Hello zabanshenas
Browse files- config.json +25 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +473 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"transformers_version": "4.8.0.dev0",
|
| 22 |
+
"type_vocab_size": 2,
|
| 23 |
+
"use_cache": true,
|
| 24 |
+
"vocab_size": 32000
|
| 25 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9d268cf15505b9efa12ac4686c99ea308d39d9ae0a3d824faaf3423208c864c
|
| 3 |
+
size 442689387
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/content/checkpoint-79500", "tokenizer_class": "RobertaTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,473 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.999939507591797,
|
| 5 |
+
"global_step": 82650,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.12,
|
| 12 |
+
"learning_rate": 5e-05,
|
| 13 |
+
"loss": 9.0179,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"eval_loss": 8.008028984069824,
|
| 19 |
+
"eval_runtime": 354.8383,
|
| 20 |
+
"eval_samples_per_second": 41.117,
|
| 21 |
+
"eval_steps_per_second": 5.14,
|
| 22 |
+
"step": 1000
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.24,
|
| 26 |
+
"learning_rate": 0.0001,
|
| 27 |
+
"loss": 7.589,
|
| 28 |
+
"step": 2000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.24,
|
| 32 |
+
"eval_loss": 7.217428684234619,
|
| 33 |
+
"eval_runtime": 357.6188,
|
| 34 |
+
"eval_samples_per_second": 40.798,
|
| 35 |
+
"eval_steps_per_second": 5.1,
|
| 36 |
+
"step": 2000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.36,
|
| 40 |
+
"learning_rate": 9.876007439553628e-05,
|
| 41 |
+
"loss": 7.0805,
|
| 42 |
+
"step": 3000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.36,
|
| 46 |
+
"eval_loss": 6.8754563331604,
|
| 47 |
+
"eval_runtime": 339.2212,
|
| 48 |
+
"eval_samples_per_second": 43.01,
|
| 49 |
+
"eval_steps_per_second": 5.377,
|
| 50 |
+
"step": 3000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.48,
|
| 54 |
+
"learning_rate": 9.752014879107254e-05,
|
| 55 |
+
"loss": 6.8341,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.48,
|
| 60 |
+
"eval_loss": 6.731923580169678,
|
| 61 |
+
"eval_runtime": 339.5448,
|
| 62 |
+
"eval_samples_per_second": 42.969,
|
| 63 |
+
"eval_steps_per_second": 5.372,
|
| 64 |
+
"step": 4000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.6,
|
| 68 |
+
"learning_rate": 9.628022318660881e-05,
|
| 69 |
+
"loss": 6.5597,
|
| 70 |
+
"step": 5000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.6,
|
| 74 |
+
"eval_loss": 6.266661643981934,
|
| 75 |
+
"eval_runtime": 339.3392,
|
| 76 |
+
"eval_samples_per_second": 42.995,
|
| 77 |
+
"eval_steps_per_second": 5.375,
|
| 78 |
+
"step": 5000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.73,
|
| 82 |
+
"learning_rate": 9.504029758214508e-05,
|
| 83 |
+
"loss": 6.1904,
|
| 84 |
+
"step": 6000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.73,
|
| 88 |
+
"eval_loss": 6.067315101623535,
|
| 89 |
+
"eval_runtime": 354.6519,
|
| 90 |
+
"eval_samples_per_second": 41.139,
|
| 91 |
+
"eval_steps_per_second": 5.143,
|
| 92 |
+
"step": 6000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.85,
|
| 96 |
+
"learning_rate": 9.380037197768134e-05,
|
| 97 |
+
"loss": 6.05,
|
| 98 |
+
"step": 7000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.85,
|
| 102 |
+
"eval_loss": 5.955410957336426,
|
| 103 |
+
"eval_runtime": 357.6298,
|
| 104 |
+
"eval_samples_per_second": 40.796,
|
| 105 |
+
"eval_steps_per_second": 5.1,
|
| 106 |
+
"step": 7000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 1.09,
|
| 110 |
+
"learning_rate": 9.132176069435834e-05,
|
| 111 |
+
"loss": 5.8802,
|
| 112 |
+
