Upload 12 files
Browse files- config.json +27 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- trainer_state.json +412 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/jupyter/lm/models/2018-2022-large/checkpoint-24000/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 24,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.27.0.dev0",
|
| 24 |
+
"type_vocab_size": 1,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 50265
|
| 27 |
+
}
|
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:d3cefe863430971264fd36bbb0774f4c3ee54f36d8019967a29172380e3f219b
|
| 3 |
+
size 1421788537
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:58077767908588406007df5bbecf880f7820f36ecaeec81609f45956ae8306be
|
| 3 |
+
size 21665
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f61efe5243275245d99a0c0911332821cf49ffd0d9c63950019543cd7ebbcf0
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:600c5a9577a891001c640a9af60591dd7a7725239ba8e6e218b47d50a5816d13
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": "<mask>",
|
| 8 |
+
"model_max_length": 512,
|
| 9 |
+
"name_or_path": "/home/jupyter/lm/models/2018-2022-large/checkpoint-24000/",
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"special_tokens_map_file": null,
|
| 13 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,412 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9920199230667882,
|
| 5 |
+
"global_step": 24000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 9.999793741991486e-06,
|
| 13 |
+
"loss": 1.742,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 9.999587070640269e-06,
|
| 19 |
+
"loss": 1.7307,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 9.999380399289051e-06,
|
| 25 |
+
"loss": 1.7414,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.08,
|
| 30 |
+
"learning_rate": 9.999173727937835e-06,
|
| 31 |
+
"loss": 1.7396,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.08,
|
| 36 |
+
"eval_accuracy": 0.6747098550914694,
|
| 37 |
+
"eval_loss": 1.6244006156921387,
|
| 38 |
+
"eval_runtime": 13.0499,
|
| 39 |
+
"eval_samples_per_second": 306.516,
|
| 40 |
+
"eval_steps_per_second": 0.766,
|
| 41 |
+
"step": 2000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.1,
|
| 45 |
+
"learning_rate": 9.998967056586617e-06,
|
| 46 |
+
"loss": 1.738,
|
| 47 |
+
"step": 2500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.12,
|
| 51 |
+
"learning_rate": 9.9987603852354e-06,
|
| 52 |
+
"loss": 1.7357,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.14,
|
| 57 |
+
"learning_rate": 9.998553713884183e-06,
|
| 58 |
+
"loss": 1.7349,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.17,
|
| 63 |
+
"learning_rate": 9.998347042532966e-06,
|
| 64 |
+
"loss": 1.7309,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.17,
|
| 69 |
+
"eval_accuracy": 0.6821878279118573,
|
| 70 |
+
"eval_loss": 1.6006274223327637,
|
| 71 |
+
"eval_runtime": 13.0815,
|
| 72 |
+
"eval_samples_per_second": 305.775,
|
| 73 |
+
"eval_steps_per_second": 0.764,
|
| 74 |
+
"step": 4000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.19,
|
| 78 |
+
"learning_rate": 9.998140371181748e-06,
|
| 79 |
+
"loss": 1.7322,
|
| 80 |
+
"step": 4500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.21,
|
| 84 |
+
"learning_rate": 9.99793369983053e-06,
|
| 85 |
+
"loss": 1.7302,
|
| 86 |
+
"step": 5000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.23,
|
| 90 |
+
"learning_rate": 9.997727028479312e-06,
|
| 91 |
+
"loss": 1.7281,
|
| 92 |
+
"step": 5500
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.25,
|
| 96 |
+
"learning_rate": 9.997520357128095e-06,
|
| 97 |
+
"loss": 1.7273,
|
| 98 |
+
"step": 6000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.25,
|
| 102 |
+
"eval_accuracy": 0.6896347482724581,
|
| 103 |
+
"eval_loss": 1.5701262950897217,
|
| 104 |
+
"eval_runtime": 13.0657,
|
| 105 |
+
"eval_samples_per_second": 306.145,
|
| 106 |
+
"eval_steps_per_second": 0.765,
|
| 107 |
+
"step": 6000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.27,
|
| 111 |
+
"learning_rate": 9.997313685776879e-06,
|
| 112 |
+
"loss": 1.7252,
|
| 113 |
+
"step": 6500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.29,
|
| 117 |
+
"learning_rate": 9.997107427768363e-06,
|
| 118 |
+
"loss": 1.7231,
|
| 119 |
+
"step": 7000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.31,
