Upload 12 files
Browse files- model.safetensors +1 -1
- optimizer.pt +1 -1
- rng_state.pth +1 -1
- scheduler.pt +1 -1
- trainer_state.json +279 -51
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 903834408
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e660274f329f10f14793a1b4455c64873e0b7ef644fa06173d9444de2d943e17
|
| 3 |
size 903834408
|
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1807824186
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:142d87c4909ea8962442c297d0977d8f5e5199d02f401ee1bfa959f7df68df99
|
| 3 |
size 1807824186
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e49afdb19bcdeee33ec1305e5c298cf6932adcae5742879c34495ed0577c979e
|
| 3 |
size 14244
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:835079408709a06b26ee2442588615220d6aabc85594e0cb0cae602a8ab2db5c
|
| 3 |
size 1064
|
trainer_state.json
CHANGED
|
@@ -1,81 +1,309 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"eval_bleu":
|
| 14 |
-
"eval_gen_len": 17.
|
| 15 |
-
"eval_loss": 0.
|
| 16 |
-
"eval_meteor": 0.
|
| 17 |
-
"eval_runtime":
|
| 18 |
-
"eval_samples_per_second": 26.
|
| 19 |
-
"eval_steps_per_second": 0.
|
| 20 |
-
"step":
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 2.0,
|
| 24 |
-
"eval_bleu":
|
| 25 |
-
"eval_gen_len": 17.
|
| 26 |
-
"eval_loss": 0.
|
| 27 |
-
"eval_meteor": 0.
|
| 28 |
-
"eval_runtime":
|
| 29 |
-
"eval_samples_per_second":
|
| 30 |
-
"eval_steps_per_second": 1.
|
| 31 |
-
"step":
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 3.0,
|
| 35 |
-
"eval_bleu":
|
| 36 |
-
"eval_gen_len": 17.
|
| 37 |
-
"eval_loss": 0.
|
| 38 |
-
"eval_meteor": 0.
|
| 39 |
-
"eval_runtime":
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second": 1.
|
| 42 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 4.0,
|
| 46 |
-
"eval_bleu":
|
| 47 |
-
"eval_gen_len": 17.
|
| 48 |
-
"eval_loss": 0.
|
| 49 |
-
"eval_meteor": 0.
|
| 50 |
-
"eval_runtime":
|
| 51 |
-
"eval_samples_per_second":
|
| 52 |
-
"eval_steps_per_second": 1.
|
| 53 |
-
"step":
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 5.0,
|
| 57 |
-
"eval_bleu":
|
| 58 |
-
"eval_gen_len": 17.
|
| 59 |
-
"eval_loss": 0.
|
| 60 |
-
"eval_meteor": 0.
|
| 61 |
-
"eval_runtime":
|
| 62 |
-
"eval_samples_per_second":
|
| 63 |
-
"eval_steps_per_second": 1.
|
| 64 |
-
"step":
|
| 65 |
-
},
|
| 66 |
-
{
|
| 67 |
-
"epoch":
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
}
|
| 72 |
],
|
| 73 |
"logging_steps": 500,
|
| 74 |
-
"max_steps":
|
| 75 |
"num_input_tokens_seen": 0,
|
| 76 |
-
"num_train_epochs":
|
| 77 |
"save_steps": 500,
|
| 78 |
-
"total_flos":
|
| 79 |
"train_batch_size": 32,
|
| 80 |
"trial_name": null,
|
| 81 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 23.25581395348837,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"eval_bleu": 59.1033,
|
| 14 |
+
"eval_gen_len": 17.5513,
|
| 15 |
+
"eval_loss": 0.1559952348470688,
|
| 16 |
+
"eval_meteor": 0.7539,
|
| 17 |
+
"eval_runtime": 19.7643,
|
| 18 |
+
"eval_samples_per_second": 26.614,
|
| 19 |
+
"eval_steps_per_second": 0.86,
|
| 20 |
+
"step": 129
|
| 21 |
},
|
| 22 |
{
|
| 23 |
"epoch": 2.0,
|
| 24 |