"step": 9000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 1.09,
|
| 116 |
+
"eval_loss": 5.814595699310303,
|
| 117 |
+
"eval_runtime": 333.2969,
|
| 118 |
+
"eval_samples_per_second": 43.775,
|
| 119 |
+
"eval_steps_per_second": 5.473,
|
| 120 |
+
"step": 9000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.45,
|
| 124 |
+
"learning_rate": 8.76032238065716e-05,
|
| 125 |
+
"loss": 5.7503,
|
| 126 |
+
"step": 12000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.45,
|
| 130 |
+
"eval_loss": 5.659432888031006,
|
| 131 |
+
"eval_runtime": 337.2485,
|
| 132 |
+
"eval_samples_per_second": 43.262,
|
| 133 |
+
"eval_steps_per_second": 5.408,
|
| 134 |
+
"step": 12000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.81,
|
| 138 |
+
"learning_rate": 8.388468691878487e-05,
|
| 139 |
+
"loss": 5.6093,
|
| 140 |
+
"step": 15000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.81,
|
| 144 |
+
"eval_loss": 5.4909515380859375,
|
| 145 |
+
"eval_runtime": 333.385,
|
| 146 |
+
"eval_samples_per_second": 43.763,
|
| 147 |
+
"eval_steps_per_second": 5.471,
|
| 148 |
+
"step": 15000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.18,
|
| 152 |
+
"learning_rate": 8.016615003099814e-05,
|
| 153 |
+
"loss": 5.3841,
|
| 154 |
+
"step": 18000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.18,
|
| 158 |
+
"eval_loss": 5.236297130584717,
|
| 159 |
+
"eval_runtime": 337.7351,
|
| 160 |
+
"eval_samples_per_second": 43.2,
|
| 161 |
+
"eval_steps_per_second": 5.401,
|
| 162 |
+
"step": 18000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 2.54,
|
| 166 |
+
"learning_rate": 7.644761314321141e-05,
|
| 167 |
+
"loss": 5.098,
|
| 168 |
+
"step": 21000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 2.54,
|
| 172 |
+
"eval_loss": 4.817739486694336,
|
| 173 |
+
"eval_runtime": 337.6417,
|
| 174 |
+
"eval_samples_per_second": 43.211,
|
| 175 |
+
"eval_steps_per_second": 5.402,
|
| 176 |
+
"step": 21000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.9,
|
| 180 |
+
"learning_rate": 7.272907625542468e-05,
|
| 181 |
+
"loss": 4.71,
|
| 182 |
+
"step": 24000
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.9,
|
| 186 |
+
"eval_loss": 4.514278411865234,
|
| 187 |
+
"eval_runtime": 333.4053,
|
| 188 |
+
"eval_samples_per_second": 43.761,
|
| 189 |
+
"eval_steps_per_second": 5.471,
|
| 190 |
+
"step": 24000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.27,
|
| 194 |
+
"learning_rate": 6.901177929324241e-05,
|
| 195 |
+
"loss": 4.4553,
|
| 196 |
+
"step": 27000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.27,
|
| 200 |
+
"eval_loss": 4.293982028961182,
|
| 201 |
+
"eval_runtime": 337.4791,
|
| 202 |
+
"eval_samples_per_second": 43.232,
|
| 203 |
+
"eval_steps_per_second": 5.405,
|
| 204 |
+
"step": 27000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 3.63,
|
| 208 |
+
"learning_rate": 6.529324240545568e-05,
|
| 209 |
+
"loss": 4.2619,
|
| 210 |
+
"step": 30000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.63,
|
| 214 |
+
"eval_loss": 4.119041442871094,
|
| 215 |
+
"eval_runtime": 333.3435,
|
| 216 |
+
"eval_samples_per_second": 43.769,
|
| 217 |
+
"eval_steps_per_second": 5.472,
|
| 218 |
+
"step": 30000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.99,
|
| 222 |
+
"learning_rate": 6.157470551766893e-05,
|
| 223 |
+
"loss": 4.0868,
|
| 224 |
+
"step": 33000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.99,
|
| 228 |
+
"eval_loss": 3.902297258377075,
|
| 229 |
+
"eval_runtime": 337.8221,
|
| 230 |
+
"eval_samples_per_second": 43.188,
|
| 231 |
+
"eval_steps_per_second": 5.399,
|
| 232 |
+
"step": 33000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 4.36,
