpoint": "output/checkpoint-6000",
|
| 4 |
"epoch": 10.0,
|
| 5 |
"global_step": 35480,
|
| 6 |
"is_hyper_param_search": false,
|
|
|
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 1.1231131887499657e-07,
|
| 13 |
+
"loss": 2.472,
|
| 14 |
"step": 100
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 2.5441897566929925e-05,
|
| 19 |
+
"loss": 2.3979,
|
| 20 |
"step": 200
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 0.08,
|
| 24 |
+
"learning_rate": 1.0307801958256833e-07,
|
| 25 |
+
"loss": 2.3356,
|
| 26 |
"step": 300
|
| 27 |
},
|
| 28 |
{
|
| 29 |
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 4.2830331047183876e-05,
|
| 31 |
+
"loss": 2.3626,
|
| 32 |
"step": 400
|
| 33 |
},
|
| 34 |
{
|
| 35 |
"epoch": 0.14,
|
| 36 |
+
"learning_rate": 2.5245954827173344e-05,
|
| 37 |
+
"loss": 2.3347,
|
| 38 |
"step": 500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
"epoch": 0.17,
|
| 42 |
+
"learning_rate": 7.54679092701715e-06,
|
| 43 |
+
"loss": 2.3057,
|
| 44 |
"step": 600
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.2,
|
| 48 |
+
"learning_rate": 1.007695167624979e-07,
|
| 49 |
+
"loss": 2.264,
|
| 50 |
"step": 700
|
| 51 |
},
|
| 52 |
{
|
| 53 |
"epoch": 0.23,
|
| 54 |
+
"learning_rate": 4.813811122230701e-05,
|
| 55 |
+
"loss": 2.2884,
|
| 56 |
"step": 800
|
| 57 |
},
|
| 58 |
{
|
| 59 |
"epoch": 0.25,
|
| 60 |
+
"learning_rate": 4.276145918519949e-05,
|
| 61 |
+
"loss": 2.3137,
|
| 62 |
"step": 900
|
| 63 |
},
|
| 64 |
{
|
| 65 |
"epoch": 0.28,
|
| 66 |
+
"learning_rate": 3.468839804192268e-05,
|
| 67 |
+
"loss": 2.3233,
|
| 68 |
"step": 1000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
"epoch": 0.31,
|
| 72 |
+
"learning_rate": 2.514797816905896e-05,
|
| 73 |
+
"loss": 2.2754,
|
| 74 |
"step": 1100
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.34,
|
| 78 |
+
"learning_rate": 1.559264200813033e-05,
|
| 79 |
+
"loss": 2.2508,
|
| 80 |
"step": 1200
|
| 81 |
},
|
| 82 |
{
|
| 83 |
"epoch": 0.37,
|
| 84 |
+
"learning_rate": 7.54679092701715e-06,
|
| 85 |
+
"loss": 2.2591,
|
| 86 |
"step": 1300
|
| 87 |
},
|
| 88 |
{
|
| 89 |
"epoch": 0.39,
|
| 90 |
+
"learning_rate": 2.0749052704813964e-06,
|
| 91 |
+
"loss": 2.231,
|
| 92 |
"step": 1400
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 0.42,
|
| 96 |
+
"learning_rate": 1.007695167624979e-07,
|
| 97 |
+
"loss": 2.2262,
|
| 98 |
"step": 1500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 0.45,
|
| 102 |
+
"learning_rate": 4.953951865520701e-05,
|
| 103 |
+
"loss": 2.2988,
|
| 104 |
"step": 1600
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.48,
|
| 108 |
+
"learning_rate": 4.813811122230701e-05,
|
| 109 |
+
"loss": 2.2338,
|
| 110 |
"step": 1700
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 0.51,
|
| 114 |
+
"learning_rate": 4.5849440623095696e-05,
|
| 115 |
+
"loss": 2.2921,
|
| 116 |
"step": 1800
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 0.54,
|
| 120 |
+
"learning_rate": 4.276145918519949e-05,
|
| 121 |
+
"loss": 2.2703,
|
| 122 |
"step": 1900
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 0.56,
|
| 126 |
+
"learning_rate": 3.8992836303516824e-05,
|
| 127 |
+
"loss": 2.2635,
|
| 128 |
"step": 2000
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 0.56,
|
| 132 |
"eval_gen_len": 20.0,
|
| 133 |
+
"eval_loss": 2.061249256134033,
|
| 134 |
+
"eval_rouge1": 21.7272,
|
| 135 |
+
"eval_rouge2": 5.8776,
|
| 136 |
+
"eval_rougeL": 21.533,
|
| 137 |
+
"eval_rougeLsum": 21.5147,
|
| 138 |
+
"eval_runtime": 165.5553,
|
| 139 |
+
"eval_samples_per_second": 42.33,
|
| 140 |
+
"eval_steps_per_second": 2.646,
|
| 141 |
"step": 2000
|
| 142 |
},
|
| 143 |
{
|
| 144 |
"epoch": 0.59,
|
| 145 |
+
"learning_rate": 3.468839804192268e-05,
|
| 146 |
+
"loss": 2.2318,
|
| 147 |
"step": 2100
|
| 148 |
},
|
| 149 |
{
|
| 150 |
"epoch": 0.62,
|
| 151 |
+
"learning_rate": 3.001356154885334e-05,
|
| 152 |
+
"loss": 2.1998,
|
| 153 |
"step": 2200
|
| 154 |
},
|
| 155 |
{
|
| 156 |
"epoch": 0.65,
|
| 157 |
+
"learning_rate": 2.514797816905896e-05,
|
| 158 |
+
"loss": 2.2198,
|
| 159 |
"step": 2300
|
| 160 |
},
|
| 161 |
{
|
| 162 |
"epoch": 0.68,
|
| 163 |
+
"learning_rate": 2.027862954317443e-05,
|
| 164 |
+
"loss": 2.1908,
|
| 165 |
"step": 2400
|
| 166 |
},
|
| 167 |
{
|
| 168 |
"epoch": 0.7,
|
| 169 |
+
"learning_rate": 1.559264200813033e-05,
|
| 170 |
+
"loss": 2.2039,
|
| 171 |
"step": 2500
|
| 172 |
},
|
| 173 |
{
|
| 174 |
"epoch": 0.73,
|
| 175 |
+
"learning_rate": 1.1270095436966314e-05,
|
| 176 |
+
"loss": 2.1967,
|
| 177 |
"step": 2600
|
| 178 |
},
|
| 179 |
{
|
| 180 |
"epoch": 0.76,
|
| 181 |
+
"learning_rate": 7.477102870300167e-06,
|
| 182 |
+
"loss": 2.1736,
|
| 183 |
"step": 2700
|
| 184 |
},
|
| 185 |
{
|
| 186 |
"epoch": 0.79,
|
| 187 |
+
"learning_rate": 4.359426885334149e-06,
|
| 188 |
+
"loss": 2.1954,
|
| 189 |
"step": 2800
|
| 190 |
},
|
| 191 |
{
|
| 192 |
"epoch": 0.82,
|
| 193 |
+
"learning_rate": 2.0368780217576533e-06,
|
| 194 |
+
"loss": 2.1828,
|
| 195 |
"step": 2900
|
| 196 |
},
|
| 197 |
{
|
| 198 |
"epoch": 0.85,
|
| 199 |
+
"learning_rate": 5.987105298975171e-07,
|
| 200 |
+
"loss": 2.1688,
|
| 201 |
"step": 3000
|
| 202 |
},
|
| 203 |
{
|
| 204 |
"epoch": 0.87,
|
| 205 |
+
"learning_rate": 1.0019237993230962e-07,
|
| 206 |
+
"loss": 2.1516,
|
| 207 |
"step": 3100
|
| 208 |
},
|
| 209 |
{
|
| 210 |
"epoch": 0.9,
|
| 211 |
+
"learning_rate": 4.9886953900836016e-05,
|
| 212 |
+
"loss": 2.2263,
|
| 213 |
"step": 3200
|
| 214 |
},
|
| 215 |
{
|
| 216 |
"epoch": 0.93,
|
| 217 |
+
"learning_rate": 4.953482257211965e-05,
|
| 218 |
+
"loss": 2.1939,
|
| 219 |
"step": 3300
|
| 220 |
},
|
| 221 |
{
|
| 222 |
"epoch": 0.96,
|
| 223 |
+
"learning_rate": 4.8946889017268244e-05,
|
| 224 |
+
"loss": 2.2039,
|
| 225 |
"step": 3400
|
| 226 |
},
|
| 227 |
{
|
| 228 |
"epoch": 0.99,
|
| 229 |
+
"learning_rate": 4.8128815357812196e-05,
|
| 230 |
+
"loss": 2.1897,
|
| 231 |
"step": 3500
|
| 232 |
},
|
| 233 |
{
|
| 234 |
"epoch": 1.01,
|
| 235 |
+
"learning_rate": 4.708848009029661e-05,
|
| 236 |
+
"loss": 2.1036,
|
| 237 |
"step": 3600
|
| 238 |
},
|
| 239 |
{
|
| 240 |
"epoch": 1.04,
|
| 241 |
+
"learning_rate": 4.583590221205278e-05,
|
| 242 |
+
"loss": 2.0092,
|
| 243 |
"step": 3700
|
| 244 |
},
|
| 245 |
{
|
| 246 |
"epoch": 1.07,
|
| 247 |
+
"learning_rate": 4.43831447327769e-05,
|
| 248 |
+
"loss": 2.0428,
|
| 249 |
"step": 3800
|
| 250 |
},
|
| 251 |
{
|
| 252 |
"epoch": 1.1,
|
| 253 |
+
"learning_rate": 4.2744198501152435e-05,
|
| 254 |
+
"loss": 2.0471,
|
| 255 |
"step": 3900
|
| 256 |
},
|
| 257 |
{
|
| 258 |
"epoch": 1.13,
|
| 259 |
+
"learning_rate": 4.093484746532906e-05,
|
| 260 |
+
"loss": 2.0365,
|
| 261 |
"step": 4000
|
| 262 |
},
|
| 263 |
{
|
| 264 |
"epoch": 1.13,
|
| 265 |
"eval_gen_len": 20.0,
|
| 266 |
+
"eval_loss": 2.034134864807129,
|
| 267 |
+
"eval_rouge1": 21.7168,
|
| 268 |
+
"eval_rouge2": 5.7378,
|
| 269 |
+
"eval_rougeL": 21.5563,
|
| 270 |
+
"eval_rougeLsum": 21.552,
|
| 271 |
+
"eval_runtime": 164.9689,
|
| 272 |
+
"eval_samples_per_second": 42.481,
|
| 273 |
+
"eval_steps_per_second": 2.655,
|
| 274 |
"step": 4000
|
| 275 |
},
|
| 276 |
{
|
| 277 |
"epoch": 1.16,
|
| 278 |
+
"learning_rate": 3.897251666487364e-05,
|
| 279 |
+
"loss": 2.0227,
|
| 280 |
"step": 4100
|
| 281 |
},
|
| 282 |
{
|
| 283 |
"epoch": 1.18,
|
| 284 |
+
"learning_rate": 3.68761044181137e-05,
|
| 285 |
+
"loss": 2.0152,
|
| 286 |
"step": 4200
|
| 287 |
},
|
| 288 |
{
|
| 289 |
"epoch": 1.21,
|
| 290 |
+
"learning_rate": 3.4665800321001055e-05,
|
| 291 |
+
"loss": 2.0071,
|
| 292 |
"step": 4300
|
| 293 |
},
|
| 294 |
{
|
| 295 |
"epoch": 1.24,
|
| 296 |
+
"learning_rate": 3.2362890810266e-05,
|
| 297 |
+
"loss": 2.0391,
|
| 298 |
"step": 4400
|
| 299 |
},
|
| 300 |
{
|
| 301 |
"epoch": 1.27,
|
| 302 |
+
"learning_rate": 2.9989554163395335e-05,
|
| 303 |
+
"loss": 2.0197,
|
| 304 |
"step": 4500
|
| 305 |
},
|
| 306 |
{
|
| 307 |
"epoch": 1.3,
|
| 308 |
+
