Upload 8 files
Browse files- config.json +26 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +501 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"RobertaForMaskedLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"eos_token_id": 2,
|
| 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": 1024,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 6,
|
| 19 |
+
"pad_token_id": 1,
|
| 20 |
+
"position_embedding_type": "absolute",
|
| 21 |
+
"torch_dtype": "float32",
|
| 22 |
+
"transformers_version": "4.37.0.dev0",
|
| 23 |
+
"type_vocab_size": 1,
|
| 24 |
+
"use_cache": true,
|
| 25 |
+
"vocab_size": 300000
|
| 26 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b620d5bada9ade93191e0d8b062fb2944ba054a8710c0976e228df384bcdb1f7
|
| 3 |
+
size 1098445096
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6e138e3331aae3e4a6ce55cddc28eccddd5bdfe34b1df9e844f32c924cd362f1
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82b83a39107cb08039bdcc3ab2d7018d894fa059e668a24e35da82d17c02cc09
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,501 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.918839153959666,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 40000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 4.9385145105755044e-05,
|
| 14 |
+
"loss": 8.6111,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.12,
|
| 19 |
+
"learning_rate": 4.8770290211510086e-05,
|
| 20 |
+
"loss": 8.9414,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.18,
|
| 25 |
+
"learning_rate": 4.815543531726513e-05,
|
| 26 |
+
"loss": 9.0231,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.25,
|
| 31 |
+
"learning_rate": 4.754058042302017e-05,
|
| 32 |
+
"loss": 8.756,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.31,
|
| 37 |
+
"learning_rate": 4.692572552877521e-05,
|
| 38 |
+
"loss": 8.6571,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.37,
|
| 43 |
+
"learning_rate": 4.631087063453025e-05,
|
| 44 |
+
"loss": 8.5083,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.43,
|
| 49 |
+
"learning_rate": 4.56960157402853e-05,
|
| 50 |
+
"loss": 8.4503,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.49,
|
| 55 |
+
"learning_rate": 4.5081160846040335e-05,
|
| 56 |
+
"loss": 8.3489,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.55,
|
| 61 |
+
"learning_rate": 4.4466305951795377e-05,
|
| 62 |
+
"loss": 8.2406,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.61,
|
| 67 |
+
"learning_rate": 4.385145105755042e-05,
|
| 68 |
+
"loss": 8.2487,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.68,
|
| 73 |
+
"learning_rate": 4.323659616330546e-05,
|
| 74 |
+
"loss": 8.1667,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.74,
|
| 79 |
+
"learning_rate": 4.262174126906051e-05,
|
| 80 |
+
"loss": 8.0874,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.8,
|
| 85 |
+
"learning_rate": 4.200688637481554e-05,
|
| 86 |
+
"loss": 8.0537,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.86,
|
| 91 |
+
"learning_rate": 4.1392031480570584e-05,
|
| 92 |
+
"loss": 8.0119,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.92,
|
| 97 |
+
"learning_rate": 4.0777176586325626e-05,
|
| 98 |
+
"loss": 7.94,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.98,
|
| 103 |
+
"learning_rate": 4.0162321692080674e-05,
|
| 104 |
+
"loss": 7.9435,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.05,
|
| 109 |
+
"learning_rate": 3.9547466797835716e-05,
|
| 110 |
+
"loss": 7.8516,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.11,
|
| 115 |
+
"learning_rate": 3.893261190359076e-05,
|
| 116 |
+
"loss": 7.7969,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.17,
|
| 121 |
+
"learning_rate": 3.831775700934579e-05,
|
| 122 |
+
"loss": 7.7974,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.23,
|
| 127 |
+
"learning_rate": 3.7702902115100834e-05,
|
| 128 |
+
"loss": 7.7728,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.29,
|
| 133 |
+
"learning_rate": 3.708804722085588e-05,
|
| 134 |
+
"loss": 7.6974,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.35,
|
| 139 |
+
"learning_rate": 3.6473192326610924e-05,
|
| 140 |
+
"loss": 7.6804,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.41,
|
| 145 |
+