|
| 236 |
+
"learning_rate": 5.785740855548667e-05,
|
| 237 |
+
"loss": 3.8931,
|
| 238 |
+
"step": 36000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 4.36,
|
| 242 |
+
"eval_loss": 3.7250819206237793,
|
| 243 |
+
"eval_runtime": 337.5683,
|
| 244 |
+
"eval_samples_per_second": 43.221,
|
| 245 |
+
"eval_steps_per_second": 5.403,
|
| 246 |
+
"step": 36000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 4.72,
|
| 250 |
+
"learning_rate": 5.413887166769994e-05,
|
| 251 |
+
"loss": 3.7433,
|
| 252 |
+
"step": 39000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 4.72,
|
| 256 |
+
"eval_loss": 3.6013708114624023,
|
| 257 |
+
"eval_runtime": 333.4516,
|
| 258 |
+
"eval_samples_per_second": 43.754,
|
| 259 |
+
"eval_steps_per_second": 5.47,
|
| 260 |
+
"step": 39000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 5.08,
|
| 264 |
+
"learning_rate": 5.0420334779913205e-05,
|
| 265 |
+
"loss": 3.6398,
|
| 266 |
+
"step": 42000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.08,
|
| 270 |
+
"eval_loss": 3.514371633529663,
|
| 271 |
+
"eval_runtime": 337.9252,
|
| 272 |
+
"eval_samples_per_second": 43.175,
|
| 273 |
+
"eval_steps_per_second": 5.398,
|
| 274 |
+
"step": 42000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 5.44,
|
| 278 |
+
"learning_rate": 4.670179789212647e-05,
|
| 279 |
+
"loss": 3.5446,
|
| 280 |
+
"step": 45000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 5.44,
|
| 284 |
+
"eval_loss": 3.439208984375,
|
| 285 |
+
"eval_runtime": 333.2805,
|
| 286 |
+
"eval_samples_per_second": 43.777,
|
| 287 |
+
"eval_steps_per_second": 5.473,
|
| 288 |
+
"step": 45000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 5.81,
|
| 292 |
+
"learning_rate": 4.298326100433974e-05,
|
| 293 |
+
"loss": 3.4674,
|
| 294 |
+
"step": 48000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.81,
|
| 298 |
+
"eval_loss": 3.360422372817993,
|
| 299 |
+
"eval_runtime": 337.4986,
|
| 300 |
+
"eval_samples_per_second": 43.23,
|
| 301 |
+
"eval_steps_per_second": 5.404,
|
| 302 |
+
"step": 48000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.17,
|
| 306 |
+
"learning_rate": 3.926472411655301e-05,
|
| 307 |
+
"loss": 3.3896,
|
| 308 |
+
"step": 51000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 6.17,
|
| 312 |
+
"eval_loss": 3.3044984340667725,
|
| 313 |
+
"eval_runtime": 337.3599,
|
| 314 |
+
"eval_samples_per_second": 43.248,
|
| 315 |
+
"eval_steps_per_second": 5.407,
|
| 316 |
+
"step": 51000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 6.53,
|
| 320 |
+
"learning_rate": 3.554618722876628e-05,
|
| 321 |
+
"loss": 3.3327,
|
| 322 |
+
"step": 54000
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 6.53,
|
| 326 |
+
"eval_loss": 3.2497129440307617,
|
| 327 |
+
"eval_runtime": 333.3738,
|
| 328 |
+
"eval_samples_per_second": 43.765,
|
| 329 |
+
"eval_steps_per_second": 5.471,
|
| 330 |
+
"step": 54000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 6.9,
|
| 334 |
+
"learning_rate": 3.1828890266584005e-05,
|
| 335 |
+
"loss": 3.2596,
|
| 336 |
+
"step": 57000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 6.9,
|
| 340 |
+
"eval_loss": 3.208232879638672,
|
| 341 |
+
"eval_runtime": 333.2588,
|
| 342 |
+
"eval_samples_per_second": 43.78,
|
| 343 |
+
"eval_steps_per_second": 5.473,
|
| 344 |
+
"step": 57000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 7.26,
|
| 348 |
+
"learning_rate": 2.811035337879727e-05,
|
| 349 |
+
"loss": 3.2211,
|
| 350 |
+
"step": 60000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 7.26,
|
| 354 |
+
"eval_loss": 3.1547913551330566,
|
| 355 |
+
"eval_runtime": 337.1177,
|
| 356 |
+