"learning_rate": 2.7568646909696192e-05,
|
| 309 |
+
"loss": 1.9765,
|
| 310 |
"step": 4600
|
| 311 |
},
|
| 312 |
{
|
| 313 |
"epoch": 1.32,
|
| 314 |
+
"learning_rate": 2.512348370942422e-05,
|
| 315 |
+
"loss": 1.9761,
|
| 316 |
"step": 4700
|
| 317 |
},
|
| 318 |
{
|
| 319 |
"epoch": 1.35,
|
| 320 |
+
"learning_rate": 2.2677612820860213e-05,
|
| 321 |
+
"loss": 1.992,
|
| 322 |
"step": 4800
|
| 323 |
},
|
| 324 |
{
|
| 325 |
"epoch": 1.38,
|
| 326 |
+
"learning_rate": 2.0254589317710082e-05,
|
| 327 |
+
"loss": 2.0143,
|
| 328 |
"step": 4900
|
| 329 |
},
|
| 330 |
{
|
| 331 |
"epoch": 1.41,
|
| 332 |
+
"learning_rate": 1.7877748240868528e-05,
|
| 333 |
+
"loss": 1.9675,
|
| 334 |
"step": 5000
|
| 335 |
},
|
| 336 |
{
|
| 337 |
"epoch": 1.44,
|
| 338 |
+
"learning_rate": 1.556997986921904e-05,
|
| 339 |
+
"loss": 2.0144,
|
| 340 |
"step": 5100
|
| 341 |
},
|
| 342 |
{
|
| 343 |
"epoch": 1.47,
|
| 344 |
+
"learning_rate": 1.3353509273735138e-05,
|
| 345 |
+
"loss": 2.0131,
|
| 346 |
"step": 5200
|
| 347 |
},
|
| 348 |
{
|
| 349 |
"epoch": 1.49,
|
| 350 |
+
"learning_rate": 1.1249682277897386e-05,
|
| 351 |
+
"loss": 1.9536,
|
| 352 |
"step": 5300
|
| 353 |
},
|
| 354 |
{
|
| 355 |
"epoch": 1.52,
|
| 356 |
+
"learning_rate": 9.278759885744533e-06,
|
| 357 |
+
"loss": 1.989,
|
| 358 |
"step": 5400
|
| 359 |
},
|
| 360 |
{
|
| 361 |
"epoch": 1.55,
|
| 362 |
+
"learning_rate": 7.45972315732879e-06,
|
| 363 |
+
"loss": 1.9796,
|
| 364 |
"step": 5500
|
| 365 |
},
|
| 366 |
{
|
| 367 |
"epoch": 1.58,
|
| 368 |
+
"learning_rate": 5.810090410731417e-06,
|
| 369 |
+
"loss": 1.9478,
|
| 370 |
"step": 5600
|
| 371 |
},
|
| 372 |
{
|
| 373 |
"epoch": 1.61,
|
| 374 |
+
"learning_rate": 4.345748511083142e-06,
|
| 375 |
+
"loss": 1.9681,
|
| 376 |
"step": 5700
|
| 377 |
},
|
| 378 |
{
|
| 379 |
"epoch": 1.63,
|
| 380 |
+
"learning_rate": 3.08079987136829e-06,
|
| 381 |
+
"loss": 1.9642,
|
| 382 |
"step": 5800
|
| 383 |
},
|
| 384 |
{
|
| 385 |
"epoch": 1.66,
|
| 386 |
+
"learning_rate": 2.027426638478571e-06,
|
| 387 |
+
"loss": 1.983,
|
| 388 |
"step": 5900
|
| 389 |
},
|
| 390 |
{
|
| 391 |
"epoch": 1.69,
|
| 392 |
+
"learning_rate": 1.1957733724791018e-06,
|
| 393 |
+
"loss": 1.9847,
|
| 394 |
"step": 6000
|
| 395 |
},
|
| 396 |
{
|
| 397 |
"epoch": 1.69,
|
| 398 |
"eval_gen_len": 20.0,
|
| 399 |
+
"eval_loss": 1.9633301496505737,
|
| 400 |
+
"eval_rouge1": 22.6551,
|
| 401 |
+
"eval_rouge2": 6.1328,
|
| 402 |
+
"eval_rougeL": 22.457,
|
| 403 |
+
"eval_rougeLsum": 22.4619,
|
| 404 |
+
"eval_runtime": 165.0565,
|
| 405 |
+
"eval_samples_per_second": 42.458,
|
| 406 |
+
"eval_steps_per_second": 2.654,
|
| 407 |
"step": 6000
|
| 408 |
},
|
| 409 |
{
|
| 410 |
"epoch": 1.72,
|
| 411 |
+
"learning_rate": 5.938493489493758e-07,
|
| 412 |
+
"loss": 1.9596,
|
| 413 |
"step": 6100
|
| 414 |
},
|
| 415 |
{
|
| 416 |
"epoch": 1.75,
|
| 417 |
+
"learning_rate": 2.27451425281131e-07,
|
| 418 |
+
"loss": 1.9612,
|
| 419 |
"step": 6200
|
| 420 |
},
|
| 421 |
{
|
| 422 |
"epoch": 1.78,
|
| 423 |
+
"learning_rate": 1.0010821377276459e-07,
|
| 424 |
+
"loss": 1.9514,
|
| 425 |
"step": 6300
|
| 426 |
},
|
| 427 |
{
|
| 428 |
"epoch": 1.8,
|
| 429 |
+
"learning_rate": 4.99717224507643e-05,
|
| 430 |
+
"loss": 1.986,
|
| 431 |
"step": 6400
|
| 432 |
},
|
| 433 |
{
|
| 434 |
"epoch": 1.83,
|
| 435 |
+
"learning_rate": 4.988343334271749e-05,
|
| 436 |
+
"loss": 2.0322,
|
| 437 |
"step": 6500
|
| 438 |
},
|
| 439 |
{
|
| 440 |
"epoch": 1.86,
|
| 441 |
+
"learning_rate": 4.9735318318596204e-05,
|
| 442 |
+
"loss": 2.0483,
|
| 443 |
"step": 6600
|
| 444 |
},
|
| 445 |
{
|
| 446 |
"epoch": 1.89,
|
| 447 |
+
"learning_rate": 4.9527734200466905e-05,
|
| 448 |
+
"loss": 2.0378,
|
| 449 |
"step": 6700
|
| 450 |
},
|
| 451 |
{
|
| 452 |
"epoch": 1.92,
|
| 453 |
+
"learning_rate": 4.926118107665238e-05,
|
| 454 |
+
"loss": 2.012,
|
| 455 |
"step": 6800
|
| 456 |
},
|
| 457 |
{
|
| 458 |
"epoch": 1.94,
|
| 459 |
+
"learning_rate": 4.893983616044946e-05,
|
| 460 |
+
"loss": 2.0259,
|
| 461 |
"step": 6900
|
| 462 |
},
|
| 463 |
{
|
| 464 |
"epoch": 1.97,
|
| 465 |
+
"learning_rate": 4.8557983100045764e-05,
|
| 466 |
+
"loss": 2.0511,
|
| 467 |
"step": 7000
|
| 468 |
},
|
| 469 |
{
|
| 470 |
"epoch": 2.0,
|
| 471 |
+
"learning_rate": 4.811949724929791e-05,
|
| 472 |
+
"loss": 2.0332,
|
| 473 |
"step": 7100
|
| 474 |
},
|
| 475 |
{
|
| 476 |
"epoch": 2.03,
|
| 477 |
+
"learning_rate": 4.762543495902719e-05,
|
| 478 |
+
"loss": 1.8404,
|
| 479 |
"step": 7200
|
| 480 |
},
|
| 481 |
{
|
| 482 |
"epoch": 2.06,
|
| 483 |
+
"learning_rate": 4.707698646856561e-05,
|
| 484 |
+
"loss": 1.8565,
|
| 485 |
"step": 7300
|
| 486 |
},
|
| 487 |
{
|
| 488 |
"epoch": 2.09,
|
| 489 |
+
"learning_rate": 4.64754730383651e-05,
|
| 490 |
+
"loss": 1.8571,
|
| 491 |
"step": 7400
|
| 492 |
},
|
| 493 |
{
|
| 494 |
"epoch": 2.11,
|
| 495 |
+
"learning_rate": 4.582234376696538e-05,
|
| 496 |
+
"loss": 1.8639,
|
| 497 |
"step": 7500
|
| 498 |
},
|
| 499 |
{
|
| 500 |
"epoch": 2.14,
|
| 501 |
+
"learning_rate": 4.511917209998861e-05,
|
| 502 |
+
"loss": 1.9017,
|
| 503 |
"step": 7600
|
| 504 |
},
|
| 505 |
{
|
| 506 |
"epoch": 2.17,
|
| 507 |
+
"learning_rate": 4.43676520395711e-05,
|
| 508 |
+
"loss": 1.8625,
|
| 509 |
"step": 7700
|
| 510 |
},
|
| 511 |
{
|
| 512 |
"epoch": 2.2,
|
| 513 |
+
"learning_rate": 4.3569594063363784e-05,
|
| 514 |
+
"loss": 1.8604,
|
| 515 |
"step": 7800
|
| 516 |
},
|
| 517 |
{
|
| 518 |
"epoch": 2.23,
|
| 519 |
+
"learning_rate": 4.2726920762932964e-05,
|
| 520 |
+
"loss": 1.8748,
|
| 521 |
"step": 7900
|
| 522 |
},
|
| 523 |
{
|
| 524 |
"epoch": 2.25,
|
| 525 |
+
"learning_rate": 4.1841662212068846e-05,
|
| 526 |
+
"loss": 1.861,
|
| 527 |
"step": 8000
|
| 528 |
},
|
| 529 |
{
|
| 530 |
"epoch": 2.25,
|
| 531 |
"eval_gen_len": 20.0,
|
| 532 |
+
"eval_loss": 2.010927438735962,
|
| 533 |
+
"eval_rouge1": 21.5977,
|
| 534 |
+
"eval_rouge2": 5.9659,
|
| 535 |
+
"eval_rougeL": 21.4021,
|
| 536 |
+
"eval_rougeLsum": 21.3731,
|
| 537 |
+
"eval_runtime": 165.7344,
|
| 538 |
+
"eval_samples_per_second": 42.285,
|
| 539 |
+
"eval_steps_per_second": 2.643,
|
| 540 |
"step": 8000
|
| 541 |
},
|
| 542 |
{
|
| 543 |
"epoch": 2.28,
|
| 544 |
+
"learning_rate": 4.091595107615995e-05,
|
| 545 |
+
"loss": 1.8498,
|
| 546 |
"step": 8100
|
| 547 |
},
|
| 548 |
{
|
| 549 |
"epoch": 2.31,
|
| 550 |
+
"learning_rate": 3.99520174744154e-05,
|
| 551 |
+
"loss": 1.8755,
|
| 552 |
"step": 8200
|
| 553 |
},
|
| 554 |
{
|
| 555 |
"epoch": 2.34,
|
| 556 |
+
"learning_rate": 3.895218360731241e-05,
|
| 557 |
+
"loss": 1.8772,
|
| 558 |
"step": 8300
|
| 559 |
},
|
| 560 |
{
|
| 561 |
"epoch": 2.37,
|
| 562 |
+
"learning_rate": 3.791885816221194e-05,
|
| 563 |
+
"loss": 1.8761,
|
| 564 |
"step": 8400
|
| 565 |
},
|
| 566 |
{
|
| 567 |
"epoch": 2.4,
|
| 568 |
+
"learning_rate": 3.6854530510619846e-05,
|
| 569 |
+
"loss": 1.879,
|
| 570 |
"step": 8500
|
| 571 |
},
|
| 572 |
{
|
| 573 |
"epoch": 2.42,
|
| 574 |
+
"learning_rate": 3.576176471107291e-05,
|
| 575 |
+
"loss": 1.8655,
|
| 576 |
"step": 8600
|
| 577 |
},
|
| 578 |
{
|
| 579 |
"epoch": 2.45,
|
| 580 |
+
"learning_rate": 3.4643193332097226e-05,
|
| 581 |
+
"loss": 1.8636,
|
| 582 |
"step": 8700
|
| 583 |
},
|
| 584 |
{
|
| 585 |
"epoch": 2.48,
|
| 586 |
+
"learning_rate": 3.350151111012003e-05,
|
| 587 |
+
"loss": 1.896,
|
| 588 |
"step": 8800
|
| 589 |
},
|
| 590 |
{
|
| 591 |
"epoch": 2.51,
|
| 592 |
+
"learning_rate": 3.23394684576136e-05,
|
| 593 |
+
"loss": 1.8561,
|
| 594 |
"step": 8900
|
| 595 |
},
|
| 596 |
{
|
| 597 |
"epoch": 2.54,
|
| 598 |
+
"learning_rate": 3.115986483711075e-05,
|
| 599 |
+
"loss": 1.8555,
|
| 600 |
"step": 9000
|
| 601 |
},
|
| 602 |
{
|
| 603 |
"epoch": 2.56,
|
| 604 |
+
"learning_rate": 2.9965542017054346e-05,
|
| 605 |
+
"loss": 1.8629,
|
| 606 |
"step": 9100
|
| 607 |
},
|
| 608 |
{
|
| 609 |
"epoch": 2.59,
|
| 610 |
+
"learning_rate": 2.8759377225728234e-05,
|
| 611 |
+
"loss": 1.8816,
|
| 612 |
"step": 9200
|