"learning_rate": 3.5858337432365965e-05,
|
| 146 |
+
"loss": 7.676,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.48,
|
| 151 |
+
"learning_rate": 3.5243482538121e-05,
|
| 152 |
+
"loss": 7.6323,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.54,
|
| 157 |
+
"learning_rate": 3.462862764387605e-05,
|
| 158 |
+
"loss": 7.6116,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 1.6,
|
| 163 |
+
"learning_rate": 3.401377274963109e-05,
|
| 164 |
+
"loss": 7.574,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.66,
|
| 169 |
+
"learning_rate": 3.339891785538613e-05,
|
| 170 |
+
"loss": 7.5571,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.72,
|
| 175 |
+
"learning_rate": 3.278406296114117e-05,
|
| 176 |
+
"loss": 7.5299,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.78,
|
| 181 |
+
"learning_rate": 3.2169208066896215e-05,
|
| 182 |
+
"loss": 7.4822,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.84,
|
| 187 |
+
"learning_rate": 3.1554353172651256e-05,
|
| 188 |
+
"loss": 7.4693,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.91,
|
| 193 |
+
"learning_rate": 3.09394982784063e-05,
|
| 194 |
+
"loss": 7.4753,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.97,
|
| 199 |
+
"learning_rate": 3.032464338416134e-05,
|
| 200 |
+
"loss": 7.4058,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.03,
|
| 205 |
+
"learning_rate": 2.9709788489916378e-05,
|
| 206 |
+
"loss": 7.4351,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.09,
|
| 211 |
+
"learning_rate": 2.9094933595671426e-05,
|
| 212 |
+
"loss": 7.3385,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.15,
|
| 217 |
+
"learning_rate": 2.8480078701426464e-05,
|
| 218 |
+
"loss": 7.3167,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.21,
|
| 223 |
+
"learning_rate": 2.7865223807181506e-05,
|
| 224 |
+
"loss": 7.3194,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.27,
|
| 229 |
+
"learning_rate": 2.7250368912936547e-05,
|
| 230 |
+
"loss": 7.3105,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 2.34,
|
| 235 |
+
"learning_rate": 2.663551401869159e-05,
|
| 236 |
+
"loss": 7.2525,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.4,
|
| 241 |
+
"learning_rate": 2.6020659124446634e-05,
|
| 242 |
+
"loss": 7.2848,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.46,
|
| 247 |
+
"learning_rate": 2.5405804230201675e-05,
|
| 248 |
+
"loss": 7.2648,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.52,
|
| 253 |
+
"learning_rate": 2.4790949335956714e-05,
|
| 254 |
+
"loss": 7.2688,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.58,
|
| 259 |
+
"learning_rate": 2.417609444171176e-05,
|
| 260 |
+
"loss": 7.2292,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.64,
|
| 265 |
+
"learning_rate": 2.35612395474668e-05,
|
| 266 |
+
"loss": 7.229,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.71,
|
| 271 |
+
"learning_rate": 2.294638465322184e-05,
|
| 272 |
+
"loss": 7.2068,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.77,
|
| 277 |
+
"learning_rate": 2.2331529758976883e-05,
|
| 278 |
+
"loss": 7.1212,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.83,
|
| 283 |
+
"learning_rate": 2.171667486473192e-05,
|
| 284 |
+
"loss": 7.1578,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.89,
|
| 289 |
+
"learning_rate": 2.1101819970486966e-05,
|
| 290 |
+
"loss": 7.0875,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.95,
|
| 295 |
+
"learning_rate": 2.0486965076242008e-05,
|
| 296 |
+
"loss": 7.1206,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3.01,
|
| 301 |
+
"learning_rate": 1.987211018199705e-05,
|
| 302 |
+
"loss": 7.1629,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3.07,
|
| 307 |
+
"learning_rate": 1.925725528775209e-05,
|
| 308 |
+
"loss": 7.0788,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 3.14,
|
| 313 |
+
"learning_rate": 1.8642400393507133e-05,
|
| 314 |
+
"loss": 7.0787,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 3.2,
|
| 319 |
+
"learning_rate": 1.8027545499262174e-05,
|
| 320 |
+
"loss": 7.0581,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.26,
|
| 325 |
+
"learning_rate": 1.741269060501722e-05,
|
| 326 |
+
"loss": 6.9689,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.32,
|
| 331 |
+