+
"eval_bleu": 65.6424,
|
| 25 |
+
"eval_gen_len": 17.6027,
|
| 26 |
+
"eval_loss": 0.0991397500038147,
|
| 27 |
+
"eval_meteor": 0.8044,
|
| 28 |
+
"eval_runtime": 14.846,
|
| 29 |
+
"eval_samples_per_second": 35.43,
|
| 30 |
+
"eval_steps_per_second": 1.145,
|
| 31 |
+
"step": 258
|
| 32 |
},
|
| 33 |
{
|
| 34 |
"epoch": 3.0,
|
| 35 |
+
"eval_bleu": 70.6577,
|
| 36 |
+
"eval_gen_len": 17.5779,
|
| 37 |
+
"eval_loss": 0.06296151131391525,
|
| 38 |
+
"eval_meteor": 0.8488,
|
| 39 |
+
"eval_runtime": 14.7963,
|
| 40 |
+
"eval_samples_per_second": 35.549,
|
| 41 |
+
"eval_steps_per_second": 1.149,
|
| 42 |
+
"step": 387
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 3.88,
|
| 46 |
+
"learning_rate": 1.689922480620155e-05,
|
| 47 |
+
"loss": 0.3038,
|
| 48 |
+
"step": 500
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
+
"eval_bleu": 71.6744,
|
| 53 |
+
"eval_gen_len": 17.5989,
|
| 54 |
+
"eval_loss": 0.04667546600103378,
|
| 55 |
+
"eval_meteor": 0.8522,
|
| 56 |
+
"eval_runtime": 14.7696,
|
| 57 |
+
"eval_samples_per_second": 35.614,
|
| 58 |
+
"eval_steps_per_second": 1.151,
|
| 59 |
+
"step": 516
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 5.0,
|
| 63 |
+
"eval_bleu": 72.4991,
|
| 64 |
+
"eval_gen_len": 17.6749,
|
| 65 |
+
"eval_loss": 0.038296110928058624,
|
| 66 |
+
"eval_meteor": 0.8509,
|
| 67 |
+
"eval_runtime": 14.8269,
|
| 68 |
+
"eval_samples_per_second": 35.476,
|
| 69 |
+
"eval_steps_per_second": 1.147,
|
| 70 |
+
"step": 645
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 6.0,
|
| 74 |
+
"eval_bleu": 72.5858,
|
| 75 |
+
"eval_gen_len": 17.6464,
|
| 76 |
+
"eval_loss": 0.03319519758224487,
|
| 77 |
+
"eval_meteor": 0.8548,
|
| 78 |
+
"eval_runtime": 14.6593,
|
| 79 |
+
"eval_samples_per_second": 35.882,
|
| 80 |
+
"eval_steps_per_second": 1.16,
|
| 81 |
+
"step": 774
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 7.0,
|
| 85 |
+
"eval_bleu": 74.3526,
|
| 86 |
+
"eval_gen_len": 17.6217,
|
| 87 |
+
"eval_loss": 0.023467697203159332,
|
| 88 |
+
"eval_meteor": 0.8734,
|
| 89 |
+
"eval_runtime": 14.705,
|
| 90 |
+
"eval_samples_per_second": 35.77,
|
| 91 |
+
"eval_steps_per_second": 1.156,
|
| 92 |
+
"step": 903
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 7.75,
|
| 96 |
+
"learning_rate": 1.3798449612403102e-05,
|
| 97 |
+
"loss": 0.0643,
|
| 98 |
+
"step": 1000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 8.0,
|
| 102 |
+
"eval_bleu": 74.9962,
|
| 103 |
+
"eval_gen_len": 17.6141,
|
| 104 |
+
"eval_loss": 0.01849055290222168,
|
| 105 |
+
"eval_meteor": 0.8793,
|
| 106 |
+
"eval_runtime": 15.0305,
|
| 107 |
+
"eval_samples_per_second": 34.995,
|
| 108 |
+
"eval_steps_per_second": 1.131,
|
| 109 |
+
"step": 1032
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 9.0,
|
| 113 |
+
"eval_bleu": 75.5462,
|
| 114 |
+
"eval_gen_len": 17.6027,
|
| 115 |
+
"eval_loss": 0.014913694001734257,
|
| 116 |
+
"eval_meteor": 0.8862,
|
| 117 |
+
"eval_runtime": 14.5903,
|
| 118 |
+
"eval_samples_per_second": 36.051,
|
| 119 |
+
"eval_steps_per_second": 1.165,
|
| 120 |
+
"step": 1161
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 10.0,
