train with TPUv2
Browse files- added_tokens.json +1 -0
- all_results.json +14 -0
- config.json +39 -0
- eval_results.json +9 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +349 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"<|endoftext|>": 50257}
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"eval_loss": 2.2617902755737305,
|
| 4 |
+
"eval_runtime": 115.5265,
|
| 5 |
+
"eval_samples": 5290,
|
| 6 |
+
"eval_samples_per_second": 45.79,
|
| 7 |
+
"eval_steps_per_second": 5.73,
|
| 8 |
+
"perplexity": 9.60026090370471,
|
| 9 |
+
"train_loss": 2.6988527534168076,
|
| 10 |
+
"train_runtime": 23608.904,
|
| 11 |
+
"train_samples": 99940,
|
| 12 |
+
"train_samples_per_second": 148.16,
|
| 13 |
+
"train_steps_per_second": 1.158
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./gpt2/output",
|
| 3 |
+
"activation_function": "gelu_new",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"embd_pdrop": 0.1,
|
| 10 |
+
"eos_token_id": 50256,
|
| 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 |
+
"reorder_and_upcast_attn": false,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 23 |
+
"scale_attn_weights": true,
|
| 24 |
+
"summary_activation": null,
|
| 25 |
+
"summary_first_dropout": 0.1,
|
| 26 |
+
"summary_proj_to_labels": true,
|
| 27 |
+
"summary_type": "cls_index",
|
| 28 |
+
"summary_use_proj": true,
|
| 29 |
+
"task_specific_params": {
|
| 30 |
+
"text-generation": {
|
| 31 |
+
"do_sample": true,
|
| 32 |
+
"max_length": 50
|
| 33 |
+
}
|
| 34 |
+
},
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.13.0.dev0",
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50258
|
| 39 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"eval_loss": 2.2617902755737305,
|
| 4 |
+
"eval_runtime": 115.5265,
|
| 5 |
+
"eval_samples": 5290,
|
| 6 |
+
"eval_samples_per_second": 45.79,
|
| 7 |
+
"eval_steps_per_second": 5.73,
|
| 8 |
+
"perplexity": 9.60026090370471
|
| 9 |
+
}
|
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:a4034228eb3a7f76d5e7c3c1f43ca1c0c0d992d27130cf91196325779be70ac8
|
| 3 |
+
size 664794436
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tf_model.h5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8a4a16f81c7a4d236ac109c3e244de8f3dae5cd1329e546533e25f7351aacfd
|
| 3 |
+
size 497938536
|
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": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "special_tokens_map_file": null, "name_or_path": "./gpt2", "tokenizer_class": "GPT2Tokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 35.0,
|
| 3 |
+
"train_loss": 2.6988527534168076,
|
| 4 |
+
"train_runtime": 23608.904,
|
| 5 |
+
"train_samples": 99940,
|
| 6 |
+
"train_samples_per_second": 148.16,
|
| 7 |
+
"train_steps_per_second": 1.158
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,349 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 35.0,
|
| 5 |
+
"global_step": 27335,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.64,
|
| 12 |
+
"learning_rate": 4.908542162063289e-05,
|
| 13 |
+
"loss": 6.7425,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.28,
|
| 18 |
+
"learning_rate": 4.8170843241265775e-05,
|
| 19 |
+
"loss": 5.4902,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.92,
|
| 24 |
+
"learning_rate": 4.725626486189867e-05,
|
| 25 |
+
"loss": 4.9535,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.56,
|
| 30 |
+
"learning_rate": 4.6341686482531555e-05,
|
| 31 |
+
"loss": 4.5816,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.2,
|
| 36 |
+
"learning_rate": 4.5427108103164445e-05,
|
| 37 |
+
"loss": 4.3055,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.84,
|
| 42 |
+
"learning_rate": 4.451252972379733e-05,
|
| 43 |
+
