push model to huggingface
Browse files- added_tokens.json +8 -0
- config.json +41 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +9 -0
- trainer_state.json +324 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|BOS|>": 50258,
|
| 3 |
+
"<|EOS|>": 50259,
|
| 4 |
+
"<|PAD|>": 50261,
|
| 5 |
+
"<|SEP|>": 50262,
|
| 6 |
+
"<|UNK|>": 50260,
|
| 7 |
+
"<|endoftext|>": 50257
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "NlpHUST/gpt2-vietnamese",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.0,
|
| 8 |
+
"bos_token_id": 50258,
|
| 9 |
+
"embd_pdrop": 0.0,
|
| 10 |
+
"eos_token_id": 50259,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"layer_norm_epsilon": 1e-05,
|
| 13 |
+
"model_type": "gpt2",
|
| 14 |
+
"n_ctx": 1024,
|
| 15 |
+
"n_embd": 768,
|
| 16 |
+
"n_head": 12,
|
| 17 |
+
"n_inner": null,
|
| 18 |
+
"n_layer": 12,
|
| 19 |
+
"n_positions": 1024,
|
| 20 |
+
"pad_token_id": 50261,
|
| 21 |
+
"reorder_and_upcast_attn": false,
|
| 22 |
+
"resid_pdrop": 0.0,
|
| 23 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 24 |
+
"scale_attn_weights": true,
|
| 25 |
+
"sep_token_id": 50262,
|
| 26 |
+
"summary_activation": null,
|
| 27 |
+
"summary_first_dropout": 0.1,
|
| 28 |
+
"summary_proj_to_labels": true,
|
| 29 |
+
"summary_type": "cls_index",
|
| 30 |
+
"summary_use_proj": true,
|
| 31 |
+
"task_specific_params": {
|
| 32 |
+
"text-generation": {
|
| 33 |
+
"do_sample": true,
|
| 34 |
+
"max_length": 50
|
| 35 |
+
}
|
| 36 |
+
},
|
| 37 |
+
"torch_dtype": "float32",
|
| 38 |
+
"transformers_version": "4.20.1",
|
| 39 |
+
"use_cache": true,
|
| 40 |
+
"vocab_size": 50263
|
| 41 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ddbaaf9cad6038d99a725bf4fc650379531ee8a9348644e6c6a1a734df95d85
|
| 3 |
+
size 705799823
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bba41e8da4a1012c71b55cef40a603d9569093a56035ab3af974e7b0a5bf7a15
|
| 3 |
+
size 664823739
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a44fa3535cdecdce83741c5b54c1c1361c7c2b3241fd09b223d4f51457d3faf3
|
| 3 |
+
size 13620
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16bcb1dff0ee0cc11a1850ea8af22140aeb826e6b971b12729c9d01aaaca9528
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<|BOS|>",
|
| 3 |
+
"eos_token": "<|EOS|>",
|
| 4 |
+
"pad_token": "<|PAD|>",
|
| 5 |
+
"sep_token": "<|SEP|>",
|
| 6 |
+
"unk_token": "<|UNK|>"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<|endoftext|>",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"name_or_path": "NlpHUST/gpt2-vietnamese",
|
| 6 |
+
"special_tokens_map_file": null,
|
| 7 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 8 |
+
"unk_token": "<|endoftext|>"
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,324 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9393565058708191,
|
| 3 |
+
"best_model_checkpoint": "./checkpoint-220",
|
| 4 |
+
"epoch": 5.930232558139535,
|
| 5 |
+
"global_step": 220,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.27,
|
| 12 |
+
"learning_rate": 5e-05,
|
| 13 |
+
"loss": 6.7937,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.27,
|
| 18 |
+
"eval_loss": 6.501975059509277,
|
| 19 |
+
"eval_runtime": 33.9782,
|
| 20 |
+
"eval_samples_per_second": 59.685,
|
| 21 |
+
"eval_steps_per_second": 1.884,
|
| 22 |
+
"step": 10
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.53,
|
| 26 |
+
"learning_rate": 0.0001,
|
| 27 |
+
"loss": 5.985,
|
| 28 |
+
"step": 20
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.53,
|
| 32 |
+
"eval_loss": 5.326801776885986,
|
| 33 |
+
"eval_runtime": 18.802,
|
| 34 |
+
"eval_samples_per_second": 107.861,
|
| 35 |
+
"eval_steps_per_second": 3.404,
|
| 36 |
+
"step": 20
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.8,
|
| 40 |
+
"learning_rate": 0.00015,
|
| 41 |
+
"loss": 4.6798,
|
| 42 |
+
"step": 30
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.8,
|
| 46 |
+
"eval_loss": 3.829317331314087,
|
| 47 |
+
"eval_runtime": 18.7742,
|
| 48 |
+
"eval_samples_per_second": 108.021,
|
| 49 |
+
"eval_steps_per_second": 3.409,
|
| 50 |
+
"step": 30