"eval_samples_per_second": 43.279,
|
| 357 |
+
"eval_steps_per_second": 5.411,
|
| 358 |
+
"step": 60000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 7.62,
|
| 362 |
+
"learning_rate": 2.4391816491010542e-05,
|
| 363 |
+
"loss": 3.1913,
|
| 364 |
+
"step": 63000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 7.62,
|
| 368 |
+
"eval_loss": 3.1304616928100586,
|
| 369 |
+
"eval_runtime": 337.6326,
|
| 370 |
+
"eval_samples_per_second": 43.213,
|
| 371 |
+
"eval_steps_per_second": 5.402,
|
| 372 |
+
"step": 63000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 7.99,
|
| 376 |
+
"learning_rate": 2.0673279603223807e-05,
|
| 377 |
+
"loss": 3.1425,
|
| 378 |
+
"step": 66000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 7.99,
|
| 382 |
+
"eval_loss": 3.0831258296966553,
|
| 383 |
+
"eval_runtime": 333.274,
|
| 384 |
+
"eval_samples_per_second": 43.778,
|
| 385 |
+
"eval_steps_per_second": 5.473,
|
| 386 |
+
"step": 66000
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 8.35,
|
| 390 |
+
"learning_rate": 1.6955982641041537e-05,
|
| 391 |
+
"loss": 3.1002,
|
| 392 |
+
"step": 69000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 8.35,
|
| 396 |
+
"eval_loss": 3.049844741821289,
|
| 397 |
+
"eval_runtime": 337.2388,
|
| 398 |
+
"eval_samples_per_second": 43.263,
|
| 399 |
+
"eval_steps_per_second": 5.409,
|
| 400 |
+
"step": 69000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 8.71,
|
| 404 |
+
"learning_rate": 1.3237445753254804e-05,
|
| 405 |
+
"loss": 3.0675,
|
| 406 |
+
"step": 72000
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 8.71,
|
| 410 |
+
"eval_loss": 3.028550624847412,
|
| 411 |
+
"eval_runtime": 333.2341,
|
| 412 |
+
"eval_samples_per_second": 43.783,
|
| 413 |
+
"eval_steps_per_second": 5.474,
|
| 414 |
+
"step": 72000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.07,
|
| 418 |
+
"learning_rate": 9.517668939863609e-06,
|
| 419 |
+
"loss": 3.0515,
|
| 420 |
+
"step": 75000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 9.07,
|
| 424 |
+
"eval_loss": 2.9997730255126953,
|
| 425 |
+
"eval_runtime": 337.3815,
|
| 426 |
+
"eval_samples_per_second": 43.245,
|
| 427 |
+
"eval_steps_per_second": 5.406,
|
| 428 |
+
"step": 75000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 9.44,
|
| 432 |
+
"learning_rate": 5.80037197768134e-06,
|
| 433 |
+
"loss": 3.021,
|
| 434 |
+
"step": 78000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 9.44,
|
| 438 |
+
"eval_loss": 2.982238292694092,
|
| 439 |
+
"eval_runtime": 337.6502,
|
| 440 |
+
"eval_samples_per_second": 43.21,
|
| 441 |
+
"eval_steps_per_second": 5.402,
|
| 442 |
+
"step": 78000
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 9.8,
|
| 446 |
+
"learning_rate": 2.0805951642901425e-06,
|
| 447 |
+
"loss": 2.996,
|
| 448 |
+
"step": 81000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 9.8,
|
| 452 |
+
"eval_loss": 2.9674391746520996,
|
| 453 |
+
"eval_runtime": 333.3185,
|
| 454 |
+
"eval_samples_per_second": 43.772,
|
| 455 |
+
"eval_steps_per_second": 5.472,
|
| 456 |
+
"step": 81000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 10.0,
|
| 460 |
+
"step": 82650,
|
| 461 |
+
"total_flos": 2.2475936453492736e+17,
|
| 462 |
+
"train_loss": 0.11406417782062916,
|
| 463 |
+
"train_runtime": 1932.5263,
|
| 464 |
+
"train_samples_per_second": 684.301,
|
| 465 |
+
"train_steps_per_second": 42.768
|
| 466 |
+
}
|
| 467 |
+
],
|
| 468 |
+
"max_steps": 82650,
|
| 469 |
+
"num_train_epochs": 10,
|
| 470 |
+
"total_flos": 2.2475936453492736e+17,
|
| 471 |
+
"trial_name": null,
|
| 472 |
+
"trial_params": null
|
| 473 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|