|
| 123 |
+
"learning_rate": 9.996901169759848e-06,
|
| 124 |
+
"loss": 1.7223,
|
| 125 |
+
"step": 7500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.33,
|
| 129 |
+
"learning_rate": 9.99669449840863e-06,
|
| 130 |
+
"loss": 1.7215,
|
| 131 |
+
"step": 8000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.33,
|
| 135 |
+
"eval_accuracy": 0.6799366211130917,
|
| 136 |
+
"eval_loss": 1.6207975149154663,
|
| 137 |
+
"eval_runtime": 11.6877,
|
| 138 |
+
"eval_samples_per_second": 342.241,
|
| 139 |
+
"eval_steps_per_second": 0.856,
|
| 140 |
+
"step": 8000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.35,
|
| 144 |
+
"learning_rate": 9.996487827057414e-06,
|
| 145 |
+
"loss": 1.7182,
|
| 146 |
+
"step": 8500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.37,
|
| 150 |
+
"learning_rate": 9.996281155706197e-06,
|
| 151 |
+
"loss": 1.7189,
|
| 152 |
+
"step": 9000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.39,
|
| 156 |
+
"learning_rate": 9.996074484354979e-06,
|
| 157 |
+
"loss": 1.7169,
|
| 158 |
+
"step": 9500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.41,
|
| 162 |
+
"learning_rate": 9.995868226346464e-06,
|
| 163 |
+
"loss": 1.7173,
|
| 164 |
+
"step": 10000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.41,
|
| 168 |
+
"eval_accuracy": 0.6820005349023803,
|
| 169 |
+
"eval_loss": 1.6004101037979126,
|
| 170 |
+
"eval_runtime": 13.0596,
|
| 171 |
+
"eval_samples_per_second": 306.287,
|
| 172 |
+
"eval_steps_per_second": 0.766,
|
| 173 |
+
"step": 10000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.43,
|
| 177 |
+
"learning_rate": 9.995661554995247e-06,
|
| 178 |
+
"loss": 1.7152,
|
| 179 |
+
"step": 10500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.45,
|
| 183 |
+
"learning_rate": 9.99545488364403e-06,
|
| 184 |
+
"loss": 1.7126,
|
| 185 |
+
"step": 11000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.48,
|
| 189 |
+
"learning_rate": 9.995248212292813e-06,
|
| 190 |
+
"loss": 1.7114,
|
| 191 |
+
"step": 11500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.5,
|
| 195 |
+
"learning_rate": 9.995041954284299e-06,
|
| 196 |
+
"loss": 1.7098,
|
| 197 |
+
"step": 12000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 0.5,
|
| 201 |
+
"eval_accuracy": 0.6854211592498203,
|
| 202 |
+
"eval_loss": 1.6027569770812988,
|
| 203 |
+
"eval_runtime": 13.0635,
|
| 204 |
+
"eval_samples_per_second": 306.196,
|
| 205 |
+
"eval_steps_per_second": 0.765,
|
| 206 |
+
"step": 12000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.52,
|
| 210 |
+
"learning_rate": 9.99483528293308e-06,
|
| 211 |
+
"loss": 1.7092,
|
| 212 |
+
"step": 12500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.54,
|
| 216 |
+
"learning_rate": 9.994628611581863e-06,
|
| 217 |
+
"loss": 1.7081,
|
| 218 |
+
"step": 13000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.56,
|
| 222 |
+
"learning_rate": 9.994421940230647e-06,
|
| 223 |
+
"loss": 1.7071,
|
| 224 |
+
"step": 13500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.58,
|
| 228 |
+
"learning_rate": 9.99421526887943e-06,
|
| 229 |
+
"loss": 1.7066,
|
| 230 |
+
"step": 14000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.58,
|
| 234 |
+
"eval_accuracy": 0.6892430278884463,
|
| 235 |
+
"eval_loss": 1.568811058998108,
|
| 236 |
+
"eval_runtime": 11.6681,
|
| 237 |
+
"eval_samples_per_second": 342.815,
|
| 238 |
+
"eval_steps_per_second": 0.857,
|
| 239 |
+
"step": 14000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.6,
|
| 243 |
+
"learning_rate": 9.994008597528212e-06,
|
| 244 |
+
"loss": 1.7062,
|
| 245 |
+
"step": 14500
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.62,
|
| 249 |
+
"learning_rate": 9.993801926176994e-06,
|
| 250 |
+
"loss": 1.7041,
|
| 251 |
+
"step": 15000
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.64,
|
| 255 |
+
"learning_rate": 9.993595254825776e-06,
|
| 256 |
+
"loss": 1.7028,
|
| 257 |
+
"step": 15500
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.66,
|
| 261 |
+
"learning_rate": 9.99338858347456e-06,
|
| 262 |
+
"loss": 1.702,
|
| 263 |
+
"step": 16000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.66,
|
| 267 |
+
"eval_accuracy": 0.689404839764552,
|
| 268 |
+
"eval_loss": 1.5777287483215332,
|
| 269 |
+
"eval_runtime": 13.0408,
|
| 270 |
+
"eval_samples_per_second": 306.729,