| 613 |
},
|
| 614 |
{
|
| 615 |
"epoch": 2.62,
|
| 616 |
+
"learning_rate": 2.7544276219762262e-05,
|
| 617 |
+
"loss": 1.8372,
|
| 618 |
"step": 9300
|
| 619 |
},
|
| 620 |
{
|
| 621 |
"epoch": 2.65,
|
| 622 |
+
"learning_rate": 2.632316628391009e-05,
|
| 623 |
+
"loss": 1.8493,
|
| 624 |
"step": 9400
|
| 625 |
},
|
| 626 |
{
|
| 627 |
"epoch": 2.68,
|
| 628 |
+
"learning_rate": 2.5098989178963792e-05,
|
| 629 |
+
"loss": 1.8573,
|
| 630 |
"step": 9500
|
| 631 |
},
|
| 632 |
{
|
| 633 |
"epoch": 2.71,
|
| 634 |
+
"learning_rate": 2.3874694054794416e-05,
|
| 635 |
+
"loss": 1.8587,
|
| 636 |
"step": 9600
|
| 637 |
},
|
| 638 |
{
|
| 639 |
"epoch": 2.73,
|
| 640 |
+
"learning_rate": 2.2653230345591686e-05,
|
| 641 |
+
"loss": 1.8501,
|
| 642 |
"step": 9700
|
| 643 |
},
|
| 644 |
{
|
| 645 |
"epoch": 2.76,
|
| 646 |
+
"learning_rate": 2.143754066441865e-05,
|
| 647 |
+
"loss": 1.8655,
|
| 648 |
"step": 9800
|
| 649 |
},
|
| 650 |
{
|
| 651 |
"epoch": 2.79,
|
| 652 |
+
"learning_rate": 2.02305537141991e-05,
|
| 653 |
+
"loss": 1.8599,
|
| 654 |
"step": 9900
|
| 655 |
},
|
| 656 |
{
|
| 657 |
"epoch": 2.82,
|
| 658 |
+
"learning_rate": 1.9035177232215682e-05,
|
| 659 |
+
"loss": 1.8634,
|
| 660 |
"step": 10000
|
| 661 |
},
|
| 662 |
{
|
| 663 |
"epoch": 2.82,
|
| 664 |
"eval_gen_len": 20.0,
|
| 665 |
+
"eval_loss": 1.9686568975448608,
|
| 666 |
+
"eval_rouge1": 22.5506,
|
| 667 |
+
"eval_rouge2": 6.0881,
|
| 668 |
+
"eval_rougeL": 22.4021,
|
| 669 |
+
"eval_rougeLsum": 22.3998,
|
| 670 |
+
"eval_runtime": 164.864,
|
| 671 |
+
"eval_samples_per_second": 42.508,
|
| 672 |
+
"eval_steps_per_second": 2.657,
|
| 673 |
"step": 10000
|
| 674 |
},
|
| 675 |
{
|
| 676 |
"epoch": 2.85,
|
| 677 |
+
"learning_rate": 1.7854290985116118e-05,
|
| 678 |
+
"loss": 1.8382,
|
| 679 |
"step": 10100
|
| 680 |
},
|
| 681 |
{
|
| 682 |
"epoch": 2.87,
|
| 683 |
+
"learning_rate": 1.669073983130307e-05,
|
| 684 |
+
"loss": 1.8459,
|
| 685 |
"step": 10200
|
| 686 |
},
|
| 687 |
{
|
| 688 |
"epoch": 2.9,
|
| 689 |
+
"learning_rate": 1.5547326867421132e-05,
|
| 690 |
+
"loss": 1.8562,
|
| 691 |
"step": 10300
|
| 692 |
},
|
| 693 |
{
|
| 694 |
"epoch": 2.93,
|
| 695 |
+
"learning_rate": 1.4426806675451438e-05,
|
| 696 |
+
"loss": 1.8404,
|
| 697 |
"step": 10400
|
| 698 |
},
|
| 699 |
{
|
| 700 |
"epoch": 2.96,
|
| 701 |
+
"learning_rate": 1.3331878686682424e-05,
|
| 702 |
+
"loss": 1.8492,
|
| 703 |
"step": 10500
|
| 704 |
},
|
| 705 |
{
|
| 706 |
"epoch": 2.99,
|
| 707 |
+
"learning_rate": 1.2265180678543392e-05,
|
| 708 |
+
"loss": 1.8172,
|
| 709 |
"step": 10600
|
| 710 |
},
|
| 711 |
{
|
| 712 |
"epoch": 3.02,
|
| 713 |
+
"learning_rate": 1.1229282419967673e-05,
|
| 714 |
+
"loss": 1.7255,
|
| 715 |
"step": 10700
|
| 716 |
},
|
| 717 |
{
|
| 718 |
"epoch": 3.04,
|
| 719 |
+
"learning_rate": 1.022667948059414e-05,
|
| 720 |
+
"loss": 1.6157,
|
| 721 |
"step": 10800
|
| 722 |
},
|
| 723 |
{
|
| 724 |
"epoch": 3.07,
|
| 725 |
+
"learning_rate": 9.25978721872139e-06,
|
| 726 |
+
"loss": 1.6024,
|
| 727 |
"step": 10900
|
| 728 |
},
|
| 729 |
{
|
| 730 |
"epoch": 3.1,
|
| 731 |
+
"learning_rate": 8.330934962498027e-06,
|
| 732 |
+
"loss": 1.5984,
|
| 733 |
"step": 11000
|
| 734 |
},
|
| 735 |
{
|
| 736 |
"epoch": 3.13,
|
| 737 |
+
"learning_rate": 7.442360398367151e-06,
|
| 738 |
+
"loss": 1.6075,
|
| 739 |
"step": 11100
|
| 740 |
},
|
| 741 |
{
|
| 742 |
"epoch": 3.16,
|
| 743 |
+
"learning_rate": 6.596204180283686e-06,
|
| 744 |
+
"loss": 1.5859,
|
| 745 |
"step": 11200
|
| 746 |
},
|
| 747 |
{
|
| 748 |
"epoch": 3.18,
|
| 749 |
+
"learning_rate": 5.79450477269154e-06,
|
| 750 |
+
"loss": 1.5973,
|
| 751 |
"step": 11300
|
| 752 |
},
|
| 753 |
{
|
| 754 |
"epoch": 3.21,
|
| 755 |
+
"learning_rate": 5.039193539684164e-06,
|
| 756 |
+
"loss": 1.6132,
|
| 757 |
"step": 11400
|
| 758 |
},
|
| 759 |
{
|
| 760 |
"epoch": 3.24,
|
| 761 |
+
"learning_rate": 4.332090092179324e-06,
|
| 762 |
+
"loss": 1.6221,
|
| 763 |
"step": 11500
|
| 764 |
},
|
| 765 |
{
|
| 766 |
"epoch": 3.27,
|
| 767 |
+
"learning_rate": 3.6748979043170137e-06,
|
| 768 |
+
"loss": 1.6258,
|
| 769 |
"step": 11600
|
| 770 |
},
|
| 771 |
{
|
| 772 |
"epoch": 3.3,
|
| 773 |
+
"learning_rate": 3.0692002096410223e-06,
|
| 774 |
+
"loss": 1.6149,
|
| 775 |
"step": 11700
|
| 776 |
},
|
| 777 |
{
|
| 778 |
"epoch": 3.33,
|
| 779 |
+
"learning_rate": 2.516456186950684e-06,
|
| 780 |
+
"loss": 1.624,
|
| 781 |
"step": 11800
|
| 782 |
},
|
| 783 |
{
|
| 784 |
"epoch": 3.35,
|
| 785 |
+
"learning_rate": 2.0179974450113125e-06,
|
| 786 |
+
"loss": 1.6138,
|
| 787 |
"step": 11900
|
| 788 |
},
|
| 789 |
{
|
| 790 |
"epoch": 3.38,
|
| 791 |
+
"learning_rate": 1.575024814592075e-06,
|
| 792 |
+
"loss": 1.6036,
|
| 793 |
"step": 12000
|
| 794 |
},
|
| 795 |
{
|
| 796 |
"epoch": 3.38,
|
| 797 |
"eval_gen_len": 20.0,
|
| 798 |
+
"eval_loss": 1.983000636100769,
|
| 799 |
+
"eval_rouge1": 22.1876,
|
| 800 |
+
"eval_rouge2": 5.6559,
|
| 801 |
+
"eval_rougeL": 21.9989,
|
| 802 |
+
"eval_rougeLsum": 21.9753,
|
| 803 |
+
"eval_runtime": 166.2195,
|
| 804 |
+
"eval_samples_per_second": 42.161,
|
| 805 |
+
"eval_steps_per_second": 2.635,
|
| 806 |
"step": 12000
|
| 807 |
},
|
| 808 |
{
|
| 809 |
"epoch": 3.41,
|
| 810 |
+
"learning_rate": 1.188605455559466e-06,
|
| 811 |
+
"loss": 1.5965,
|
| 812 |
"step": 12100
|
| 813 |
},
|
| 814 |
{
|
| 815 |
"epoch": 3.44,
|
| 816 |
+
"learning_rate": 8.596702859957324e-07,
|
| 817 |
+
"loss": 1.5971,
|
| 818 |
"step": 12200
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 3.47,
|
| 822 |
+
"learning_rate": 5.890117395356814e-07,
|
| 823 |
+
"loss": 1.6098,
|
| 824 |
"step": 12300
|
| 825 |
},
|
| 826 |
{
|
| 827 |
"epoch": 3.49,
|
| 828 |
+
"learning_rate": 3.772818563246123e-07,
|
| 829 |
+
"loss": 1.6057,
|
| 830 |
"step": 12400
|
| 831 |
},
|
| 832 |
{
|
| 833 |
"epoch": 3.52,
|
| 834 |
+
"learning_rate": 2.2499071219653263e-07,
|
| 835 |
+
"loss": 1.611,
|
| 836 |
"step": 12500
|
| 837 |
},
|
| 838 |
{
|
| 839 |
"epoch": 3.55,
|
| 840 |
+
"learning_rate": 1.3250518985677592e-07,
|
| 841 |
+
"loss": 1.6154,
|
| 842 |
"step": 12600
|
| 843 |
},
|
| 844 |
{
|
| 845 |
"epoch": 3.58,
|
| 846 |
+
"learning_rate": 1.0004809502943347e-07,
|
| 847 |
+
"loss": 1.6232,
|
| 848 |
"step": 12700
|
| 849 |
},
|
| 850 |
{
|
| 851 |
"epoch": 3.61,
|
| 852 |
+
"learning_rate": 4.999307463393912e-05,
|
| 853 |
+
"loss": 1.6383,
|
| 854 |
"step": 12800
|
| 855 |
},
|
| 856 |
{
|
| 857 |
"epoch": 3.64,
|
| 858 |
+
"learning_rate": 4.997113651616064e-05,
|
| 859 |
+
"loss": 1.6506,
|
| 860 |
"step": 12900
|
| 861 |
},
|
| 862 |
{
|
| 863 |
"epoch": 3.66,
|
| 864 |
+
"learning_rate": 4.993418683760613e-05,
|
| 865 |
+
"loss": 1.6974,
|
| 866 |
"step": 13000
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 3.69,
|
| 870 |
+
"learning_rate": 4.988224785538034e-05,
|
| 871 |
+
"loss": 1.7072,
|
| 872 |
"step": 13100
|
| 873 |
},
|
| 874 |
{
|
| 875 |
"epoch": 3.72,
|
| 876 |
+
"learning_rate": 4.981535085558401e-05,
|
| 877 |
+
"loss": 1.6934,
|
| 878 |
"step": 13200
|
| 879 |
},
|
| 880 |
{
|
| 881 |
"epoch": 3.75,
|
| 882 |
+
"learning_rate": 4.97335361344684e-05,
|
| 883 |
+
"loss": 1.6793,
|
| 884 |
"step": 13300
|
| 885 |
},
|
| 886 |
{
|
| 887 |
"epoch": 3.78,
|
| 888 |
+
"learning_rate": 4.963685297416225e-05,
|
| 889 |
+
"loss": 1.7101,
|
| 890 |
"step": 13400
|
| 891 |
},
|
| 892 |
{
|
| 893 |
"epoch": 3.8,
|
| 894 |
+
"learning_rate": 4.952535961298611e-05,
|
| 895 |
+
"loss": 1.75,
|
| 896 |
"step": 13500
|
| 897 |
},
|
| 898 |
{
|
| 899 |
"epoch": 3.83,
|
| 900 |
+
"learning_rate": 4.939912321037175e-05,
|
| 901 |
+
"loss": 1.7315,
|
| 902 |
"step": 13600
|
| 903 |
},
|
| 904 |
{
|
| 905 |
"epoch": 3.86,
|
| 906 |
+
"learning_rate": 4.9258219806407825e-05,
|
| 907 |
+
"loss": 1.7341,
|
| 908 |
"step": 13700
|
| 909 |
},
|
| 910 |
{
|
| 911 |
"epoch": 3.89,
|
| 912 |
+
"learning_rate": 4.910273427603616e-05,
|
| 913 |
+
"loss": 1.7312,
|
| 914 |
"step": 13800
|
| 915 |