"loss": 4.0758,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 4.48,
|
| 48 |
+
"learning_rate": 4.359795134443022e-05,
|
| 49 |
+
"loss": 3.8768,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 5.12,
|
| 54 |
+
"learning_rate": 4.268337296506311e-05,
|
| 55 |
+
"loss": 3.7165,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 5.76,
|
| 60 |
+
"learning_rate": 4.1768794585696e-05,
|
| 61 |
+
"loss": 3.5584,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 6.4,
|
| 66 |
+
"learning_rate": 4.085421620632888e-05,
|
| 67 |
+
"loss": 3.431,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 7.04,
|
| 72 |
+
"learning_rate": 3.993963782696177e-05,
|
| 73 |
+
"loss": 3.3197,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 7.68,
|
| 78 |
+
"learning_rate": 3.902505944759466e-05,
|
| 79 |
+
"loss": 3.2002,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 8.32,
|
| 84 |
+
"learning_rate": 3.811048106822755e-05,
|
| 85 |
+
"loss": 3.1084,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 8.96,
|
| 90 |
+
"learning_rate": 3.719590268886043e-05,
|
| 91 |
+
"loss": 3.0326,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 9.6,
|
| 96 |
+
"learning_rate": 3.628132430949332e-05,
|
| 97 |
+
"loss": 2.9372,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 10.24,
|
| 102 |
+
"learning_rate": 3.536674593012621e-05,
|
| 103 |
+
"loss": 2.8657,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 10.88,
|
| 108 |
+
"learning_rate": 3.44521675507591e-05,
|
| 109 |
+
"loss": 2.8072,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 11.52,
|
| 114 |
+
"learning_rate": 3.353758917139199e-05,
|
| 115 |
+
"loss": 2.7354,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 12.16,
|
| 120 |
+
"learning_rate": 3.2623010792024876e-05,
|
| 121 |
+
"loss": 2.6862,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 12.8,
|
| 126 |
+
"learning_rate": 3.1708432412657766e-05,
|
| 127 |
+
"loss": 2.6269,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 13.44,
|
| 132 |
+
"learning_rate": 3.0793854033290656e-05,
|
| 133 |
+
"loss": 2.5687,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 14.08,
|
| 138 |
+
"learning_rate": 2.9879275653923545e-05,
|
| 139 |
+
"loss": 2.5422,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 14.72,
|
| 144 |
+
"learning_rate": 2.896469727455643e-05,
|
| 145 |
+
"loss": 2.4796,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 15.36,
|
| 150 |
+
"learning_rate": 2.8050118895189322e-05,
|
| 151 |
+
"loss": 2.4468,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 16.01,
|
| 156 |
+
"learning_rate": 2.7135540515822205e-05,
|
| 157 |
+
"loss": 2.4179,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 16.65,
|
| 162 |
+
"learning_rate": 2.6220962136455095e-05,
|
| 163 |
+
"loss": 2.3558,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 17.29,
|
| 168 |
+
"learning_rate": 2.530638375708798e-05,
|
| 169 |
+
"loss": 2.3408,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 17.93,
|
| 174 |
+
"learning_rate": 2.439180537772087e-05,
|
| 175 |
+
"loss": 2.3129,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 18.57,
|
| 180 |
+
"learning_rate": 2.347722699835376e-05,
|
| 181 |
+
"loss": 2.2645,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 19.21,
|
| 186 |
+
"learning_rate": 2.2562648618986647e-05,
|
| 187 |
+
"loss": 2.2492,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 19.85,
|
| 192 |
+
"learning_rate": 2.1648070239619537e-05,
|
| 193 |
+
"loss": 2.2222,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 20.49,
|
| 198 |
+
"learning_rate": 2.0733491860252424e-05,
|
| 199 |
+
"loss": 2.1802,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 21.13,
|
| 204 |
+
"learning_rate": 1.9818913480885314e-05,
