Upload 12 files
Browse files- all_results.json +14 -0
- config.json +38 -0
- eval_results.json +9 -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
- train_results.json +8 -0
- trainer_state.json +439 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"eval_loss": 2.9766225814819336,
|
| 4 |
+
"eval_runtime": 76.2504,
|
| 5 |
+
"eval_samples": 1090,
|
| 6 |
+
"eval_samples_per_second": 14.295,
|
| 7 |
+
"eval_steps_per_second": 1.797,
|
| 8 |
+
"perplexity": 19.621434810964658,
|
| 9 |
+
"train_loss": 2.9473999731030567,
|
| 10 |
+
"train_runtime": 8951.9422,
|
| 11 |
+
"train_samples": 5808,
|
| 12 |
+
"train_samples_per_second": 3.893,
|
| 13 |
+
"train_steps_per_second": 3.893
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gpt2",
|
| 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 |
+
"gradient_checkpointing": false,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 768,
|
| 17 |
+
"n_head": 12,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 12,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"resid_pdrop": 0.1,
|
| 22 |
+
"scale_attn_weights": true,
|
| 23 |
+
"summary_activation": null,
|
| 24 |
+
"summary_first_dropout": 0.1,
|
| 25 |
+
"summary_proj_to_labels": true,
|
| 26 |
+
"summary_type": "cls_index",
|
| 27 |
+
"summary_use_proj": true,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"text-generation": {
|
| 30 |
+
"do_sample": true,
|
| 31 |
+
"max_length": 50
|
| 32 |
+
}
|
| 33 |
+
},
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.10.0.dev0",
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 50257
|
| 38 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"eval_loss": 2.9766225814819336,
|
| 4 |
+
"eval_runtime": 76.2504,
|
| 5 |
+
"eval_samples": 1090,
|
| 6 |
+
"eval_samples_per_second": 14.295,
|
| 7 |
+
"eval_steps_per_second": 1.797,
|
| 8 |
+
"perplexity": 19.621434810964658
|
| 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 sha256:54f43f999e17f4f4b2a3dba99e4bcf39ee831ee27e3e047c2d01b1db6608ef3d
|
| 3 |
+
size 510407951
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
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, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 6.0,
|
| 3 |
+
"train_loss": 2.9473999731030567,
|
| 4 |
+
"train_runtime": 8951.9422,
|
| 5 |
+
"train_samples": 5808,
|
| 6 |
+
"train_samples_per_second": 3.893,
|
| 7 |
+
"train_steps_per_second": 3.893
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,439 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"global_step": 34848,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.09,
|
| 12 |
+
"learning_rate": 4.92825987144169e-05,
|
| 13 |
+
"loss": 3.4212,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.17,
|
| 18 |
+
"learning_rate": 4.85651974288338e-05,
|
| 19 |
+
"loss": 3.323,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.26,
|
| 24 |
+
"learning_rate": 4.784779614325069e-05,
|
| 25 |
+
"loss": 3.2791,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.34,
|
| 30 |
+
"learning_rate": 4.7130394857667584e-05,
|
| 31 |
+
"loss": 3.2457,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.43,
|
| 36 |
+
"learning_rate": 4.6412993572084486e-05,
|
| 37 |
+
"loss": 3.2237,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.52,
|
| 42 |
+
"learning_rate": 4.569559228650138e-05,
|
| 43 |
+
"loss": 3.1983,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.6,
|
| 48 |
+
"learning_rate": 4.4978191000918276e-05,
|
| 49 |
+
"loss": 3.195,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.69,
|
| 54 |
+
"learning_rate": 4.426078971533517e-05,
|
| 55 |
+
"loss": 3.1841,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.77,
|
| 60 |
+
"learning_rate": 4.354338842975207e-05,
|
| 61 |
+
"loss": 3.1802,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.86,
|
| 66 |
+
"learning_rate": 4.282598714416897e-05,
|
| 67 |
+
"loss": 3.1674,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.95,
|
| 72 |
+
"learning_rate": 4.210858585858586e-05,
|
| 73 |
+
"loss": 3.1341,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.03,
|
| 78 |
+
"learning_rate": 4.139118457300275e-05,
|
| 79 |
+
"loss": 3.101,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.12,
|
| 84 |
+
"learning_rate": 4.0673783287419655e-05,