},
|
| 916 |
{
|
| 917 |
"epoch": 3.92,
|
| 918 |
+
"learning_rate": 4.893276027792627e-05,
|
| 919 |
+
"loss": 1.7162,
|
| 920 |
"step": 13900
|
| 921 |
},
|
| 922 |
{
|
| 923 |
"epoch": 3.95,
|
| 924 |
+
"learning_rate": 4.874840019805889e-05,
|
| 925 |
+
"loss": 1.7558,
|
| 926 |
"step": 14000
|
| 927 |
},
|
| 928 |
{
|
| 929 |
"epoch": 3.95,
|
| 930 |
"eval_gen_len": 20.0,
|
| 931 |
+
"eval_loss": 2.0177605152130127,
|
| 932 |
+
"eval_rouge1": 21.6845,
|
| 933 |
+
"eval_rouge2": 5.7382,
|
| 934 |
+
"eval_rougeL": 21.4848,
|
| 935 |
+
"eval_rougeLsum": 21.4995,
|
| 936 |
+
"eval_runtime": 165.4038,
|
| 937 |
+
"eval_samples_per_second": 42.369,
|
| 938 |
+
"eval_steps_per_second": 2.648,
|
| 939 |
"step": 14000
|
| 940 |
},
|
| 941 |
{
|
| 942 |
"epoch": 3.97,
|
| 943 |
+
"learning_rate": 4.854976508805247e-05,
|
| 944 |
+
"loss": 1.767,
|
| 945 |
"step": 14100
|
| 946 |
},
|
| 947 |
{
|
| 948 |
"epoch": 4.0,
|
| 949 |
+
"learning_rate": 4.833697459826981e-05,
|
| 950 |
+
"loss": 1.7569,
|
| 951 |
"step": 14200
|
| 952 |
},
|
| 953 |
{
|
| 954 |
"epoch": 4.03,
|
| 955 |
+
"learning_rate": 4.811015690574522e-05,
|
| 956 |
+
"loss": 1.5871,
|
| 957 |
"step": 14300
|
| 958 |
},
|
| 959 |
{
|
| 960 |
"epoch": 4.06,
|
| 961 |
+
"learning_rate": 4.7869448636975414e-05,
|
| 962 |
+
"loss": 1.6034,
|
| 963 |
"step": 14400
|
| 964 |
},
|
| 965 |
{
|
| 966 |
"epoch": 4.09,
|
| 967 |
+
"learning_rate": 4.761499478562084e-05,
|
| 968 |
+
"loss": 1.6308,
|
| 969 |
"step": 14500
|
| 970 |
},
|
| 971 |
{
|
| 972 |
"epoch": 4.11,
|
| 973 |
+
"learning_rate": 4.73469486251669e-05,
|
| 974 |
+
"loss": 1.5885,
|
| 975 |
"step": 14600
|
| 976 |
},
|
| 977 |
{
|
| 978 |
"epoch": 4.14,
|
| 979 |
+
"learning_rate": 4.7065471616597775e-05,
|
| 980 |
+
"loss": 1.612,
|
| 981 |
"step": 14700
|
| 982 |
},
|
| 983 |
{
|
| 984 |
"epoch": 4.17,
|
| 985 |
+
"learning_rate": 4.677073331113833e-05,
|
| 986 |
+
"loss": 1.6088,
|
| 987 |
"step": 14800
|
| 988 |
},
|
| 989 |
{
|
| 990 |
"epoch": 4.2,
|
| 991 |
+
"learning_rate": 4.646291124812277e-05,
|
| 992 |
+
"loss": 1.6277,
|
| 993 |
"step": 14900
|
| 994 |
},
|
| 995 |
{
|
| 996 |
"epoch": 4.23,
|
| 997 |
+
"learning_rate": 4.614219084805167e-05,
|
| 998 |
+
"loss": 1.6087,
|
| 999 |
"step": 15000
|
| 1000 |
},
|
| 1001 |
{
|
| 1002 |
"epoch": 4.26,
|
| 1003 |
+
"learning_rate": 4.580876530090152e-05,
|
| 1004 |
+
"loss": 1.6462,
|
| 1005 |
"step": 15100
|
| 1006 |
},
|
| 1007 |
{
|
| 1008 |
"epoch": 4.28,
|
| 1009 |
+
"learning_rate": 4.546283544975434e-05,
|
| 1010 |
+
"loss": 1.6423,
|
| 1011 |
"step": 15200
|
| 1012 |
},
|
| 1013 |
{
|
| 1014 |
"epoch": 4.31,
|
| 1015 |
+
"learning_rate": 4.51046096698173e-05,
|
| 1016 |
+
"loss": 1.642,
|
| 1017 |
"step": 15300
|
| 1018 |
},
|
| 1019 |
{
|
| 1020 |
"epoch": 4.34,
|
| 1021 |
+
"learning_rate": 4.473430374290533e-05,
|
| 1022 |
+
"loss": 1.6263,
|
| 1023 |
"step": 15400
|
| 1024 |
},
|
| 1025 |
{
|
| 1026 |
"epoch": 4.37,
|
| 1027 |
+
"learning_rate": 4.435214072746215e-05,
|
| 1028 |
+
"loss": 1.6582,
|
| 1029 |
"step": 15500
|
| 1030 |
},
|
| 1031 |
{
|
| 1032 |
"epoch": 4.4,
|
| 1033 |
+
"learning_rate": 4.3958350824198286e-05,
|
| 1034 |
+
"loss": 1.6671,
|
| 1035 |
"step": 15600
|
| 1036 |
},
|
| 1037 |
{
|
| 1038 |
"epoch": 4.43,
|
| 1039 |
+
"learning_rate": 4.355317123742669e-05,
|
| 1040 |
+
"loss": 1.6473,
|
| 1041 |
"step": 15700
|
| 1042 |
},
|
| 1043 |
{
|
| 1044 |
"epoch": 4.45,
|
| 1045 |
+
"learning_rate": 4.314106363710374e-05,
|
| 1046 |
+
"loss": 1.6576,
|
| 1047 |
"step": 15800
|
| 1048 |
},
|
| 1049 |
{
|
| 1050 |
"epoch": 4.48,
|
| 1051 |
+
"learning_rate": 4.271395127748479e-05,
|
| 1052 |
+
"loss": 1.633,
|
| 1053 |
"step": 15900
|
| 1054 |
},
|
| 1055 |
{
|
| 1056 |
"epoch": 4.51,
|
| 1057 |
+
"learning_rate": 4.227619881411398e-05,
|
| 1058 |
+
"loss": 1.64,
|
| 1059 |
"step": 16000
|
| 1060 |
},
|
| 1061 |
{
|
| 1062 |
"epoch": 4.51,
|
| 1063 |
"eval_gen_len": 20.0,
|
| 1064 |
+
"eval_loss": 2.032703161239624,
|
| 1065 |
+
"eval_rouge1": 22.2681,
|
| 1066 |
+
"eval_rouge2": 5.8023,
|
| 1067 |
+
"eval_rougeL": 22.0116,
|
| 1068 |
+
"eval_rougeLsum": 21.9997,
|
| 1069 |
+
"eval_runtime": 165.398,
|
| 1070 |
+
"eval_samples_per_second": 42.371,
|
| 1071 |
+
"eval_steps_per_second": 2.648,
|
| 1072 |
"step": 16000
|
| 1073 |
},
|
| 1074 |
{
|
| 1075 |
"epoch": 4.54,
|
| 1076 |
+
"learning_rate": 4.18280699327066e-05,
|
| 1077 |
+
"loss": 1.651,
|
| 1078 |
"step": 16100
|
| 1079 |
},
|
| 1080 |
{
|
| 1081 |
"epoch": 4.57,
|
| 1082 |
+
"learning_rate": 4.1369834569344205e-05,
|
| 1083 |
+
"loss": 1.6491,
|
| 1084 |
"step": 16200
|
| 1085 |
},
|
| 1086 |
{
|
| 1087 |
"epoch": 4.59,
|
| 1088 |
+
"learning_rate": 4.090176874787515e-05,
|
| 1089 |
+
"loss": 1.6302,
|
| 1090 |
"step": 16300
|
| 1091 |
},
|
| 1092 |
{
|
| 1093 |
"epoch": 4.62,
|
| 1094 |
+
"learning_rate": 4.042415441364819e-05,
|
| 1095 |
+
"loss": 1.6376,
|
| 1096 |
"step": 16400
|
| 1097 |
},
|
| 1098 |
{
|
| 1099 |
"epoch": 4.65,
|
| 1100 |
+
"learning_rate": 3.993727926367911e-05,
|
| 1101 |
+
"loss": 1.6322,
|
| 1102 |
"step": 16500
|
| 1103 |
},
|
| 1104 |
{
|
| 1105 |
"epoch": 4.68,
|
| 1106 |
+
"learning_rate": 3.944143657335282e-05,
|
| 1107 |
+
"loss": 1.6651,
|
| 1108 |
"step": 16600
|
| 1109 |
},
|
| 1110 |
{
|
| 1111 |
"epoch": 4.71,
|
| 1112 |
+
"learning_rate": 3.8936925019765214e-05,
|
| 1113 |
+
"loss": 1.6308,
|
| 1114 |
"step": 16700
|
| 1115 |
},
|
| 1116 |
{
|
| 1117 |
"epoch": 4.74,
|
| 1118 |
+
"learning_rate": 3.842404850181127e-05,
|
| 1119 |
+
"loss": 1.6703,
|
| 1120 |
"step": 16800
|
| 1121 |
},
|
| 1122 |
{
|
| 1123 |
"epoch": 4.76,
|
| 1124 |
+
"learning_rate": 3.790311595712772e-05,
|
| 1125 |
+
"loss": 1.6816,
|
| 1126 |
"step": 16900
|
| 1127 |
},
|
| 1128 |
{
|
| 1129 |
"epoch": 4.79,
|
| 1130 |
+
"learning_rate": 3.737444117600056e-05,
|
| 1131 |
+
"loss": 1.6568,
|
| 1132 |
"step": 17000
|
| 1133 |
},
|
| 1134 |
{
|
| 1135 |
"epoch": 4.82,
|
| 1136 |
+
"learning_rate": 3.6838342612349524e-05,
|
| 1137 |
+
"loss": 1.6697,
|
| 1138 |
"step": 17100
|
| 1139 |
},
|
| 1140 |
{
|
| 1141 |
"epoch": 4.85,
|
| 1142 |
+
"learning_rate": 3.629514319190331e-05,
|
| 1143 |
+
"loss": 1.6352,
|
| 1144 |
"step": 17200
|
| 1145 |
},
|
| 1146 |
{
|
| 1147 |
"epoch": 4.88,
|
| 1148 |
+
"learning_rate": 3.57451701176813e-05,
|
| 1149 |
+
"loss": 1.6724,
|
| 1150 |
"step": 17300
|
| 1151 |
},
|
| 1152 |
{
|
| 1153 |
"epoch": 4.9,
|
| 1154 |
+
"learning_rate": 3.5188754672898564e-05,
|
| 1155 |
+
"loss": 1.6444,
|
| 1156 |
"step": 17400
|
| 1157 |
},
|
| 1158 |
{
|
| 1159 |
"epoch": 4.93,
|
| 1160 |
+
"learning_rate": 3.462623202141332e-05,
|
| 1161 |
+
"loss": 1.6568,
|
| 1162 |
"step": 17500
|
| 1163 |
},
|
| 1164 |
{
|
| 1165 |
"epoch": 4.96,
|
| 1166 |
+
"learning_rate": 3.4057941005836765e-05,
|
| 1167 |
+
"loss": 1.6626,
|
| 1168 |
"step": 17600
|
| 1169 |
},
|
| 1170 |
{
|
| 1171 |
"epoch": 4.99,
|
| 1172 |
+
"learning_rate": 3.34842239434269e-05,
|
| 1173 |
+
"loss": 1.6246,
|
| 1174 |
"step": 17700
|
| 1175 |
},
|
| 1176 |
{
|
| 1177 |
"epoch": 5.02,
|
| 1178 |
+
"learning_rate": 3.290542641988946e-05,
|
| 1179 |
+
"loss": 1.4957,
|
| 1180 |
"step": 17800
|
| 1181 |
},
|
| 1182 |
{
|
| 1183 |
"epoch": 5.05,
|
| 1184 |
+
"learning_rate": 3.232189708121e-05,
|
| 1185 |
+
"loss": 1.3941,
|
| 1186 |
"step": 17900
|
| 1187 |
},
|
| 1188 |
{
|
| 1189 |
"epoch": 5.07,
|
| 1190 |
+
"learning_rate": 3.173398742364255e-05,
|
| 1191 |
+
"loss": 1.4248,
|
| 1192 |
"step": 18000
|
| 1193 |
},
|
| 1194 |
{
|
| 1195 |
"epoch": 5.07,
|
| 1196 |
"eval_gen_len": 20.0,
|
| 1197 |
+
"eval_loss": 2.0742380619049072,
|
| 1198 |
+
"eval_rouge1": 21.8569,
|
| 1199 |
+
"eval_rouge2": 5.5533,
|
| 1200 |
+
"eval_rougeL": 21.6308,
|
| 1201 |
+
"eval_rougeLsum": 21.638,
|
| 1202 |
+
"eval_runtime": 166.3338,
|
| 1203 |
+
"eval_samples_per_second": 42.132,
|
| 1204 |
+
"eval_steps_per_second": 2.633,
|
| 1205 |
"step": 18000
|
| 1206 |
},
|
| 1207 |
{
|
