End of training
Browse files- all_results.json +18 -0
- generated_predictions.txt +0 -0
- generation_config.json +0 -1
- predict_results.json +12 -0
- train_results.json +8 -0
- trainer_state.json +229 -0
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"predict_gen_len": 43.5895330938943,
|
| 4 |
+
"predict_loss": 1.8740674257278442,
|
| 5 |
+
"predict_rouge1": 34.5439,
|
| 6 |
+
"predict_rouge2": 15.8854,
|
| 7 |
+
"predict_rougeL": 29.5836,
|
| 8 |
+
"predict_rougeLsum": 31.959,
|
| 9 |
+
"predict_runtime": 421.428,
|
| 10 |
+
"predict_samples": 1949,
|
| 11 |
+
"predict_samples_per_second": 4.625,
|
| 12 |
+
"predict_steps_per_second": 0.289,
|
| 13 |
+
"train_loss": 2.1397388414151406,
|
| 14 |
+
"train_runtime": 8310.1091,
|
| 15 |
+
"train_samples": 11044,
|
| 16 |
+
"train_samples_per_second": 13.29,
|
| 17 |
+
"train_steps_per_second": 0.416
|
| 18 |
+
}
|
generated_predictions.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
generation_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
"decoder_start_token_id": 0,
|
| 4 |
"eos_token_id": 1,
|
| 5 |
"pad_token_id": 0,
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"decoder_start_token_id": 0,
|
| 3 |
"eos_token_id": 1,
|
| 4 |
"pad_token_id": 0,
|
predict_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"predict_gen_len": 43.5895330938943,
|
| 3 |
+
"predict_loss": 1.8740674257278442,
|
| 4 |
+
"predict_rouge1": 34.5439,
|
| 5 |
+
"predict_rouge2": 15.8854,
|
| 6 |
+
"predict_rougeL": 29.5836,
|
| 7 |
+
"predict_rougeLsum": 31.959,
|
| 8 |
+
"predict_runtime": 421.428,
|
| 9 |
+
"predict_samples": 1949,
|
| 10 |
+
"predict_samples_per_second": 4.625,
|
| 11 |
+
"predict_steps_per_second": 0.289
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_loss": 2.1397388414151406,
|
| 4 |
+
"train_runtime": 8310.1091,
|
| 5 |
+
"train_samples": 11044,
|
| 6 |
+
"train_samples_per_second": 13.29,
|
| 7 |
+
"train_steps_per_second": 0.416
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,229 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 3460,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.29,
|
| 12 |
+
"learning_rate": 4.855491329479769e-05,
|
| 13 |
+
"loss": 2.85,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.58,
|
| 18 |
+
"learning_rate": 4.710982658959538e-05,
|
| 19 |
+
"loss": 2.5244,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.87,
|
| 24 |
+
"learning_rate": 4.566473988439307e-05,
|
| 25 |
+
"loss": 2.4551,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 1.16,
|
| 30 |
+
"learning_rate": 4.421965317919075e-05,
|
| 31 |
+
"loss": 2.3574,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.45,
|
| 36 |
+
"learning_rate": 4.2774566473988445e-05,
|
| 37 |
+
"loss": 2.3376,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.73,
|
| 42 |
+
"learning_rate": 4.132947976878613e-05,
|
| 43 |
+
"loss": 2.314,
|
| 44 |
+
"step": 600
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 2.02,
|
| 48 |
+
"learning_rate": 3.988439306358382e-05,
|
| 49 |
+
"loss": 2.2859,
|
| 50 |
+
"step": 700
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 2.31,
|
| 54 |
+
"learning_rate": 3.84393063583815e-05,
|
| 55 |
+
"loss": 2.2306,
|
| 56 |
+
"step": 800
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 2.6,
|
| 60 |
+
"learning_rate": 3.699421965317919e-05,
|
| 61 |
+
"loss": 2.2102,
|
| 62 |
+
"step": 900
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 2.89,
|
| 66 |
+
"learning_rate": 3.554913294797688e-05,
|
| 67 |
+
"loss": 2.2117,
|
| 68 |
+
"step": 1000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.18,
|
| 72 |
+
"learning_rate": 3.410404624277457e-05,
|
| 73 |
+
"loss": 2.1662,
|
| 74 |
+
"step": 1100
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 3.47,
|
| 78 |
+
"learning_rate": 3.265895953757225e-05,
|
| 79 |
+
"loss": 2.1411,
|
| 80 |
+
"step": 1200
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 3.76,
|
| 84 |
+
"learning_rate": 3.1213872832369946e-05,
|
| 85 |
+
"loss": 2.1541,
|
| 86 |
