Training in progress, epoch 1
Browse files- all_results.json +25 -25
- eval_results.json +10 -10
- generated_predictions.txt +0 -0
- predict_results.json +10 -10
- pytorch_model.bin +1 -1
- runs/Mar26_18-34-27_kogecha/events.out.tfevents.1711446687.kogecha +3 -0
- runs/Mar26_19-07-17_kogecha/events.out.tfevents.1711447649.kogecha +3 -0
- train_results.json +5 -5
- trainer_state.json +94 -172
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,28 +1,28 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
-
"eval_gen_len":
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_rouge1":
|
| 6 |
-
"eval_rouge2": 3.
|
| 7 |
-
"eval_rougeL":
|
| 8 |
-
"eval_rougeLsum":
|
| 9 |
-
"eval_runtime":
|
| 10 |
-
"eval_samples":
|
| 11 |
-
"eval_samples_per_second":
|
| 12 |
-
"eval_steps_per_second":
|
| 13 |
-
"predict_gen_len":
|
| 14 |
-
"predict_loss":
|
| 15 |
-
"predict_rouge1":
|
| 16 |
-
"predict_rouge2":
|
| 17 |
-
"predict_rougeL":
|
| 18 |
-
"predict_rougeLsum":
|
| 19 |
-
"predict_runtime":
|
| 20 |
-
"predict_samples":
|
| 21 |
-
"predict_samples_per_second":
|
| 22 |
-
"predict_steps_per_second":
|
| 23 |
-
"train_loss":
|
| 24 |
-
"train_runtime":
|
| 25 |
-
"train_samples":
|
| 26 |
-
"train_samples_per_second":
|
| 27 |
-
"train_steps_per_second":
|
| 28 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
+
"eval_gen_len": 63.7625,
|
| 4 |
+
"eval_loss": 2.0723605155944824,
|
| 5 |
+
"eval_rouge1": 15.5769,
|
| 6 |
+
"eval_rouge2": 3.3042,
|
| 7 |
+
"eval_rougeL": 11.0176,
|
| 8 |
+
"eval_rougeLsum": 12.8107,
|
| 9 |
+
"eval_runtime": 78.8993,
|
| 10 |
+
"eval_samples": 80,
|
| 11 |
+
"eval_samples_per_second": 1.014,
|
| 12 |
+
"eval_steps_per_second": 1.014,
|
| 13 |
+
"predict_gen_len": 58.329787234042556,
|
| 14 |
+
"predict_loss": 2.241582155227661,
|
| 15 |
+
"predict_rouge1": 20.5805,
|
| 16 |
+
"predict_rouge2": 6.166,
|
| 17 |
+
"predict_rougeL": 14.2848,
|
| 18 |
+
"predict_rougeLsum": 15.2919,
|
| 19 |
+
"predict_runtime": 90.5083,
|
| 20 |
+
"predict_samples": 94,
|
| 21 |
+
"predict_samples_per_second": 1.039,
|
| 22 |
+
"predict_steps_per_second": 1.039,
|
| 23 |
+
"train_loss": 1.0774688316355856,
|
| 24 |
+
"train_runtime": 820.1414,
|
| 25 |
+
"train_samples": 717,
|
| 26 |
+
"train_samples_per_second": 4.371,
|
| 27 |
+
"train_steps_per_second": 4.371
|
| 28 |
}
|
eval_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
-
"eval_gen_len":
|
| 4 |
-
"eval_loss":
|
| 5 |
-
"eval_rouge1":
|
| 6 |
-
"eval_rouge2": 3.
|
| 7 |
-
"eval_rougeL":
|
| 8 |
-
"eval_rougeLsum":
|
| 9 |
-
"eval_runtime":
|
| 10 |
-
"eval_samples":
|
| 11 |
-
"eval_samples_per_second":
|
| 12 |
-
"eval_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
+
"eval_gen_len": 63.7625,
|
| 4 |
+
"eval_loss": 2.0723605155944824,
|
| 5 |
+
"eval_rouge1": 15.5769,
|
| 6 |
+
"eval_rouge2": 3.3042,
|
| 7 |
+
"eval_rougeL": 11.0176,
|
| 8 |
+
"eval_rougeLsum": 12.8107,
|
| 9 |
+
"eval_runtime": 78.8993,
|
| 10 |
+
"eval_samples": 80,
|
| 11 |
+
"eval_samples_per_second": 1.014,
|
| 12 |
+
"eval_steps_per_second": 1.014
|
| 13 |
}
|
generated_predictions.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
predict_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"predict_gen_len":
|
| 3 |
-
"predict_loss":
|
| 4 |
-
"predict_rouge1":
|
| 5 |
-
"predict_rouge2":
|
| 6 |
-
"predict_rougeL":
|
| 7 |
-
"predict_rougeLsum":
|
| 8 |
-
"predict_runtime":
|
| 9 |
-
"predict_samples":
|
| 10 |
-
"predict_samples_per_second":
|
| 11 |
-
"predict_steps_per_second":
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"predict_gen_len": 58.329787234042556,
|
| 3 |
+
"predict_loss": 2.241582155227661,
|
| 4 |
+
"predict_rouge1": 20.5805,
|
| 5 |
+
"predict_rouge2": 6.166,
|
| 6 |
+
"predict_rougeL": 14.2848,
|
| 7 |