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.08,
|
| 54 |
+
"learning_rate": 0.0002,
|
| 55 |
+
"loss": 3.0462,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 1.08,
|
| 60 |
+
"eval_loss": 1.9157757759094238,
|
| 61 |
+
"eval_runtime": 18.7907,
|
| 62 |
+
"eval_samples_per_second": 107.926,
|
| 63 |
+
"eval_steps_per_second": 3.406,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 1.35,
|
| 68 |
+
"learning_rate": 0.00025,
|
| 69 |
+
"loss": 1.5197,
|
| 70 |
+
"step": 50
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.35,
|
| 74 |
+
"eval_loss": 1.2286747694015503,
|
| 75 |
+
"eval_runtime": 18.812,
|
| 76 |
+
"eval_samples_per_second": 107.804,
|
| 77 |
+
"eval_steps_per_second": 3.402,
|
| 78 |
+
"step": 50
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 1.61,
|
| 82 |
+
"learning_rate": 0.0003,
|
| 83 |
+
"loss": 1.1349,
|
| 84 |
+
"step": 60
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.61,
|
| 88 |
+
"eval_loss": 1.1046648025512695,
|
| 89 |
+
"eval_runtime": 18.8413,
|
| 90 |
+
"eval_samples_per_second": 107.636,
|
| 91 |
+
"eval_steps_per_second": 3.397,
|
| 92 |
+
"step": 60
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.88,
|
| 96 |
+
"learning_rate": 0.00035,
|
| 97 |
+
"loss": 1.0718,
|
| 98 |
+
"step": 70
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.88,
|
| 102 |
+
"eval_loss": 1.0654218196868896,
|
| 103 |
+
"eval_runtime": 18.8231,
|
| 104 |
+
"eval_samples_per_second": 107.74,
|
| 105 |
+
"eval_steps_per_second": 3.4,
|
| 106 |
+
"step": 70
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 2.16,
|
| 110 |
+
"learning_rate": 0.0004,
|
| 111 |
+
"loss": 1.0987,
|
| 112 |
+
"step": 80
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.16,
|
| 116 |
+
"eval_loss": 1.0404733419418335,
|
| 117 |
+
"eval_runtime": 18.8082,
|
| 118 |
+
"eval_samples_per_second": 107.825,
|
| 119 |
+
"eval_steps_per_second": 3.403,
|
| 120 |
+
"step": 80
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 2.43,
|
| 124 |
+
"learning_rate": 0.00045000000000000004,
|
| 125 |
+
"loss": 1.0133,
|
| 126 |
+
"step": 90
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 2.43,
|
| 130 |
+
"eval_loss": 1.0208371877670288,
|
| 131 |
+
"eval_runtime": 18.8192,
|
| 132 |
+
"eval_samples_per_second": 107.762,
|
| 133 |
+
"eval_steps_per_second": 3.401,
|
| 134 |
+
"step": 90
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.69,
|
| 138 |
+
"learning_rate": 0.0005,
|
| 139 |
+
"loss": 0.9869,
|
| 140 |
+
"step": 100
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.69,
|
| 144 |
+
"eval_loss": 1.0047191381454468,
|
| 145 |
+
"eval_runtime": 18.852,
|
| 146 |
+
"eval_samples_per_second": 107.575,
|
| 147 |
+
"eval_steps_per_second": 3.395,
|
| 148 |
+
"step": 100
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.96,
|
| 152 |
+
"learning_rate": 0.00045901639344262296,
|
| 153 |
+
"loss": 0.9809,
|
| 154 |
+
"step": 110
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.96,
|
| 158 |
+
"eval_loss": 0.9912181496620178,
|
| 159 |
+
"eval_runtime": 18.8516,
|
| 160 |
+
"eval_samples_per_second": 107.577,
|
| 161 |
+
"eval_steps_per_second": 3.395,
|
| 162 |
+
"step": 110
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 3.24,
|
| 166 |
+
"learning_rate": 0.0004180327868852459,
|
| 167 |
+
"loss": 1.0275,
|
| 168 |
+
"step": 120
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 3.24,
|
| 172 |
+
"eval_loss": 0.9803428649902344,
|
| 173 |
+
"eval_runtime": 18.8293,
|
| 174 |
+
"eval_samples_per_second": 107.705,
|
| 175 |
+
"eval_steps_per_second": 3.399,
|
| 176 |
+
"step": 120
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.5,
|
| 180 |
+
"learning_rate": 0.0003770491803278688,
|
| 181 |
+
"loss": 0.9608,
|
| 182 |
+
"step": 130
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.5,
|
| 186 |
+
"eval_loss": 0.9717100262641907,
|
| 187 |
+
"eval_runtime": 18.8516,
|
| 188 |
+
"eval_samples_per_second": 107.577,
|
| 189 |
+
"eval_steps_per_second": 3.395,
|
| 190 |
+
"step": 130
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.77,
|
| 194 |
+
"learning_rate": 0.0003360655737704918,