|
| 124 |
+
"eval_bleu": 76.3236,
|
| 125 |
+
"eval_gen_len": 17.5798,
|
| 126 |
+
"eval_loss": 0.014180008322000504,
|
| 127 |
+
"eval_meteor": 0.8954,
|
| 128 |
+
"eval_runtime": 14.6398,
|
| 129 |
+
"eval_samples_per_second": 35.929,
|
| 130 |
+
"eval_steps_per_second": 1.161,
|
| 131 |
+
"step": 1290
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 11.0,
|
| 135 |
+
"eval_bleu": 75.8326,
|
| 136 |
+
"eval_gen_len": 17.5951,
|
| 137 |
+
"eval_loss": 0.010033702477812767,
|
| 138 |
+
"eval_meteor": 0.8888,
|
| 139 |
+
"eval_runtime": 14.6128,
|
| 140 |
+
"eval_samples_per_second": 35.996,
|
| 141 |
+
"eval_steps_per_second": 1.163,
|
| 142 |
+
"step": 1419
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 11.63,
|
| 146 |
+
"learning_rate": 1.0697674418604651e-05,
|
| 147 |
+
"loss": 0.0341,
|
| 148 |
+
"step": 1500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 12.0,
|
| 152 |
+
"eval_bleu": 75.9138,
|
| 153 |
+
"eval_gen_len": 17.5951,
|
| 154 |
+
"eval_loss": 0.009980925358831882,
|
| 155 |
+
"eval_meteor": 0.8891,
|
| 156 |
+
"eval_runtime": 14.7328,
|
| 157 |
+
"eval_samples_per_second": 35.703,
|
| 158 |
+
"eval_steps_per_second": 1.154,
|
| 159 |
+
"step": 1548
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 13.0,
|
| 163 |
+
"eval_bleu": 76.0534,
|
| 164 |
+
"eval_gen_len": 17.5913,
|
| 165 |
+
"eval_loss": 0.0070331464521586895,
|
| 166 |
+
"eval_meteor": 0.8901,
|
| 167 |
+
"eval_runtime": 14.643,
|
| 168 |
+
"eval_samples_per_second": 35.922,
|
| 169 |
+
"eval_steps_per_second": 1.161,
|
| 170 |
+
"step": 1677
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 14.0,
|
| 174 |
+
"eval_bleu": 76.3943,
|
| 175 |
+
"eval_gen_len": 17.5798,
|
| 176 |
+
"eval_loss": 0.006607058458030224,
|
| 177 |
+
"eval_meteor": 0.8952,
|
| 178 |
+
"eval_runtime": 14.5594,
|
| 179 |
+
"eval_samples_per_second": 36.128,
|
| 180 |
+
"eval_steps_per_second": 1.168,
|
| 181 |
+
"step": 1806
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 15.0,
|
| 185 |
+
"eval_bleu": 76.9833,
|
| 186 |
+
"eval_gen_len": 17.5608,
|
| 187 |
+
"eval_loss": 0.003804780077189207,
|
| 188 |
+
"eval_meteor": 0.9027,
|
| 189 |
+
"eval_runtime": 14.9867,
|
| 190 |
+
"eval_samples_per_second": 35.098,
|
| 191 |
+
"eval_steps_per_second": 1.134,
|
| 192 |
+
"step": 1935
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 15.5,
|
| 196 |
+
"learning_rate": 7.596899224806202e-06,
|
| 197 |
+
"loss": 0.0191,
|
| 198 |
+
"step": 2000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 16.0,
|
| 202 |
+
"eval_bleu": 76.9399,
|
| 203 |
+
"eval_gen_len": 17.5608,
|
| 204 |
+
"eval_loss": 0.0028171560261398554,
|
| 205 |
+
"eval_meteor": 0.9025,
|
| 206 |
+
"eval_runtime": 14.5931,
|
| 207 |
+
"eval_samples_per_second": 36.044,
|
| 208 |
+
"eval_steps_per_second": 1.165,
|
| 209 |
+
"step": 2064
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 17.0,
|
| 213 |
+
"eval_bleu": 76.5796,
|
| 214 |
+
"eval_gen_len": 17.5722,
|
| 215 |
+
"eval_loss": 0.005369492340832949,
|
| 216 |
+
"eval_meteor": 0.8979,
|
| 217 |
+
"eval_runtime": 14.6939,
|
| 218 |
+
"eval_samples_per_second": 35.797,