| 1208 |
"epoch": 5.1,
|
| 1209 |
+
"learning_rate": 3.114205158198149e-05,
|
| 1210 |
+
"loss": 1.4175,
|
| 1211 |
"step": 18100
|
| 1212 |
},
|
| 1213 |
{
|
| 1214 |
"epoch": 5.13,
|
| 1215 |
+
"learning_rate": 3.054644611624394e-05,
|
| 1216 |
+
"loss": 1.3888,
|
| 1217 |
"step": 18200
|
| 1218 |
},
|
| 1219 |
{
|
| 1220 |
"epoch": 5.16,
|
| 1221 |
+
"learning_rate": 2.9947529796891307e-05,
|
| 1222 |
+
"loss": 1.4086,
|
| 1223 |
"step": 18300
|
| 1224 |
},
|
| 1225 |
{
|
| 1226 |
"epoch": 5.19,
|
| 1227 |
+
"learning_rate": 2.9345663388719467e-05,
|
| 1228 |
+
"loss": 1.3948,
|
| 1229 |
"step": 18400
|
| 1230 |
},
|
| 1231 |
{
|
| 1232 |
"epoch": 5.21,
|
| 1233 |
+
"learning_rate": 2.8741209433547458e-05,
|
| 1234 |
+
"loss": 1.4149,
|
| 1235 |
"step": 18500
|
| 1236 |
},
|
| 1237 |
{
|
| 1238 |
"epoch": 5.24,
|
| 1239 |
+
"learning_rate": 2.8134532031835893e-05,
|
| 1240 |
+
"loss": 1.4184,
|
| 1241 |
"step": 18600
|
| 1242 |
},
|
| 1243 |
{
|
| 1244 |
"epoch": 5.27,
|
| 1245 |
+
"learning_rate": 2.7525996623366436e-05,
|
| 1246 |
+
"loss": 1.43,
|
| 1247 |
"step": 18700
|
| 1248 |
},
|
| 1249 |
{
|
| 1250 |
"epoch": 5.3,
|
| 1251 |
+
"learning_rate": 2.691596976711453e-05,
|
| 1252 |
+
"loss": 1.4435,
|
| 1253 |
"step": 18800
|
| 1254 |
},
|
| 1255 |
{
|
| 1256 |
"epoch": 5.33,
|
| 1257 |
+
"learning_rate": 2.630481892044803e-05,
|
| 1258 |
+
"loss": 1.4092,
|
| 1259 |
"step": 18900
|
| 1260 |
},
|
| 1261 |
{
|
| 1262 |
"epoch": 5.36,
|
| 1263 |
+
"learning_rate": 2.5692912217784543e-05,
|
| 1264 |
+
"loss": 1.4241,
|
| 1265 |
"step": 19000
|
| 1266 |
},
|
| 1267 |
{
|
| 1268 |
"epoch": 5.38,
|
| 1269 |
+
"learning_rate": 2.5080618248841106e-05,
|
| 1270 |
+
"loss": 1.414,
|
| 1271 |
"step": 19100
|
| 1272 |
},
|
| 1273 |
{
|
| 1274 |
"epoch": 5.41,
|
| 1275 |
+
"learning_rate": 2.4468305836609452e-05,
|
| 1276 |
+
"loss": 1.4265,
|
| 1277 |
"step": 19200
|
| 1278 |
},
|
| 1279 |
{
|
| 1280 |
"epoch": 5.44,
|
| 1281 |
+
"learning_rate": 2.3856343815190883e-05,
|
| 1282 |
+
"loss": 1.4061,
|
| 1283 |
"step": 19300
|
| 1284 |
},
|
| 1285 |
{
|
| 1286 |
"epoch": 5.47,
|
| 1287 |
+
"learning_rate": 2.324510080762437e-05,
|
| 1288 |
+
"loss": 1.3992,
|
| 1289 |
"step": 19400
|
| 1290 |
},
|
| 1291 |
{
|
| 1292 |
"epoch": 5.5,
|
| 1293 |
+
"learning_rate": 2.2634945003841808e-05,
|
| 1294 |
+
"loss": 1.4221,
|
| 1295 |
"step": 19500
|
| 1296 |
},
|
| 1297 |
{
|
| 1298 |
"epoch": 5.52,
|
| 1299 |
+
"learning_rate": 2.202624393888421e-05,
|
| 1300 |
+
"loss": 1.3943,
|
| 1301 |
"step": 19600
|
| 1302 |
},
|
| 1303 |
{
|
| 1304 |
"epoch": 5.55,
|
| 1305 |
+
"learning_rate": 2.1419364271512303e-05,
|
| 1306 |
+
"loss": 1.4266,
|
| 1307 |
"step": 19700
|
| 1308 |
},
|
| 1309 |
{
|
| 1310 |
"epoch": 5.58,
|
| 1311 |
+
"learning_rate": 2.0814671563345028e-05,
|
| 1312 |
+
"loss": 1.4466,
|
| 1313 |
"step": 19800
|
| 1314 |
},
|
| 1315 |
{
|
| 1316 |
"epoch": 5.61,
|
| 1317 |
+
"learning_rate": 2.021853765291574e-05,
|
| 1318 |
+
"loss": 1.4312,
|
| 1319 |
"step": 19900
|
| 1320 |
},
|
| 1321 |
{
|
| 1322 |
"epoch": 5.64,
|
| 1323 |
+
"learning_rate": 1.9619279130307914e-05,
|
| 1324 |
+
"loss": 1.4263,
|
| 1325 |
"step": 20000
|
| 1326 |
},
|
| 1327 |
{
|
| 1328 |
"epoch": 5.64,
|
| 1329 |
"eval_gen_len": 20.0,
|
| 1330 |
+
"eval_loss": 2.0796058177948,
|
| 1331 |
+
"eval_rouge1": 22.037,
|
| 1332 |
+
"eval_rouge2": 5.454,
|
| 1333 |
+
"eval_rougeL": 21.7861,
|
| 1334 |
+
"eval_rougeLsum": 21.7976,
|
| 1335 |
+
"eval_runtime": 165.631,
|
| 1336 |
+
"eval_samples_per_second": 42.311,
|
| 1337 |
+
"eval_steps_per_second": 2.644,
|
| 1338 |
"step": 20000
|
| 1339 |
},
|
| 1340 |
{
|
| 1341 |
"epoch": 5.67,
|
| 1342 |
+
"learning_rate": 1.902329187088426e-05,
|
| 1343 |
+
"loss": 1.4114,
|
| 1344 |
"step": 20100
|
| 1345 |
},
|
| 1346 |
{
|
| 1347 |
"epoch": 5.69,
|
| 1348 |
+
"learning_rate": 1.8430934875084445e-05,
|
| 1349 |
+
"loss": 1.4068,
|
| 1350 |
"step": 20200
|
| 1351 |
},
|
| 1352 |
{
|
| 1353 |
"epoch": 5.72,
|
| 1354 |
+
"learning_rate": 1.7842564956613097e-05,
|
| 1355 |
+
"loss": 1.4212,
|
| 1356 |
"step": 20300
|
| 1357 |
},
|
| 1358 |
{
|
| 1359 |
"epoch": 5.75,
|
| 1360 |
+
"learning_rate": 1.7258536527508527e-05,
|
| 1361 |
+
"loss": 1.4179,
|
| 1362 |
"step": 20400
|
| 1363 |
},
|
| 1364 |
{
|
| 1365 |
"epoch": 5.78,
|
| 1366 |
+
"learning_rate": 1.6679201384658204e-05,
|
| 1367 |
+
"loss": 1.4263,
|
| 1368 |
"step": 20500
|
| 1369 |
},
|
| 1370 |
{
|
| 1371 |
"epoch": 5.81,
|
| 1372 |
+
"learning_rate": 1.6104908497889437e-05,
|
| 1373 |
+
"loss": 1.4062,
|
| 1374 |
"step": 20600
|
| 1375 |
},
|
| 1376 |
{
|
| 1377 |
"epoch": 5.83,
|
| 1378 |
+
"learning_rate": 1.5536003799763033e-05,
|
| 1379 |
+
"loss": 1.4168,
|
| 1380 |
"step": 20700
|
| 1381 |
},
|
| 1382 |
{
|
| 1383 |
"epoch": 5.86,
|
| 1384 |
+
"learning_rate": 1.497282997719642e-05,
|
| 1385 |
+
"loss": 1.4502,
|
| 1386 |
"step": 20800
|
| 1387 |
},
|
| 1388 |
{
|
| 1389 |
"epoch": 5.89,
|
| 1390 |
+
"learning_rate": 1.4415726265041886e-05,
|
| 1391 |
+
"loss": 1.42,
|
| 1392 |
"step": 20900
|
| 1393 |
},
|
| 1394 |
{
|
| 1395 |
"epoch": 5.92,
|
| 1396 |
+
"learning_rate": 1.3865028241744182e-05,
|
| 1397 |
+
"loss": 1.421,
|
| 1398 |
"step": 21000
|
| 1399 |
},
|
| 1400 |
{
|
| 1401 |
"epoch": 5.95,
|
| 1402 |
+
"learning_rate": 1.332106762720061e-05,
|
| 1403 |
+
"loss": 1.4272,
|
| 1404 |
"step": 21100
|
| 1405 |
},
|
| 1406 |
{
|
| 1407 |
"epoch": 5.98,
|
| 1408 |
+
"learning_rate": 1.2784172082945395e-05,
|
| 1409 |
+
"loss": 1.4115,
|
| 1410 |
"step": 21200
|
| 1411 |
},
|
| 1412 |
{
|
| 1413 |
"epoch": 6.0,
|
| 1414 |
+
"learning_rate": 1.2254665014778574e-05,
|
| 1415 |
+
"loss": 1.3844,
|
| 1416 |
"step": 21300
|
| 1417 |
},
|
| 1418 |
{
|
| 1419 |
"epoch": 6.03,
|
| 1420 |
+
"learning_rate": 1.1732865377958439e-05,
|
| 1421 |
+
"loss": 1.2502,
|
| 1422 |
"step": 21400
|
| 1423 |
},
|
| 1424 |
{
|
| 1425 |
"epoch": 6.06,
|
| 1426 |
+
"learning_rate": 1.1219087485074895e-05,
|
| 1427 |
+
"loss": 1.232,
|
| 1428 |
"step": 21500
|
| 1429 |
},
|
| 1430 |
{
|
| 1431 |
"epoch": 6.09,
|
| 1432 |
+
"learning_rate": 1.0713640816719211e-05,
|
| 1433 |
+
"loss": 1.2675,
|
| 1434 |
"step": 21600
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"epoch": 6.12,
|
| 1438 |
+
"learning_rate": 1.021682983506454e-05,
|
| 1439 |
+
"loss": 1.2537,
|
| 1440 |
"step": 21700
|
| 1441 |
},
|
| 1442 |
{
|
| 1443 |
"epoch": 6.14,
|
| 1444 |
+
"learning_rate": 9.728953800469257e-06,
|
| 1445 |
+
"loss": 1.2703,
|
| 1446 |
"step": 21800
|
| 1447 |
},
|
| 1448 |
{
|
| 1449 |
"epoch": 6.17,
|
| 1450 |
+
"learning_rate": 9.250306591213766e-06,
|
| 1451 |
+
"loss": 1.2496,
|
| 1452 |
"step": 21900
|
| 1453 |
},
|
| 1454 |
{
|
| 1455 |
"epoch": 6.2,
|
| 1456 |
+
"learning_rate": 8.781176526479135e-06,
|
| 1457 |
+
"loss": 1.2478,
|
| 1458 |
"step": 22000
|
| 1459 |
},
|
| 1460 |
{
|
| 1461 |
"epoch": 6.2,
|
| 1462 |
"eval_gen_len": 20.0,
|
| 1463 |
+
"eval_loss": 2.1144540309906006,
|
| 1464 |
+
"eval_rouge1": 21.5358,
|
| 1465 |
+
"eval_rouge2": 5.3838,
|
| 1466 |
+
"eval_rougeL": 21.3299,
|
| 1467 |
+
"eval_rougeLsum": 21.3191,
|
| 1468 |
+
"eval_runtime": 166.7361,
|
| 1469 |
+
"eval_samples_per_second": 42.03,
|
| 1470 |
+
"eval_steps_per_second": 2.627,
|
| 1471 |
"step": 22000
|
| 1472 |
},
|
| 1473 |
{
|
| 1474 |
"epoch": 6.23,
|
| 1475 |
+
"learning_rate": 8.321846192674462e-06,
|
| 1476 |
+
"loss": 1.2486,
|
| 1477 |
"step": 22100
|
| 1478 |
},
|
| 1479 |
{
|
| 1480 |
"epoch": 6.26,
|
| 1481 |
+
"learning_rate": 7.877034040486934e-06,
|
| 1482 |
+
"loss": 1.2412,
|
| 1483 |
"step": 22200
|
| 1484 |
},
|
| 1485 |
{
|
| 1486 |
"epoch": 6.29,
|
| 1487 |
+
"learning_rate": 7.4380223596522265e-06,
|
| 1488 |
+
"loss": 1.2552,
|
| 1489 |
"step": 22300
|
| 1490 |
},
|
| 1491 |
{
|
| 1492 |
"epoch": 6.31,
|
| 1493 |
+
"learning_rate": 7.009619475593796e-06,
|
| 1494 |
+
"loss": 1.2642,
|
| 1495 |
"step": 22400
|
| 1496 |
},
|
| 1497 |
{
|
| 1498 |
"epoch": 6.34,