|
| 195 |
+
"loss": 0.9431,
|
| 196 |
+
"step": 140
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.77,
|
| 200 |
+
"eval_loss": 0.9643934965133667,
|
| 201 |
+
"eval_runtime": 18.8147,
|
| 202 |
+
"eval_samples_per_second": 107.788,
|
| 203 |
+
"eval_steps_per_second": 3.402,
|
| 204 |
+
"step": 140
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.05,
|
| 208 |
+
"learning_rate": 0.00029508196721311476,
|
| 209 |
+
"loss": 0.991,
|
| 210 |
+
"step": 150
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 4.05,
|
| 214 |
+
"eval_loss": 0.9581753015518188,
|
| 215 |
+
"eval_runtime": 18.8481,
|
| 216 |
+
"eval_samples_per_second": 107.597,
|
| 217 |
+
"eval_steps_per_second": 3.396,
|
| 218 |
+
"step": 150
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 4.32,
|
| 222 |
+
"learning_rate": 0.0002540983606557377,
|
| 223 |
+
"loss": 0.9387,
|
| 224 |
+
"step": 160
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 4.32,
|
| 228 |
+
"eval_loss": 0.9531411528587341,
|
| 229 |
+
"eval_runtime": 18.8022,
|
| 230 |
+
"eval_samples_per_second": 107.86,
|
| 231 |
+
"eval_steps_per_second": 3.404,
|
| 232 |
+
"step": 160
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 4.58,
|
| 236 |
+
"learning_rate": 0.00021311475409836064,
|
| 237 |
+
"loss": 0.9203,
|
| 238 |
+
"step": 170
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 4.58,
|
| 242 |
+
"eval_loss": 0.9489945769309998,
|
| 243 |
+
"eval_runtime": 18.7924,
|
| 244 |
+
"eval_samples_per_second": 107.916,
|
| 245 |
+
"eval_steps_per_second": 3.406,
|
| 246 |
+
"step": 170
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 4.85,
|
| 250 |
+
"learning_rate": 0.00017213114754098362,
|
| 251 |
+
"loss": 0.9235,
|
| 252 |
+
"step": 180
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 4.85,
|
| 256 |
+
"eval_loss": 0.9456363320350647,
|
| 257 |
+
"eval_runtime": 18.8084,
|
| 258 |
+
"eval_samples_per_second": 107.824,
|
| 259 |
+
"eval_steps_per_second": 3.403,
|
| 260 |
+
"step": 180
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 5.13,
|
| 264 |
+
"learning_rate": 0.00013114754098360657,
|
| 265 |
+
"loss": 0.9746,
|
| 266 |
+
"step": 190
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.13,
|
| 270 |
+
"eval_loss": 0.9429621696472168,
|
| 271 |
+
"eval_runtime": 18.8357,
|
| 272 |
+
"eval_samples_per_second": 107.668,
|
| 273 |
+
"eval_steps_per_second": 3.398,
|
| 274 |
+
"step": 190
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 5.4,
|
| 278 |
+
"learning_rate": 9.016393442622952e-05,
|
| 279 |
+
"loss": 0.9176,
|
| 280 |
+
"step": 200
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 5.4,
|
| 284 |
+
"eval_loss": 0.9410804510116577,
|
| 285 |
+
"eval_runtime": 18.8338,
|
| 286 |
+
"eval_samples_per_second": 107.679,
|
| 287 |
+
"eval_steps_per_second": 3.398,
|
| 288 |
+
"step": 200
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 5.66,
|
| 292 |
+
"learning_rate": 4.9180327868852456e-05,
|
| 293 |
+
"loss": 0.9175,
|
| 294 |
+
"step": 210
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 5.66,
|
| 298 |
+
"eval_loss": 0.9398788213729858,
|
| 299 |
+
"eval_runtime": 18.8076,
|
| 300 |
+
"eval_samples_per_second": 107.829,
|
| 301 |
+
"eval_steps_per_second": 3.403,
|
| 302 |
+
"step": 210
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 5.93,
|
| 306 |
+
"learning_rate": 8.19672131147541e-06,
|
| 307 |
+
"loss": 0.91,
|
| 308 |
+
"step": 220
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 5.93,
|
| 312 |
+
"eval_loss": 0.9393565058708191,
|
| 313 |
+
"eval_runtime": 18.7996,
|
| 314 |
+
"eval_samples_per_second": 107.874,
|
| 315 |
+
"eval_steps_per_second": 3.404,
|
| 316 |
+
"step": 220
|
| 317 |
+
}
|
| 318 |
+
],
|
| 319 |
+
"max_steps": 222,
|
| 320 |
+
"num_train_epochs": 6,
|
| 321 |
+
"total_flos": 8.954608582656e+16,
|
| 322 |
+
"trial_name": null,
|
| 323 |
+
"trial_params": null
|
| 324 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d63085201a984ac892343b3cb198a554ce4ee1f6c37c3b3eaafc435322c042e
|
| 3 |
+
size 3247
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|