|
| 219 |
+
"eval_steps_per_second": 1.157,
|
| 220 |
+
"step": 2193
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 18.0,
|
| 224 |
+
"eval_bleu": 77.0507,
|
| 225 |
+
"eval_gen_len": 17.557,
|
| 226 |
+
"eval_loss": 0.002158859744668007,
|
| 227 |
+
"eval_meteor": 0.904,
|
| 228 |
+
"eval_runtime": 14.6859,
|
| 229 |
+
"eval_samples_per_second": 35.817,
|
| 230 |
+
"eval_steps_per_second": 1.158,
|
| 231 |
+
"step": 2322
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 19.0,
|
| 235 |
+
"eval_bleu": 76.3097,
|
| 236 |
+
"eval_gen_len": 17.5837,
|
| 237 |
+
"eval_loss": 0.0028479481115937233,
|
| 238 |
+
"eval_meteor": 0.8933,
|
| 239 |
+
"eval_runtime": 14.699,
|
| 240 |
+
"eval_samples_per_second": 35.785,
|
| 241 |
+
"eval_steps_per_second": 1.157,
|
| 242 |
+
"step": 2451
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 19.38,
|
| 246 |
+
"learning_rate": 4.4961240310077525e-06,
|
| 247 |
+
"loss": 0.0121,
|
| 248 |
+
"step": 2500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 20.0,
|
| 252 |
+
"eval_bleu": 77.0507,
|
| 253 |
+
"eval_gen_len": 17.557,
|
| 254 |
+
"eval_loss": 0.0012633432634174824,
|
| 255 |
+
"eval_meteor": 0.904,
|
| 256 |
+
"eval_runtime": 14.9177,
|
| 257 |
+
"eval_samples_per_second": 35.26,
|
| 258 |
+
"eval_steps_per_second": 1.14,
|
| 259 |
+
"step": 2580
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 21.0,
|
| 263 |
+
"eval_bleu": 76.5168,
|
| 264 |
+
"eval_gen_len": 17.576,
|
| 265 |
+
"eval_loss": 0.001905079698190093,
|
| 266 |
+
"eval_meteor": 0.8965,
|
| 267 |
+
"eval_runtime": 14.6207,
|
| 268 |
+
"eval_samples_per_second": 35.976,
|
| 269 |
+
"eval_steps_per_second": 1.163,
|
| 270 |
+
"step": 2709
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 22.0,
|
| 274 |
+
"eval_bleu": 77.2739,
|
| 275 |
+
"eval_gen_len": 17.5494,
|
| 276 |
+
"eval_loss": 0.0008121016435325146,
|
| 277 |
+
"eval_meteor": 0.9072,
|
| 278 |
+
"eval_runtime": 14.6135,
|
| 279 |
+
"eval_samples_per_second": 35.994,
|
| 280 |
+
"eval_steps_per_second": 1.163,
|
| 281 |
+
"step": 2838
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 23.0,
|
| 285 |
+
"eval_bleu": 77.1609,
|
| 286 |
+
"eval_gen_len": 17.5532,
|
| 287 |
+
"eval_loss": 0.0007495949394069612,
|
| 288 |
+
"eval_meteor": 0.9056,
|
| 289 |
+
"eval_runtime": 14.5508,
|
| 290 |
+
"eval_samples_per_second": 36.149,
|
| 291 |
+
"eval_steps_per_second": 1.168,
|
| 292 |
+
"step": 2967
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 23.26,
|
| 296 |
+
"learning_rate": 1.3953488372093025e-06,
|
| 297 |
+
"loss": 0.0083,
|
| 298 |
+
"step": 3000
|
| 299 |
}
|
| 300 |
],
|
| 301 |
"logging_steps": 500,
|
| 302 |
+
"max_steps": 3225,
|
| 303 |
"num_input_tokens_seen": 0,
|
| 304 |
+
"num_train_epochs": 25,
|
| 305 |
"save_steps": 500,
|
| 306 |
+
"total_flos": 1.172703512236032e+16,
|
| 307 |
"train_batch_size": 32,
|
| 308 |
"trial_name": null,
|
| 309 |
"trial_params": null
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4856
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd8cbeb50927f789bd585d35e44d98f7fd2319ad0be400b4d24eb8eb3c59ace0
|
| 3 |
size 4856
|