+
"step": 1300
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 4.05,
|
| 90 |
+
"learning_rate": 2.9768786127167632e-05,
|
| 91 |
+
"loss": 2.1407,
|
| 92 |
+
"step": 1400
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 4.34,
|
| 96 |
+
"learning_rate": 2.832369942196532e-05,
|
| 97 |
+
"loss": 2.1051,
|
| 98 |
+
"step": 1500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 4.62,
|
| 102 |
+
"learning_rate": 2.6878612716763007e-05,
|
| 103 |
+
"loss": 2.0974,
|
| 104 |
+
"step": 1600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 4.91,
|
| 108 |
+
"learning_rate": 2.5433526011560693e-05,
|
| 109 |
+
"loss": 2.1,
|
| 110 |
+
"step": 1700
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 5.2,
|
| 114 |
+
"learning_rate": 2.3988439306358382e-05,
|
| 115 |
+
"loss": 2.0643,
|
| 116 |
+
"step": 1800
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 5.49,
|
| 120 |
+
"learning_rate": 2.254335260115607e-05,
|
| 121 |
+
"loss": 2.048,
|
| 122 |
+
"step": 1900
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 5.78,
|
| 126 |
+
"learning_rate": 2.1098265895953757e-05,
|
| 127 |
+
"loss": 2.0663,
|
| 128 |
+
"step": 2000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 6.07,
|
| 132 |
+
"learning_rate": 1.9653179190751446e-05,
|
| 133 |
+
"loss": 2.0447,
|
| 134 |
+
"step": 2100
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.36,
|
| 138 |
+
"learning_rate": 1.8208092485549132e-05,
|
| 139 |
+
"loss": 2.0395,
|
| 140 |
+
"step": 2200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 6.65,
|
| 144 |
+
"learning_rate": 1.676300578034682e-05,
|
| 145 |
+
"loss": 2.021,
|
| 146 |
+
"step": 2300
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 6.94,
|
| 150 |
+
"learning_rate": 1.531791907514451e-05,
|
| 151 |
+
"loss": 2.0177,
|
| 152 |
+
"step": 2400
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 7.23,
|
| 156 |
+
"learning_rate": 1.3872832369942197e-05,
|
| 157 |
+
"loss": 2.0087,
|
| 158 |
+
"step": 2500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 7.51,
|
| 162 |
+
"learning_rate": 1.2427745664739884e-05,
|
| 163 |
+
"loss": 1.9849,
|
| 164 |
+
"step": 2600
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 7.8,
|
| 168 |
+
"learning_rate": 1.0982658959537573e-05,
|
| 169 |
+
"loss": 1.9991,
|
| 170 |
+
"step": 2700
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 8.09,
|
| 174 |
+
"learning_rate": 9.53757225433526e-06,
|
| 175 |
+
"loss": 1.9992,
|
| 176 |
+
"step": 2800
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 8.38,
|
| 180 |
+
"learning_rate": 8.092485549132949e-06,
|
| 181 |
+
"loss": 1.9687,
|
| 182 |
+
"step": 2900
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 8.67,
|
| 186 |
+
"learning_rate": 6.647398843930635e-06,
|
| 187 |
+
"loss": 1.9803,
|
| 188 |
+
"step": 3000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 8.96,
|
| 192 |
+
"learning_rate": 5.202312138728324e-06,
|
| 193 |
+
"loss": 2.0046,
|
| 194 |
+
"step": 3100
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 9.25,
|
| 198 |
+
"learning_rate": 3.757225433526012e-06,
|
| 199 |
+
"loss": 1.9629,
|
| 200 |
+
"step": 3200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 9.54,
|
| 204 |
+
"learning_rate": 2.3121387283236993e-06,
|
| 205 |
+
"loss": 1.9686,
|
| 206 |
+
"step": 3300
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 9.83,
|
| 210 |
+
"learning_rate": 8.670520231213873e-07,
|
| 211 |
+
"loss": 1.9876,
|
| 212 |
+
"step": 3400
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 10.0,
|
| 216 |
+
"step": 3460,
|
| 217 |
+
"total_flos": 3.302612726022144e+17,
|
| 218 |
+
"train_loss": 2.1397388414151406,
|
| 219 |
+
"train_runtime": 8310.1091,
|
| 220 |
+
"train_samples_per_second": 13.29,
|
| 221 |
+
"train_steps_per_second": 0.416
|
| 222 |
+
}
|
| 223 |
+
],
|
| 224 |
+
"max_steps": 3460,
|
| 225 |
+
"num_train_epochs": 10,
|
| 226 |
+
"total_flos": 3.302612726022144e+17,
|
| 227 |
+
"trial_name": null,
|
| 228 |
+
"trial_params": null
|
| 229 |
+
}
|