|
| 85 |
+
"loss": 3.0298,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.21,
|
| 90 |
+
"learning_rate": 3.995638200183655e-05,
|
| 91 |
+
"loss": 3.0358,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.29,
|
| 96 |
+
"learning_rate": 3.9238980716253446e-05,
|
| 97 |
+
"loss": 3.0531,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.38,
|
| 102 |
+
"learning_rate": 3.852157943067034e-05,
|
| 103 |
+
"loss": 3.0409,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.46,
|
| 108 |
+
"learning_rate": 3.7804178145087236e-05,
|
| 109 |
+
"loss": 3.0291,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.55,
|
| 114 |
+
"learning_rate": 3.708677685950414e-05,
|
| 115 |
+
"loss": 3.0346,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.64,
|
| 120 |
+
"learning_rate": 3.6369375573921034e-05,
|
| 121 |
+
"loss": 3.0356,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.72,
|
| 126 |
+
"learning_rate": 3.565197428833792e-05,
|
| 127 |
+
"loss": 3.0163,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.81,
|
| 132 |
+
"learning_rate": 3.4934573002754824e-05,
|
| 133 |
+
"loss": 3.026,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.89,
|
| 138 |
+
"learning_rate": 3.421717171717172e-05,
|
| 139 |
+
"loss": 3.0223,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.98,
|
| 144 |
+
"learning_rate": 3.3499770431588615e-05,
|
| 145 |
+
"loss": 3.0286,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.07,
|
| 150 |
+
"learning_rate": 3.278236914600551e-05,
|
| 151 |
+
"loss": 2.9479,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.15,
|
| 156 |
+
"learning_rate": 3.2064967860422406e-05,
|
| 157 |
+
"loss": 2.9327,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.24,
|
| 162 |
+
"learning_rate": 3.134756657483931e-05,
|
| 163 |
+
"loss": 2.943,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.32,
|
| 168 |
+
"learning_rate": 3.06301652892562e-05,
|
| 169 |
+
"loss": 2.9277,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.41,
|
| 174 |
+
"learning_rate": 2.9912764003673095e-05,
|
| 175 |
+
"loss": 2.9443,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 2.5,
|
| 180 |
+
"learning_rate": 2.919536271808999e-05,
|
| 181 |
+
"loss": 2.9452,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 2.58,
|
| 186 |
+
"learning_rate": 2.847796143250689e-05,
|
| 187 |
+
"loss": 2.9482,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 2.67,
|
| 192 |
+
"learning_rate": 2.7760560146923788e-05,
|
| 193 |
+
"loss": 2.9429,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 2.75,
|
| 198 |
+
"learning_rate": 2.704315886134068e-05,
|
| 199 |
+
"loss": 2.9463,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.84,
|
| 204 |
+
"learning_rate": 2.6325757575757575e-05,
|
| 205 |
+
"loss": 2.9292,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.93,
|
| 210 |
+
"learning_rate": 2.5608356290174473e-05,
|
| 211 |
+
"loss": 2.9286,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.01,
|
| 216 |
+
"learning_rate": 2.489095500459137e-05,
|
| 217 |
+
"loss": 2.9312,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.1,
|
| 222 |
+
"learning_rate": 2.4173553719008264e-05,
|
| 223 |
+
"loss": 2.8712,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.19,
|
| 228 |
+
"learning_rate": 2.3456152433425163e-05,
|
| 229 |
+
"loss": 2.8583,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.27,
|
| 234 |
+
"learning_rate": 2.2738751147842058e-05,
|
| 235 |
+
"loss": 2.882,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.36,
|
| 240 |
+
"learning_rate": 2.2021349862258957e-05,
|
| 241 |
+
"loss": 2.857,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 3.44,
|
| 246 |
+
"learning_rate": 2.130394857667585e-05,
|
| 247 |
+
"loss": 2.8815,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.53,
|
| 252 |
+
"learning_rate": 2.0586547291092747e-05,
|
| 253 |
+
"loss": 2.8775,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.62,
|
| 258 |
+
"learning_rate": 1.9869146005509643e-05,
|
| 259 |
+
"loss": 2.8606,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 3.7,
|
| 264 |
+
"learning_rate": 1.915174471992654e-05,
|
| 265 |
+
"loss": 2.8845,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 3.79,
|
| 270 |
+