|
| 205 |
+
"loss": 2.173,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 21.77,
|
| 210 |
+
"learning_rate": 1.89043351015182e-05,
|
| 211 |
+
"loss": 2.1459,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 22.41,
|
| 216 |
+
"learning_rate": 1.7989756722151087e-05,
|
| 217 |
+
"loss": 2.118,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 23.05,
|
| 222 |
+
"learning_rate": 1.7075178342783976e-05,
|
| 223 |
+
"loss": 2.1077,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 23.69,
|
| 228 |
+
"learning_rate": 1.6160599963416863e-05,
|
| 229 |
+
"loss": 2.0791,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 24.33,
|
| 234 |
+
"learning_rate": 1.5246021584049754e-05,
|
| 235 |
+
"loss": 2.0544,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 24.97,
|
| 240 |
+
"learning_rate": 1.4331443204682643e-05,
|
| 241 |
+
"loss": 2.0541,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 25.61,
|
| 246 |
+
"learning_rate": 1.341686482531553e-05,
|
| 247 |
+
"loss": 2.0238,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 26.25,
|
| 252 |
+
"learning_rate": 1.2502286445948419e-05,
|
| 253 |
+
"loss": 2.0115,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 26.89,
|
| 258 |
+
"learning_rate": 1.1587708066581307e-05,
|
| 259 |
+
"loss": 1.9977,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 27.53,
|
| 264 |
+
"learning_rate": 1.0673129687214195e-05,
|
| 265 |
+
"loss": 1.979,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 28.17,
|
| 270 |
+
"learning_rate": 9.758551307847083e-06,
|
| 271 |
+
"loss": 1.9705,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 28.81,
|
| 276 |
+
"learning_rate": 8.843972928479972e-06,
|
| 277 |
+
"loss": 1.9635,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 29.45,
|
| 282 |
+
"learning_rate": 7.92939454911286e-06,
|
| 283 |
+
"loss": 1.9388,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 30.09,
|
| 288 |
+
"learning_rate": 7.014816169745747e-06,
|
| 289 |
+
"loss": 1.9347,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 30.73,
|
| 294 |
+
"learning_rate": 6.100237790378636e-06,
|
| 295 |
+
"loss": 1.9227,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 31.37,
|
| 300 |
+
"learning_rate": 5.1856594110115235e-06,
|
| 301 |
+
"loss": 1.9157,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 32.01,
|
| 306 |
+
"learning_rate": 4.271081031644412e-06,
|
| 307 |
+
"loss": 1.9104,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 32.65,
|
| 312 |
+
"learning_rate": 3.3565026522773006e-06,
|
| 313 |
+
"loss": 1.895,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 33.29,
|
| 318 |
+
"learning_rate": 2.4419242729101884e-06,
|
| 319 |
+
"loss": 1.8957,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 33.93,
|
| 324 |
+
"learning_rate": 1.5273458935430768e-06,
|
| 325 |
+
"loss": 1.8829,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 34.57,
|
| 330 |
+
"learning_rate": 6.127675141759649e-07,
|
| 331 |
+
"loss": 1.8824,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 35.0,
|
| 336 |
+
"step": 27335,
|
| 337 |
+
"total_flos": 5.713934155776e+16,
|
| 338 |
+
"train_loss": 2.6988527534168076,
|
| 339 |
+
"train_runtime": 23608.904,
|
| 340 |
+
"train_samples_per_second": 148.16,
|
| 341 |
+
"train_steps_per_second": 1.158
|
| 342 |
+
}
|
| 343 |
+
],
|
| 344 |
+
"max_steps": 27335,
|
| 345 |
+
"num_train_epochs": 35,
|
| 346 |
+
"total_flos": 5.713934155776e+16,
|
| 347 |
+
"trial_name": null,
|
| 348 |
+
"trial_params": null
|
| 349 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:479fcaaa17cbced1ba01f7b545b882d75d139a89da1fbb57266758f9216ddec5
|
| 3 |
+
size 2799
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|