|
| 271 |
+
"eval_steps_per_second": 0.767,
|
| 272 |
+
"step": 16000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.68,
|
| 276 |
+
"learning_rate": 9.993181912123342e-06,
|
| 277 |
+
"loss": 1.6984,
|
| 278 |
+
"step": 16500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.7,
|
| 282 |
+
"learning_rate": 9.992975240772125e-06,
|
| 283 |
+
"loss": 1.6999,
|
| 284 |
+
"step": 17000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.72,
|
| 288 |
+
"learning_rate": 9.99276898276361e-06,
|
| 289 |
+
"loss": 1.6983,
|
| 290 |
+
"step": 17500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.74,
|
| 294 |
+
"learning_rate": 9.992562724755096e-06,
|
| 295 |
+
"loss": 1.6972,
|
| 296 |
+
"step": 18000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.74,
|
| 300 |
+
"eval_accuracy": 0.6915187376725839,
|
| 301 |
+
"eval_loss": 1.5638251304626465,
|
| 302 |
+
"eval_runtime": 11.6615,
|
| 303 |
+
"eval_samples_per_second": 343.008,
|
| 304 |
+
"eval_steps_per_second": 0.858,
|
| 305 |
+
"step": 18000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 0.76,
|
| 309 |
+
"learning_rate": 9.992356053403878e-06,
|
| 310 |
+
"loss": 1.694,
|
| 311 |
+
"step": 18500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.79,
|
| 315 |
+
"learning_rate": 9.992149795395364e-06,
|
| 316 |
+
"loss": 1.6954,
|
| 317 |
+
"step": 19000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.81,
|
| 321 |
+
"learning_rate": 9.991943124044146e-06,
|
| 322 |
+
"loss": 1.6946,
|
| 323 |
+
"step": 19500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.83,
|
| 327 |
+
"learning_rate": 9.991736452692928e-06,
|
| 328 |
+
"loss": 1.6939,
|
| 329 |
+
"step": 20000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.83,
|
| 333 |
+
"eval_accuracy": 0.6928982725527831,
|
| 334 |
+
"eval_loss": 1.5452697277069092,
|
| 335 |
+
"eval_runtime": 13.0226,
|
| 336 |
+
"eval_samples_per_second": 307.159,
|
| 337 |
+
"eval_steps_per_second": 0.768,
|
| 338 |
+
"step": 20000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.85,
|
| 342 |
+
"learning_rate": 9.99152978134171e-06,
|
| 343 |
+
"loss": 1.6927,
|
| 344 |
+
"step": 20500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.87,
|
| 348 |
+
"learning_rate": 9.991323109990494e-06,
|
| 349 |
+
"loss": 1.6901,
|
| 350 |
+
"step": 21000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.89,
|
| 354 |
+
"learning_rate": 9.991116438639277e-06,
|
| 355 |
+
"loss": 1.6892,
|
| 356 |
+
"step": 21500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.91,
|
| 360 |
+
"learning_rate": 9.990909767288059e-06,
|
| 361 |
+
"loss": 1.6898,
|
| 362 |
+
"step": 22000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.91,
|
| 366 |
+
"eval_accuracy": 0.683527801316733,
|
| 367 |
+
"eval_loss": 1.5818458795547485,
|
| 368 |
+
"eval_runtime": 13.0663,
|
| 369 |
+
"eval_samples_per_second": 306.132,
|
| 370 |
+
"eval_steps_per_second": 0.765,
|
| 371 |
+
"step": 22000
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 0.93,
|
| 375 |
+
"learning_rate": 9.990703095936843e-06,
|
| 376 |
+
"loss": 1.6889,
|
| 377 |
+
"step": 22500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 0.95,
|
| 381 |
+
"learning_rate": 9.990496424585625e-06,
|
| 382 |
+
"loss": 1.6855,
|
| 383 |
+
"step": 23000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.97,
|
| 387 |
+
"learning_rate": 9.990289753234407e-06,
|
| 388 |
+
"loss": 1.6853,
|
| 389 |
+
"step": 23500
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.99,
|
| 393 |
+
"learning_rate": 9.990083908568595e-06,
|
| 394 |
+
"loss": 1.6856,
|
| 395 |
+
"step": 24000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.99,
|
| 399 |
+
"eval_accuracy": 0.6877091672681934,
|
| 400 |
+
"eval_loss": 1.5628535747528076,
|
| 401 |
+
"eval_runtime": 13.0163,
|
| 402 |
+
"eval_samples_per_second": 307.306,
|
| 403 |
+
"eval_steps_per_second": 0.768,
|
| 404 |
+
"step": 24000
|
| 405 |
+
}
|
| 406 |
+
],
|
| 407 |
+
"max_steps": 24193000,
|
| 408 |
+
"num_train_epochs": 1000,
|
| 409 |
+
"total_flos": 1.78960468082688e+19,
|
| 410 |
+
"trial_name": null,
|
| 411 |
+
"trial_params": null
|
| 412 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef24a1135e89a697be436da25d8cd72945892ca512dc446e1b722f8c1b608bd6
|
| 3 |
+
size 3515
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|