|
| 1499 |
+
"learning_rate": 6.592083442189996e-06,
|
| 1500 |
+
"loss": 1.265,
|
| 1501 |
"step": 22500
|
| 1502 |
},
|
| 1503 |
{
|
| 1504 |
"epoch": 6.37,
|
| 1505 |
+
"learning_rate": 6.1856657675346675e-06,
|
| 1506 |
+
"loss": 1.2631,
|
| 1507 |
"step": 22600
|
| 1508 |
},
|
| 1509 |
{
|
| 1510 |
"epoch": 6.4,
|
| 1511 |
+
"learning_rate": 5.790611262438083e-06,
|
| 1512 |
+
"loss": 1.2736,
|
| 1513 |
"step": 22700
|
| 1514 |
},
|
| 1515 |
{
|
| 1516 |
"epoch": 6.43,
|
| 1517 |
+
"learning_rate": 5.407157892962079e-06,
|
| 1518 |
+
"loss": 1.2595,
|
| 1519 |
"step": 22800
|
| 1520 |
},
|
| 1521 |
{
|
| 1522 |
"epoch": 6.45,
|
| 1523 |
+
"learning_rate": 5.035536637078171e-06,
|
| 1524 |
+
"loss": 1.2661,
|
| 1525 |
"step": 22900
|
| 1526 |
},
|
| 1527 |
{
|
| 1528 |
"epoch": 6.48,
|
| 1529 |
+
"learning_rate": 4.675971345535108e-06,
|
| 1530 |
+
"loss": 1.2651,
|
| 1531 |
"step": 23000
|
| 1532 |
},
|
| 1533 |
{
|
| 1534 |
"epoch": 6.51,
|
| 1535 |
+
"learning_rate": 4.328678607019489e-06,
|
| 1536 |
+
"loss": 1.2499,
|
| 1537 |
"step": 23100
|
| 1538 |
},
|
| 1539 |
{
|
| 1540 |
"epoch": 6.54,
|
| 1541 |
+
"learning_rate": 3.993867617690892e-06,
|
| 1542 |
+
"loss": 1.263,
|
| 1543 |
"step": 23200
|
| 1544 |
},
|
| 1545 |
{
|
| 1546 |
"epoch": 6.57,
|
| 1547 |
+
"learning_rate": 3.6717400551698886e-06,
|
| 1548 |
+
"loss": 1.2546,
|
| 1549 |
"step": 23300
|
| 1550 |
},
|
| 1551 |
{
|
| 1552 |
"epoch": 6.6,
|
| 1553 |
+
"learning_rate": 3.3624899570550363e-06,
|
| 1554 |
+
"loss": 1.261,
|
| 1555 |
"step": 23400
|
| 1556 |
},
|
| 1557 |
{
|
| 1558 |
"epoch": 6.62,
|
| 1559 |
+
"learning_rate": 3.066303604041807e-06,
|
| 1560 |
+
"loss": 1.2418,
|
| 1561 |
"step": 23500
|
| 1562 |
},
|
| 1563 |
{
|
| 1564 |
"epoch": 6.65,
|
| 1565 |
+
"learning_rate": 2.7833594077141535e-06,
|
| 1566 |
+
"loss": 1.2601,
|
| 1567 |
"step": 23600
|
| 1568 |
},
|
| 1569 |
{
|
| 1570 |
"epoch": 6.68,
|
| 1571 |
+
"learning_rate": 2.5138278030759714e-06,
|
| 1572 |
+
"loss": 1.2397,
|
| 1573 |
"step": 23700
|
| 1574 |
},
|
| 1575 |
{
|
| 1576 |
"epoch": 6.71,
|
| 1577 |
+
"learning_rate": 2.2578711458874663e-06,
|
| 1578 |
+
"loss": 1.264,
|
| 1579 |
"step": 23800
|
| 1580 |
},
|
| 1581 |
{
|
| 1582 |
"epoch": 6.74,
|
| 1583 |
+
"learning_rate": 2.0156436148680858e-06,
|
| 1584 |
+
"loss": 1.2497,
|
| 1585 |
"step": 23900
|
| 1586 |
},
|
| 1587 |
{
|
| 1588 |
"epoch": 6.76,
|
| 1589 |
+
"learning_rate": 1.787291118825041e-06,
|
| 1590 |
+
"loss": 1.2469,
|
| 1591 |
"step": 24000
|
| 1592 |
},
|
| 1593 |
{
|
| 1594 |
"epoch": 6.76,
|
| 1595 |
"eval_gen_len": 20.0,
|
| 1596 |
+
"eval_loss": 2.113508462905884,
|
| 1597 |
+
"eval_rouge1": 21.3962,
|
| 1598 |
+
"eval_rouge2": 5.3698,
|
| 1599 |
+
"eval_rougeL": 21.1842,
|
| 1600 |
+
"eval_rougeLsum": 21.159,
|
| 1601 |
+
"eval_runtime": 166.5668,
|
| 1602 |
+
"eval_samples_per_second": 42.073,
|
| 1603 |
+
"eval_steps_per_second": 2.63,
|
| 1604 |
"step": 24000
|
| 1605 |
},
|
| 1606 |
{
|
| 1607 |
"epoch": 6.79,
|
| 1608 |
+
"learning_rate": 1.5729512087633123e-06,
|
| 1609 |
+
"loss": 1.2383,
|
| 1610 |
"step": 24100
|
| 1611 |
},
|
| 1612 |
{
|
| 1613 |
"epoch": 6.82,
|
| 1614 |
+
"learning_rate": 1.372752995030021e-06,
|
| 1615 |
+
"loss": 1.2619,
|
| 1616 |
"step": 24200
|
| 1617 |
},
|
| 1618 |
{
|
| 1619 |
"epoch": 6.85,
|
| 1620 |
+
"learning_rate": 1.1868170695432342e-06,
|
| 1621 |
+
"loss": 1.2536,
|
| 1622 |
"step": 24300
|
| 1623 |
},
|
| 1624 |
{
|
| 1625 |
"epoch": 6.88,
|
| 1626 |
+
"learning_rate": 1.0152554331518699e-06,
|
| 1627 |
+
"loss": 1.2514,
|
| 1628 |
"step": 24400
|
| 1629 |
},
|
| 1630 |
{
|
| 1631 |
"epoch": 6.91,
|
| 1632 |
+
"learning_rate": 8.596702859957324e-07,
|
| 1633 |
+
"loss": 1.2585,
|
| 1634 |
"step": 24500
|
| 1635 |
},
|
| 1636 |
{
|
| 1637 |
"epoch": 6.93,
|
| 1638 |
+
"learning_rate": 7.170123718266064e-07,
|
| 1639 |
+
"loss": 1.2439,
|
| 1640 |
"step": 24600
|
| 1641 |
},
|
| 1642 |
{
|
| 1643 |
"epoch": 6.96,
|
| 1644 |
+
"learning_rate": 5.890117395356814e-07,
|
| 1645 |
+
"loss": 1.245,
|
| 1646 |
"step": 24700
|
| 1647 |
},
|
| 1648 |
{
|
| 1649 |
"epoch": 6.99,
|
| 1650 |
+
"learning_rate": 4.7574549191759186e-07,
|
| 1651 |
+
"loss": 1.2446,
|
| 1652 |
"step": 24800
|
| 1653 |
},
|
| 1654 |
{
|
| 1655 |
"epoch": 7.02,
|
| 1656 |
+
"learning_rate": 3.772818563246123e-07,
|
| 1657 |
+
"loss": 1.2194,
|
| 1658 |
"step": 24900
|
| 1659 |
},
|
| 1660 |
{
|
| 1661 |
"epoch": 7.05,
|
| 1662 |
+
"learning_rate": 2.936801435690251e-07,
|
| 1663 |
+
"loss": 1.2058,
|
| 1664 |
"step": 25000
|
| 1665 |
},
|
| 1666 |
{
|
| 1667 |
"epoch": 7.07,
|
| 1668 |
+
"learning_rate": 2.2499071219653263e-07,
|
| 1669 |
+
"loss": 1.1916,
|
| 1670 |
"step": 25100
|
| 1671 |
},
|
| 1672 |
{
|
| 1673 |
"epoch": 7.1,
|
| 1674 |
+
"learning_rate": 1.7171816152852273e-07,
|
| 1675 |
+
"loss": 1.2186,
|
| 1676 |
"step": 25200
|
| 1677 |
},
|
| 1678 |
{
|
| 1679 |
"epoch": 7.13,
|
| 1680 |
+
"learning_rate": 1.328184223787534e-07,
|
| 1681 |
+
"loss": 1.2151,
|
| 1682 |
"step": 25300
|
| 1683 |
},
|
| 1684 |
{
|
| 1685 |
"epoch": 7.16,
|
| 1686 |
+
"learning_rate": 1.0892786169791435e-07,
|
| 1687 |
+
"loss": 1.2098,
|
| 1688 |
"step": 25400
|
| 1689 |
},
|
| 1690 |
{
|
| 1691 |
"epoch": 7.19,
|
| 1692 |
+
"learning_rate": 1.0006087026643128e-07,
|
| 1693 |
+
"loss": 1.2011,
|
| 1694 |
"step": 25500
|
| 1695 |
},
|
| 1696 |
{
|
| 1697 |
"epoch": 7.22,
|
| 1698 |
+
"learning_rate": 4.9998444254188996e-05,
|
| 1699 |
+
"loss": 1.2333,
|
| 1700 |
"step": 25600
|
| 1701 |
},
|
| 1702 |
{
|
| 1703 |
"epoch": 7.24,
|
| 1704 |
+
"learning_rate": 4.9993146582012154e-05,
|
| 1705 |
+
"loss": 1.3057,
|
| 1706 |
"step": 25700
|
| 1707 |
},
|
| 1708 |
{
|
| 1709 |
"epoch": 7.27,
|
| 1710 |
+
"learning_rate": 4.998409256370816e-05,
|
| 1711 |
+
"loss": 1.2949,
|
| 1712 |
"step": 25800
|
| 1713 |
},
|
| 1714 |
{
|
| 1715 |
"epoch": 7.3,
|
| 1716 |
+
"learning_rate": 4.997128356277887e-05,
|
| 1717 |
+
"loss": 1.3107,
|
| 1718 |
"step": 25900
|
| 1719 |
},
|
| 1720 |
{
|
| 1721 |
"epoch": 7.33,
|
| 1722 |
+
"learning_rate": 4.995472150821271e-05,
|
| 1723 |
+
"loss": 1.3323,
|
| 1724 |
"step": 26000
|
| 1725 |
},
|
| 1726 |
{
|
| 1727 |
"epoch": 7.33,
|
| 1728 |
"eval_gen_len": 20.0,
|
| 1729 |
+
"eval_loss": 2.143944501876831,
|
| 1730 |
+
"eval_rouge1": 21.5245,
|
| 1731 |
+
"eval_rouge2": 5.444,
|
| 1732 |
+
"eval_rougeL": 21.312,
|
| 1733 |
+
"eval_rougeLsum": 21.3015,
|
| 1734 |
+
"eval_runtime": 166.5992,
|
| 1735 |
+
"eval_samples_per_second": 42.065,
|
| 1736 |
+
"eval_steps_per_second": 2.629,
|
| 1737 |
"step": 26000
|
| 1738 |
},
|
| 1739 |
{
|
| 1740 |
"epoch": 7.36,
|
| 1741 |
+
"learning_rate": 4.9934408894194186e-05,
|
| 1742 |
+
"loss": 1.3458,
|
| 1743 |
"step": 26100
|
| 1744 |
},
|
| 1745 |
{
|
| 1746 |
"epoch": 7.38,
|
| 1747 |
+
"learning_rate": 4.991034877972824e-05,
|
| 1748 |
+
"loss": 1.3346,
|
| 1749 |
"step": 26200
|
| 1750 |
},
|
| 1751 |
{
|
| 1752 |
"epoch": 7.41,
|
| 1753 |
+
"learning_rate": 4.988254478817961e-05,
|
| 1754 |
+
"loss": 1.3482,
|
| 1755 |
"step": 26300
|
| 1756 |
},
|
| 1757 |
{
|
| 1758 |
"epoch": 7.44,
|
| 1759 |
+
"learning_rate": 4.9851001106727165e-05,
|
| 1760 |
+
"loss": 1.3519,
|
| 1761 |
"step": 26400
|
| 1762 |
},
|
| 1763 |
{
|
| 1764 |
"epoch": 7.47,
|
| 1765 |
+
"learning_rate": 4.9815722485733305e-05,
|
| 1766 |
+
"loss": 1.3699,
|
| 1767 |
"step": 26500
|
| 1768 |
},
|
| 1769 |
{
|
| 1770 |
"epoch": 7.5,
|
| 1771 |
+
"learning_rate": 4.9776714238028576e-05,
|
| 1772 |
+
"loss": 1.3496,
|
| 1773 |
"step": 26600
|
| 1774 |
},
|
| 1775 |
{
|
| 1776 |
"epoch": 7.53,
|
| 1777 |
+
"learning_rate": 4.97339822381116e-05,
|
| 1778 |
+
"loss": 1.3835,
|
| 1779 |
"step": 26700
|
| 1780 |
},
|
| 1781 |
{
|
| 1782 |
"epoch": 7.55,
|
| 1783 |
+
"learning_rate": 4.968753292126438e-05,
|
| 1784 |
+
"loss": 1.3604,
|
| 1785 |
"step": 26800
|
| 1786 |
},
|
| 1787 |
{
|
| 1788 |
"epoch": 7.58,
|
| 1789 |
+
"learning_rate": 4.96373732825832e-05,