"learning_rate": 1.8434343434343433e-05,
|
| 271 |
+
"loss": 2.8692,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.87,
|
| 276 |
+
"learning_rate": 1.7716942148760332e-05,
|
| 277 |
+
"loss": 2.8829,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 3.96,
|
| 282 |
+
"learning_rate": 1.6999540863177227e-05,
|
| 283 |
+
"loss": 2.8782,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.05,
|
| 288 |
+
"learning_rate": 1.6282139577594123e-05,
|
| 289 |
+
"loss": 2.8401,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.13,
|
| 294 |
+
"learning_rate": 1.5564738292011018e-05,
|
| 295 |
+
"loss": 2.822,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.22,
|
| 300 |
+
"learning_rate": 1.4847337006427917e-05,
|
| 301 |
+
"loss": 2.8197,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 4.3,
|
| 306 |
+
"learning_rate": 1.4129935720844812e-05,
|
| 307 |
+
"loss": 2.8227,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 4.39,
|
| 312 |
+
"learning_rate": 1.3412534435261709e-05,
|
| 313 |
+
"loss": 2.8154,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.48,
|
| 318 |
+
"learning_rate": 1.2695133149678604e-05,
|
| 319 |
+
"loss": 2.8247,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 4.56,
|
| 324 |
+
"learning_rate": 1.1977731864095501e-05,
|
| 325 |
+
"loss": 2.8196,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 4.65,
|
| 330 |
+
"learning_rate": 1.1260330578512397e-05,
|
| 331 |
+
"loss": 2.8357,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.73,
|
| 336 |
+
"learning_rate": 1.0542929292929294e-05,
|
| 337 |
+
"loss": 2.8163,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.82,
|
| 342 |
+
"learning_rate": 9.825528007346189e-06,
|
| 343 |
+
"loss": 2.8381,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 4.91,
|
| 348 |
+
"learning_rate": 9.108126721763086e-06,
|
| 349 |
+
"loss": 2.8198,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 4.99,
|
| 354 |
+
"learning_rate": 8.390725436179981e-06,
|
| 355 |
+
"loss": 2.8302,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 5.08,
|
| 360 |
+
"learning_rate": 7.673324150596878e-06,
|
| 361 |
+
"loss": 2.7897,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 5.17,
|
| 366 |
+
"learning_rate": 6.955922865013774e-06,
|
| 367 |
+
"loss": 2.7858,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 5.25,
|
| 372 |
+
"learning_rate": 6.238521579430671e-06,
|
| 373 |
+
"loss": 2.7865,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 5.34,
|
| 378 |
+
"learning_rate": 5.521120293847567e-06,
|
| 379 |
+
"loss": 2.7889,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.42,
|
| 384 |
+
"learning_rate": 4.803719008264463e-06,
|
| 385 |
+
"loss": 2.7797,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 5.51,
|
| 390 |
+
"learning_rate": 4.086317722681359e-06,
|
| 391 |
+
"loss": 2.7869,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 5.6,
|
| 396 |
+
"learning_rate": 3.3689164370982553e-06,
|
| 397 |
+
"loss": 2.7922,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 5.68,
|
| 402 |
+
"learning_rate": 2.651515151515152e-06,
|
| 403 |
+
"loss": 2.8032,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 5.77,
|
| 408 |
+
"learning_rate": 1.934113865932048e-06,
|
| 409 |
+
"loss": 2.7963,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 5.85,
|
| 414 |
+
"learning_rate": 1.216712580348944e-06,
|
| 415 |
+
"loss": 2.7952,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 5.94,
|
| 420 |
+
"learning_rate": 4.993112947658403e-07,
|
| 421 |
+
"loss": 2.7968,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 6.0,
|
| 426 |
+
"step": 34848,
|
| 427 |
+
"total_flos": 1.8211009462272e+16,
|
| 428 |
+
"train_loss": 2.9473999731030567,
|
| 429 |
+
"train_runtime": 8951.9422,
|
| 430 |
+
"train_samples_per_second": 3.893,
|
| 431 |
+
"train_steps_per_second": 3.893
|
| 432 |
+
}
|
| 433 |
+
],
|
| 434 |
+
"max_steps": 34848,
|
| 435 |
+
"num_train_epochs": 6,
|
| 436 |
+
"total_flos": 1.8211009462272e+16,
|
| 437 |
+
"trial_name": null,
|
| 438 |
+
"trial_params": null
|
| 439 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36be4475c5bc4a5d78685a1931ee9159c6e597abc2c4de0acef633f4b381a45a
|
| 3 |
+
size 2607
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|