"learning_rate": 1.6797835710772257e-05,
|
| 332 |
+
"loss": 7.0185,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.38,
|
| 337 |
+
"learning_rate": 1.6182980816527302e-05,
|
| 338 |
+
"loss": 6.9885,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 3.44,
|
| 343 |
+
"learning_rate": 1.5568125922282344e-05,
|
| 344 |
+
"loss": 6.9848,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.5,
|
| 349 |
+
"learning_rate": 1.4953271028037382e-05,
|
| 350 |
+
"loss": 6.9358,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.57,
|
| 355 |
+
"learning_rate": 1.4338416133792425e-05,
|
| 356 |
+
"loss": 6.9342,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 3.63,
|
| 361 |
+
"learning_rate": 1.3723561239547467e-05,
|
| 362 |
+
"loss": 6.94,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.69,
|
| 367 |
+
"learning_rate": 1.310870634530251e-05,
|
| 368 |
+
"loss": 6.9609,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 3.75,
|
| 373 |
+
"learning_rate": 1.249385145105755e-05,
|
| 374 |
+
"loss": 6.9132,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 3.81,
|
| 379 |
+
"learning_rate": 1.1878996556812592e-05,
|
| 380 |
+
"loss": 6.8702,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 3.87,
|
| 385 |
+
"learning_rate": 1.1264141662567635e-05,
|
| 386 |
+
"loss": 6.9124,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.94,
|
| 391 |
+
"learning_rate": 1.0649286768322676e-05,
|
| 392 |
+
"loss": 6.8865,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 4.0,
|
| 397 |
+
"learning_rate": 1.0034431874077718e-05,
|
| 398 |
+
"loss": 6.8776,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 4.06,
|
| 403 |
+
"learning_rate": 9.41957697983276e-06,
|
| 404 |
+
"loss": 6.8486,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 4.12,
|
| 409 |
+
"learning_rate": 8.804722085587803e-06,
|
| 410 |
+
"loss": 6.8326,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 4.18,
|
| 415 |
+
"learning_rate": 8.189867191342844e-06,
|
| 416 |
+
"loss": 6.8254,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 4.24,
|
| 421 |
+
"learning_rate": 7.575012297097884e-06,
|
| 422 |
+
"loss": 6.82,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 4.3,
|
| 427 |
+
"learning_rate": 6.960157402852927e-06,
|
| 428 |
+
"loss": 6.782,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 4.37,
|
| 433 |
+
"learning_rate": 6.345302508607968e-06,
|
| 434 |
+
"loss": 6.7768,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 4.43,
|
| 439 |
+
"learning_rate": 5.730447614363011e-06,
|
| 440 |
+
"loss": 6.841,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.49,
|
| 445 |
+
"learning_rate": 5.115592720118052e-06,
|
| 446 |
+
"loss": 6.8454,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 4.55,
|
| 451 |
+
"learning_rate": 4.500737825873094e-06,
|
| 452 |
+
"loss": 6.8015,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 4.61,
|
| 457 |
+
"learning_rate": 3.885882931628136e-06,
|
| 458 |
+
"loss": 6.8061,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 4.67,
|
| 463 |
+
"learning_rate": 3.2710280373831774e-06,
|
| 464 |
+
"loss": 6.8078,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 4.73,
|
| 469 |
+
"learning_rate": 2.65617314313822e-06,
|
| 470 |
+
"loss": 6.7983,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 4.8,
|
| 475 |
+
"learning_rate": 2.0413182488932614e-06,
|
| 476 |
+
"loss": 6.792,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 4.86,
|
| 481 |
+
"learning_rate": 1.426463354648303e-06,
|
| 482 |
+
"loss": 6.751,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 4.92,
|
| 487 |
+
"learning_rate": 8.116084604033448e-07,
|
| 488 |
+
"loss": 6.7829,
|
| 489 |
+
"step": 40000
|
| 490 |
+
}
|
| 491 |
+
],
|
| 492 |
+
"logging_steps": 500,
|
| 493 |
+
"max_steps": 40660,
|
| 494 |
+
"num_input_tokens_seen": 0,
|
| 495 |
+
"num_train_epochs": 5,
|
| 496 |
+
"save_steps": 10000,
|
| 497 |
+
"total_flos": 1.0574867779746048e+16,
|
| 498 |
+
"train_batch_size": 64,
|
| 499 |
+
"trial_name": null,
|
| 500 |
+
"trial_params": null
|
| 501 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cad7686fbd600da53499a7bf369501cded5f32b5b6772e741ef823e4e16f51f8
|
| 3 |
+
size 4664
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|