|
| 1790 |
+
"loss": 1.3776,
|
| 1791 |
"step": 26900
|
| 1792 |
},
|
| 1793 |
{
|
| 1794 |
"epoch": 7.61,
|
| 1795 |
+
"learning_rate": 4.9583510875925124e-05,
|
| 1796 |
+
"loss": 1.3988,
|
| 1797 |
"step": 27000
|
| 1798 |
},
|
| 1799 |
{
|
| 1800 |
"epoch": 7.64,
|
| 1801 |
+
"learning_rate": 4.952595381277048e-05,
|
| 1802 |
+
"loss": 1.3795,
|
| 1803 |
"step": 27100
|
| 1804 |
},
|
| 1805 |
{
|
| 1806 |
"epoch": 7.67,
|
| 1807 |
+
"learning_rate": 4.946471076100126e-05,
|
| 1808 |
+
"loss": 1.3823,
|
| 1809 |
"step": 27200
|
| 1810 |
},
|
| 1811 |
{
|
| 1812 |
"epoch": 7.69,
|
| 1813 |
+
"learning_rate": 4.939979094359581e-05,
|
| 1814 |
+
"loss": 1.3671,
|
| 1815 |
"step": 27300
|
| 1816 |
},
|
| 1817 |
{
|
| 1818 |
"epoch": 7.72,
|
| 1819 |
+
"learning_rate": 4.933120413723981e-05,
|
| 1820 |
+
"loss": 1.4092,
|
| 1821 |
"step": 27400
|
| 1822 |
},
|
| 1823 |
{
|
| 1824 |
"epoch": 7.75,
|
| 1825 |
+
"learning_rate": 4.925896067085404e-05,
|
| 1826 |
+
"loss": 1.4064,
|
| 1827 |
"step": 27500
|
| 1828 |
},
|
| 1829 |
{
|
| 1830 |
"epoch": 7.78,
|
| 1831 |
+
"learning_rate": 4.918307142403879e-05,
|
| 1832 |
+
"loss": 1.4131,
|
| 1833 |
"step": 27600
|
| 1834 |
},
|
| 1835 |
{
|
| 1836 |
"epoch": 7.81,
|
| 1837 |
+
"learning_rate": 4.91035478254355e-05,
|
| 1838 |
+
"loss": 1.4069,
|
| 1839 |
"step": 27700
|
| 1840 |
},
|
| 1841 |
{
|
| 1842 |
"epoch": 7.84,
|
| 1843 |
+
"learning_rate": 4.902040185100559e-05,
|
| 1844 |
+
"loss": 1.4013,
|
| 1845 |
"step": 27800
|
| 1846 |
},
|
| 1847 |
{
|
| 1848 |
"epoch": 7.86,
|
| 1849 |
+
"learning_rate": 4.893364602222699e-05,
|
| 1850 |
+
"loss": 1.4102,
|
| 1851 |
"step": 27900
|
| 1852 |
},
|
| 1853 |
{
|
| 1854 |
"epoch": 7.89,
|
| 1855 |
+
"learning_rate": 4.88432934042084e-05,
|
| 1856 |
+
"loss": 1.4175,
|
| 1857 |
"step": 28000
|
| 1858 |
},
|
| 1859 |
{
|
| 1860 |
"epoch": 7.89,
|
| 1861 |
"eval_gen_len": 20.0,
|
| 1862 |
+
"eval_loss": 2.1455013751983643,
|
| 1863 |
+
"eval_rouge1": 21.4843,
|
| 1864 |
+
"eval_rouge2": 5.5418,
|
| 1865 |
+
"eval_rougeL": 21.2359,
|
| 1866 |
+
"eval_rougeLsum": 21.2323,
|
| 1867 |
+
"eval_runtime": 165.871,
|
| 1868 |
+
"eval_samples_per_second": 42.25,
|
| 1869 |
+
"eval_steps_per_second": 2.641,
|
| 1870 |
"step": 28000
|
| 1871 |
},
|
| 1872 |
{
|
| 1873 |
"epoch": 7.92,
|
| 1874 |
+
"learning_rate": 4.874935760372175e-05,
|
| 1875 |
+
"loss": 1.407,
|
| 1876 |
"step": 28100
|
| 1877 |
},
|
| 1878 |
{
|
| 1879 |
"epoch": 7.95,
|
| 1880 |
+
"learning_rate": 4.865284543447741e-05,
|
| 1881 |
+
"loss": 1.4325,
|
| 1882 |
"step": 28200
|
| 1883 |
},
|
| 1884 |
{
|
| 1885 |
"epoch": 7.98,
|
| 1886 |
+
"learning_rate": 4.855182171477396e-05,
|
| 1887 |
+
"loss": 1.4169,
|
| 1888 |
"step": 28300
|
| 1889 |
},
|
| 1890 |
{
|
| 1891 |
"epoch": 8.0,
|
| 1892 |
+
"learning_rate": 4.844725870716676e-05,
|
| 1893 |
+
"loss": 1.4046,
|
| 1894 |
"step": 28400
|
| 1895 |
},
|
| 1896 |
{
|
| 1897 |
"epoch": 8.03,
|
| 1898 |
+
"learning_rate": 4.833917215846013e-05,
|
| 1899 |
+
"loss": 1.1944,
|
| 1900 |
"step": 28500
|
| 1901 |
},
|
| 1902 |
{
|
| 1903 |
"epoch": 8.06,
|
| 1904 |
+
"learning_rate": 4.822757834609075e-05,
|
| 1905 |
+
"loss": 1.2087,
|
| 1906 |
"step": 28600
|
| 1907 |
},
|
| 1908 |
{
|
| 1909 |
"epoch": 8.09,
|
| 1910 |
+
"learning_rate": 4.811249407567628e-05,
|
| 1911 |
+
"loss": 1.2257,
|
| 1912 |
"step": 28700
|
| 1913 |
},
|
| 1914 |
{
|
| 1915 |
"epoch": 8.12,
|
| 1916 |
+
"learning_rate": 4.799393667848454e-05,
|
| 1917 |
+
"loss": 1.2269,
|
| 1918 |
"step": 28800
|
| 1919 |
},
|
| 1920 |
{
|
| 1921 |
"epoch": 8.15,
|
| 1922 |
+
"learning_rate": 4.787192400882345e-05,
|
| 1923 |
+
"loss": 1.244,
|
| 1924 |
"step": 28900
|
| 1925 |
},
|
| 1926 |
{
|
| 1927 |
"epoch": 8.17,
|
| 1928 |
+
"learning_rate": 4.774647444135227e-05,
|
| 1929 |
+
"loss": 1.2302,
|
| 1930 |
"step": 29000
|
| 1931 |
},
|
| 1932 |
{
|
| 1933 |
"epoch": 8.2,
|
| 1934 |
+
"learning_rate": 4.7617606868314405e-05,
|
| 1935 |
+
"loss": 1.2461,
|
| 1936 |
"step": 29100
|
| 1937 |
},
|
| 1938 |
{
|
| 1939 |
"epoch": 8.23,
|
| 1940 |
+
"learning_rate": 4.748534069669236e-05,
|
| 1941 |
+
"loss": 1.2514,
|
| 1942 |
"step": 29200
|
| 1943 |
},
|
| 1944 |
{
|
| 1945 |
"epoch": 8.26,
|
| 1946 |
+
"learning_rate": 4.7349695845285055e-05,
|
| 1947 |
+
"loss": 1.2402,
|
| 1948 |
"step": 29300
|
| 1949 |
},
|
| 1950 |
{
|
| 1951 |
"epoch": 8.29,
|
| 1952 |
+
"learning_rate": 4.721069274170819e-05,
|
| 1953 |
+
"loss": 1.2567,
|
| 1954 |
"step": 29400
|
| 1955 |
},
|
| 1956 |
{
|
| 1957 |
"epoch": 8.31,
|
| 1958 |
+
"learning_rate": 4.706835231931785e-05,
|
| 1959 |
+
"loss": 1.2423,
|
| 1960 |
"step": 29500
|
| 1961 |
},
|
| 1962 |
{
|
| 1963 |
"epoch": 8.34,
|
| 1964 |
+
"learning_rate": 4.6922696014058083e-05,
|
| 1965 |
+
"loss": 1.2573,
|
| 1966 |
"step": 29600
|
| 1967 |
},
|
| 1968 |
{
|
| 1969 |
"epoch": 8.37,
|
| 1970 |
+
"learning_rate": 4.677374576123271e-05,
|
| 1971 |
+
"loss": 1.253,
|
| 1972 |
"step": 29700
|
| 1973 |
},
|
| 1974 |
{
|
| 1975 |
"epoch": 8.4,
|
| 1976 |
+
"learning_rate": 4.6621523992201896e-05,
|
| 1977 |
+
"loss": 1.2469,
|
| 1978 |
"step": 29800
|
| 1979 |
},
|
| 1980 |
{
|
| 1981 |
"epoch": 8.43,
|
| 1982 |
+
"learning_rate": 4.646605363100417e-05,
|
| 1983 |
+
"loss": 1.2911,
|
| 1984 |
"step": 29900
|
| 1985 |
},
|
| 1986 |
{
|
| 1987 |
"epoch": 8.46,
|
| 1988 |
+
"learning_rate": 4.6307358090904045e-05,
|
| 1989 |
+
"loss": 1.2541,
|
| 1990 |
"step": 30000
|
| 1991 |
},
|
| 1992 |
{
|
| 1993 |
"epoch": 8.46,
|
| 1994 |
"eval_gen_len": 20.0,
|
| 1995 |
+
"eval_loss": 2.217175006866455,
|
| 1996 |
+
"eval_rouge1": 20.9025,
|
| 1997 |
+
"eval_rouge2": 5.1166,
|
| 1998 |
+
"eval_rougeL": 20.7062,
|
| 1999 |
+
"eval_rougeLsum": 20.6916,
|
| 2000 |
+
"eval_runtime": 165.6707,
|
| 2001 |
+
"eval_samples_per_second": 42.301,
|
| 2002 |
+
"eval_steps_per_second": 2.644,
|
| 2003 |
"step": 30000
|
| 2004 |
},
|
| 2005 |
{
|
| 2006 |
"epoch": 8.48,
|
| 2007 |
+
"learning_rate": 4.6147096005744875e-05,
|
| 2008 |
+
"loss": 1.2806,
|
| 2009 |
"step": 30100
|
| 2010 |
},
|
| 2011 |
{
|
| 2012 |
"epoch": 8.51,
|
| 2013 |
+
"learning_rate": 4.598205393356323e-05,
|
| 2014 |
+
"loss": 1.2891,
|
| 2015 |
"step": 30200
|
| 2016 |
},
|
| 2017 |
{
|
| 2018 |
"epoch": 8.54,
|
| 2019 |
+
"learning_rate": 4.581385957105333e-05,
|
| 2020 |
+
"loss": 1.2964,
|
| 2021 |
"step": 30300
|
| 2022 |
},
|
| 2023 |
{
|
| 2024 |
"epoch": 8.57,
|
| 2025 |
+
"learning_rate": 4.564253824766751e-05,
|
| 2026 |
+
"loss": 1.2694,
|
| 2027 |
"step": 30400
|
| 2028 |
},
|
| 2029 |
{
|
| 2030 |
"epoch": 8.6,
|
| 2031 |
+
"learning_rate": 4.54681157637669e-05,
|
| 2032 |
+
"loss": 1.2883,
|
| 2033 |
"step": 30500
|
| 2034 |
},
|
| 2035 |
{
|
| 2036 |
"epoch": 8.62,
|
| 2037 |
+
"learning_rate": 4.5290618386736e-05,
|
| 2038 |
+
"loss": 1.3061,
|
| 2039 |
"step": 30600
|
| 2040 |
},
|
| 2041 |
{
|
| 2042 |
"epoch": 8.65,
|
| 2043 |
+
"learning_rate": 4.51100728470269e-05,
|
| 2044 |
+
"loss": 1.3022,
|
| 2045 |
"step": 30700
|
| 2046 |
},
|
| 2047 |
{
|
| 2048 |
"epoch": 8.68,
|
| 2049 |
+
"learning_rate": 4.492650633413379e-05,
|
| 2050 |
+
"loss": 1.2958,
|
| 2051 |
"step": 30800
|
| 2052 |
},
|
| 2053 |
{
|
| 2054 |
"epoch": 8.71,
|
| 2055 |
+
"learning_rate": 4.473994649249829e-05,
|
| 2056 |
+
"loss": 1.2966,
|
| 2057 |
"step": 30900
|
| 2058 |
},
|
| 2059 |
{
|
| 2060 |
"epoch": 8.74,
|
| 2061 |
+
"learning_rate": 4.455042141734634e-05,
|
| 2062 |
+
"loss": 1.2956,
|
| 2063 |
"step": 31000
|
| 2064 |
},
|
| 2065 |
{
|
| 2066 |
"epoch": 8.77,
|
| 2067 |
+
"learning_rate": 4.4357959650457124e-05,
|
| 2068 |
+
"loss": 1.3057,
|
| 2069 |
"step": 31100
|
| 2070 |
},
|
| 2071 |
{
|
| 2072 |
"epoch": 8.79,
|
| 2073 |
+
"learning_rate": 4.41625901758648e-05,
|
| 2074 |
+
"loss": 1.3006,
|
| 2075 |
"step": 31200
|
| 2076 |
},
|
| 2077 |
{
|
| 2078 |
"epoch": 8.82,
|
| 2079 |
+
"learning_rate": 4.396434241549363e-05,
|
| 2080 |
+
"loss": 1.311,
|
| 2081 |
"step": 31300
|
| 2082 |
},
|
| 2083 |
{
|
| 2084 |
"epoch": 8.85,
|
| 2085 |
+
"learning_rate": 4.37632462247271e-05,
|
| 2086 |
+
"loss": 1.309,
|
| 2087 |
"step": 31400
|
| 2088 |
},
|
| 2089 |
{
|
| 2090 |
"epoch": 8.88,
|
| 2091 |
+
"learning_rate": 4.355933188791186e-05,
|
| 2092 |
+
"loss": 1.3324,
|
| 2093 |
"step": 31500
|
| 2094 |
},
|
| 2095 |
{
|
| 2096 |
"epoch": 8.91,
|
| 2097 |
+
"learning_rate": 4.335263011379698e-05,
|
| 2098 |
+
"loss": 1.3186,
|
| 2099 |
"step": 31600
|
| 2100 |
},
|
| 2101 |
{
|
| 2102 |
"epoch": 8.93,
|
| 2103 |
+
"learning_rate": 4.314317203090931e-05,
|
| 2104 |
+
"loss": 1.3298,
|
| 2105 |
"step": 31700
|
| 2106 |
},
|
| 2107 |
{
|
| 2108 |
"epoch": 8.96,
|
| 2109 |
+
"learning_rate": 4.2930989182865715e-05,
|
| 2110 |
+
"loss": 1.3148,
|
| 2111 |
"step": 31800
|
| 2112 |
},
|
| 2113 |
{
|
| 2114 |
"epoch": 8.99,
|
| 2115 |
+
"learning_rate": 4.271611352362262e-05,
|
| 2116 |
+
"loss": 1.3318,
|
| 2117 |
"step": 31900
|
| 2118 |
},
|
| 2119 |
{
|
| 2120 |
"epoch": 9.02,
|
| 2121 |
+
"learning_rate": 4.2498577412663946e-05,
|
| 2122 |
+
"loss": 1.1331,
|
| 2123 |
"step": 32000
|
| 2124 |
},
|
| 2125 |
{
|
| 2126 |
"epoch": 9.02,
|
| 2127 |
"eval_gen_len": 20.0,
|
| 2128 |
+
"eval_loss": 2.278179168701172,
|
| 2129 |
+
"eval_rouge1": 20.9415,
|
| 2130 |
+
"eval_rouge2": 5.2115,
|
| 2131 |
+
"eval_rougeL": 20.7647,
|
| 2132 |
+
"eval_rougeLsum": 20.7806,
|
| 2133 |
+
"eval_runtime": 166.4103,
|
| 2134 |
+
"eval_samples_per_second": 42.113,
|
| 2135 |
+
"eval_steps_per_second": 2.632,
|
| 2136 |
"step": 32000
|
| 2137 |
},
|
| 2138 |
{
|
| 2139 |
"epoch": 9.05,
|
| 2140 |
+
"learning_rate": 4.2278413610127834e-05,
|
| 2141 |
+
"loss": 1.0677,
|
| 2142 |
"step": 32100
|
| 2143 |
},
|
| 2144 |
{
|
| 2145 |
"epoch": 9.08,
|
| 2146 |
+
"learning_rate": 4.205565527187312e-05,
|
| 2147 |
+
"loss": 1.0712,
|
| 2148 |
"step": 32200
|
| 2149 |
},
|
| 2150 |
{
|
| 2151 |
"epoch": 9.1,
|
| 2152 |
+
"learning_rate": 4.183033594448618e-05,
|
| 2153 |
+
"loss": 1.0928,
|
| 2154 |
"step": 32300
|
| 2155 |
},
|
| 2156 |
{
|
| 2157 |
"epoch": 9.13,
|
| 2158 |
+
"learning_rate": 4.160248956022893e-05,
|
| 2159 |
+
"loss": 1.0821,
|
| 2160 |
"step": 32400
|
| 2161 |
},
|
| 2162 |
{
|
| 2163 |
"epoch": 9.16,
|
| 2164 |
+
"learning_rate": 4.137215043192875e-05,
|
| 2165 |
+
"loss": 1.0988,
|
| 2166 |
"step": 32500
|
| 2167 |
},
|
| 2168 |
{
|
| 2169 |
"epoch": 9.19,
|
| 2170 |
+
"learning_rate": 4.11393532478111e-05,
|
| 2171 |
+
"loss": 1.103,
|
| 2172 |
"step": 32600
|
| 2173 |
},
|
| 2174 |
{
|
| 2175 |
"epoch": 9.22,
|
| 2176 |
+
"learning_rate": 4.0904133066275636e-05,
|
| 2177 |
+
"loss": 1.1109,
|
| 2178 |
"step": 32700
|
| 2179 |
},
|
| 2180 |
{
|
| 2181 |
"epoch": 9.24,
|
| 2182 |
+
"learning_rate": 4.066652531061647e-05,
|
| 2183 |
+
"loss": 1.0833,
|
| 2184 |
"step": 32800
|
| 2185 |
},
|
| 2186 |
{
|
| 2187 |
"epoch": 9.27,
|
| 2188 |
+
"learning_rate": 4.0426565763687624e-05,
|
| 2189 |
+
"loss": 1.0964,
|
| 2190 |
"step": 32900
|
| 2191 |
},
|
| 2192 |
{
|
| 2193 |
"epoch": 9.3,
|
| 2194 |
+
"learning_rate": 4.0184290562514214e-05,
|
| 2195 |
+
"loss": 1.1168,
|
| 2196 |
"step": 33000
|
| 2197 |
},
|
| 2198 |
{
|
| 2199 |
"epoch": 9.33,
|
| 2200 |
+
"learning_rate": 3.9939736192850386e-05,
|
| 2201 |
+
"loss": 1.1122,
|
| 2202 |
"step": 33100
|
| 2203 |
},
|
| 2204 |
{
|
| 2205 |
"epoch": 9.36,
|
| 2206 |
+
"learning_rate": 3.969293948368467e-05,
|
| 2207 |
+
"loss": 1.1165,
|
| 2208 |
"step": 33200
|
| 2209 |
},
|
| 2210 |
{
|
| 2211 |
"epoch": 9.39,
|
| 2212 |
+
"learning_rate": 3.944393760169368e-05,
|
| 2213 |
+
"loss": 1.1106,
|
| 2214 |
"step": 33300
|
| 2215 |
},
|
| 2216 |
{
|
| 2217 |
"epoch": 9.41,
|
| 2218 |
+
"learning_rate": 3.9192768045644926e-05,
|
| 2219 |
+
"loss": 1.1119,
|
| 2220 |
"step": 33400
|
| 2221 |
},
|
| 2222 |
{
|
| 2223 |
"epoch": 9.44,
|
| 2224 |
+
"learning_rate": 3.8939468640749696e-05,
|
| 2225 |
+
"loss": 1.1258,
|
| 2226 |
"step": 33500
|
| 2227 |
},
|
| 2228 |
{
|
| 2229 |
"epoch": 9.47,
|
| 2230 |
+
"learning_rate": 3.868407753296665e-05,
|
| 2231 |
+
"loss": 1.099,
|
| 2232 |
"step": 33600
|
| 2233 |
},
|
| 2234 |
{
|
| 2235 |
"epoch": 9.5,
|
| 2236 |
+
"learning_rate": 3.842921766325347e-05,
|
| 2237 |
+
"loss": 1.1246,
|
| 2238 |
"step": 33700
|
| 2239 |
},
|
| 2240 |
{
|
| 2241 |
"epoch": 9.53,
|
| 2242 |
+
"learning_rate": 3.816977879359396e-05,
|
| 2243 |
+
"loss": 1.1175,
|
| 2244 |
"step": 33800
|
| 2245 |
},
|
| 2246 |
{
|
| 2247 |
"epoch": 9.55,
|
| 2248 |
+
"learning_rate": 3.790836413350648e-05,
|
| 2249 |
+
"loss": 1.1313,
|
| 2250 |
"step": 33900
|
| 2251 |
},
|
| 2252 |
{
|
| 2253 |
"epoch": 9.58,
|
| 2254 |
+
"learning_rate": 3.764501305107728e-05,
|
| 2255 |
+
"loss": 1.1067,
|
| 2256 |
"step": 34000
|
| 2257 |
},
|
| 2258 |
{
|
| 2259 |
"epoch": 9.58,
|
| 2260 |
"eval_gen_len": 20.0,
|
| 2261 |
+
"eval_loss": 2.27223801612854,
|
| 2262 |
+
"eval_rouge1": 21.5648,
|
| 2263 |
+
"eval_rouge2": 5.4445,
|
| 2264 |
+
"eval_rougeL": 21.3624,
|
| 2265 |
+
"eval_rougeLsum": 21.3838,
|
| 2266 |
+
"eval_runtime": 166.4194,
|
| 2267 |
+
"eval_samples_per_second": 42.11,
|
| 2268 |
+
"eval_steps_per_second": 2.632,
|
| 2269 |
"step": 34000
|
| 2270 |
},
|
| 2271 |
{
|
| 2272 |
"epoch": 9.61,
|
| 2273 |
+
"learning_rate": 3.737976520601068e-05,
|
| 2274 |
+
"loss": 1.1316,
|
| 2275 |
"step": 34100
|
| 2276 |
},
|
| 2277 |
{
|
| 2278 |
"epoch": 9.64,
|
| 2279 |
+
"learning_rate": 3.7112660543656495e-05,
|
| 2280 |
+
"loss": 1.137,
|
| 2281 |
"step": 34200
|
| 2282 |
},
|
| 2283 |
{
|
| 2284 |
"epoch": 9.67,
|
| 2285 |
+
"learning_rate": 3.6843739288994395e-05,
|
| 2286 |
+
"loss": 1.1319,
|
| 2287 |
"step": 34300
|
| 2288 |
},
|
| 2289 |
{
|
| 2290 |
"epoch": 9.7,
|
| 2291 |
+
"learning_rate": 3.657304194057615e-05,
|
| 2292 |
+
"loss": 1.1217,
|
| 2293 |
"step": 34400
|
| 2294 |
},
|
| 2295 |
{
|
| 2296 |
"epoch": 9.72,
|
| 2297 |
+
"learning_rate": 3.630060926442673e-05,
|
| 2298 |
+
"loss": 1.1465,
|
| 2299 |
"step": 34500
|
| 2300 |
},
|
| 2301 |
{
|
| 2302 |
"epoch": 9.75,
|
| 2303 |
+
"learning_rate": 3.602648228790508e-05,
|
| 2304 |
+
"loss": 1.1396,
|
| 2305 |
"step": 34600
|
| 2306 |
},
|
| 2307 |
{
|
| 2308 |
"epoch": 9.78,
|
| 2309 |
+
"learning_rate": 3.5750702293525555e-05,
|
| 2310 |
+
"loss": 1.132,
|
| 2311 |
"step": 34700
|
| 2312 |
},
|
| 2313 |
{
|
| 2314 |
"epoch": 9.81,
|
| 2315 |
+
"learning_rate": 3.5473310812740905e-05,
|
| 2316 |
+
"loss": 1.159,
|
| 2317 |
"step": 34800
|
| 2318 |
},
|
| 2319 |
{
|
| 2320 |
"epoch": 9.84,
|
| 2321 |
+
"learning_rate": 3.519434961968779e-05,
|
| 2322 |
+
"loss": 1.1484,
|
| 2323 |
"step": 34900
|
| 2324 |
},
|
| 2325 |
{
|
| 2326 |
"epoch": 9.86,
|
| 2327 |
+
"learning_rate": 3.491386072489581e-05,
|
| 2328 |
+
"loss": 1.1375,
|
| 2329 |
"step": 35000
|
| 2330 |
},
|
| 2331 |
{
|
| 2332 |
"epoch": 9.89,
|
| 2333 |
+
"learning_rate": 3.4631886368960794e-05,
|
| 2334 |
+
"loss": 1.1493,
|
| 2335 |
"step": 35100
|
| 2336 |
},
|
| 2337 |
{
|
| 2338 |
"epoch": 9.92,
|
| 2339 |
+
"learning_rate": 3.434846901618357e-05,
|
| 2340 |
+
"loss": 1.1374,
|
| 2341 |
"step": 35200
|
| 2342 |
},
|
| 2343 |
{
|
| 2344 |
"epoch": 9.95,
|
| 2345 |
+
"learning_rate": 3.406365134817494e-05,
|
| 2346 |
+
"loss": 1.1569,
|
| 2347 |
"step": 35300
|
| 2348 |
},
|
| 2349 |
{
|
| 2350 |
"epoch": 9.98,
|
| 2351 |
+
"learning_rate": 3.3777476257428106e-05,
|
| 2352 |
+
"loss": 1.1441,
|
| 2353 |
"step": 35400
|
| 2354 |
},
|
| 2355 |
{
|
| 2356 |
"epoch": 10.0,
|
| 2357 |
"step": 35480,
|
| 2358 |
"total_flos": 2.3762843604025344e+17,
|
| 2359 |
+
"train_loss": 1.581618417182931,
|
| 2360 |
+
"train_runtime": 14068.2834,
|
| 2361 |
+
"train_samples_per_second": 40.346,
|
| 2362 |
+
"train_steps_per_second": 2.522
|
| 2363 |
}
|
| 2364 |
],
|
| 2365 |
"max_steps": 35480,
|
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:ccb6c58ad85c6302cbcc0ea2d49c40e211911e0bcc1dfc125087695e4f753b0c
|
| 3 |
+
size 3503
|