+
"predict_rougeLsum": 15.2919,
|
| 8 |
+
"predict_runtime": 90.5083,
|
| 9 |
+
"predict_samples": 94,
|
| 10 |
+
"predict_samples_per_second": 1.039,
|
| 11 |
+
"predict_steps_per_second": 1.039
|
| 12 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 501807853
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19dbc6c5a6017e5db63b49510291f078d1639718550d47be1687a31bf30a05af
|
| 3 |
size 501807853
|
runs/Mar26_18-34-27_kogecha/events.out.tfevents.1711446687.kogecha
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a3139ec298ed4a872dfea73e55876be15c25d282143607cd2478f9e7e121ecd
|
| 3 |
+
size 565
|
runs/Mar26_19-07-17_kogecha/events.out.tfevents.1711447649.kogecha
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b968ba2687d93eecb051e7ade0a201cda659c0742805148d4e08b52f12a14971
|
| 3 |
+
size 6380
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples":
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 5.0,
|
| 3 |
+
"train_loss": 1.0774688316355856,
|
| 4 |
+
"train_runtime": 820.1414,
|
| 5 |
+
"train_samples": 717,
|
| 6 |
+
"train_samples_per_second": 4.371,
|
| 7 |
+
"train_steps_per_second": 4.371
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,210 +1,132 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "saved/tobyoki-pairwise-wo_space/bart-base-japanese/BaseModel/checkpoint-
|
| 4 |
"epoch": 5.0,
|
| 5 |
-
"global_step":
|
| 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.
|
| 12 |
-
"learning_rate": 4.
|
| 13 |
-
"loss": 2.
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0
|
| 18 |
-
"
|
| 19 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0
|
| 24 |
-
"
|
| 25 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch":
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch":
|
| 36 |
-
"eval_gen_len":
|
| 37 |
-
"eval_loss": 2.
|
| 38 |
-
"eval_rouge1":
|
| 39 |
-
"eval_rouge2":
|
| 40 |
-
"eval_rougeL":
|
| 41 |
-
"eval_rougeLsum":
|
| 42 |
-
"eval_runtime":
|
| 43 |
-
"eval_samples_per_second":
|
| 44 |
-
"eval_steps_per_second":
|
| 45 |
-
"step":
|
| 46 |
-
},
|
| 47 |
-
{
|
| 48 |
-
"epoch":
|
| 49 |
-
"learning_rate":
|
| 50 |
-
"loss": 0.
|
| 51 |
"step": 2500
|
| 52 |
},
|
| 53 |
{
|
| 54 |
-
"epoch":
|
| 55 |
-
"
|
| 56 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
"step": 3000
|
| 58 |
},
|
| 59 |
{
|
| 60 |
-
"epoch":
|
| 61 |
-
"learning_rate":
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 3500
|
| 64 |
},
|
| 65 |
-
{
|
| 66 |
-
"epoch": 1.98,
|
| 67 |
-
"learning_rate": 3.0246913580246916e-05,
|
| 68 |
-
"loss": 0.3308,
|
| 69 |
-
"step": 4000
|
| 70 |
-
},
|
| 71 |
-
{
|
| 72 |
-
"epoch": 2.0,
|
| 73 |
-
"eval_gen_len": 91.65034965034965,
|
| 74 |
-
"eval_loss": 2.9422976970672607,
|
| 75 |
-
"eval_rouge1": 17.9514,
|
| 76 |
-
"eval_rouge2": 2.8091,
|
| 77 |
-
"eval_rougeL": 10.9133,
|
| 78 |
-
"eval_rougeLsum": 15.4068,
|
| 79 |
-
"eval_runtime": 356.3388,
|
| 80 |
-
"eval_samples_per_second": 0.803,
|
| 81 |
-
"eval_steps_per_second": 0.803,
|
| 82 |
-
"step": 4050
|
| 83 |
-
},
|
| 84 |
-
{
|
| 85 |
-
"epoch": 2.22,
|
| 86 |
-
"learning_rate": 2.777777777777778e-05,
|
| 87 |
-
"loss": 0.2778,
|
| 88 |
-
"step": 4500
|
| 89 |
-
},
|
| 90 |
-
{
|
| 91 |
-
"epoch": 2.47,
|
| 92 |
-
"learning_rate": 2.5308641975308646e-05,
|
| 93 |
-
"loss": 0.2482,
|
| 94 |
-
"step": 5000
|
| 95 |
-
},
|
| 96 |
-
{
|
| 97 |
-
"epoch": 2.72,
|
| 98 |
-
"learning_rate": 2.2839506172839506e-05,
|
| 99 |
-
"loss": 0.2349,
|
| 100 |
-
"step": 5500
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 2.96,
|
| 104 |
-
"learning_rate": 2.037037037037037e-05,
|
| 105 |
-
"loss": 0.2302,
|
| 106 |
-
"step": 6000
|
| 107 |
-
},
|
| 108 |
-
{
|
| 109 |
-
"epoch": 3.0,
|
| 110 |
-
"eval_gen_len": 77.1993006993007,
|
| 111 |
-
"eval_loss": 3.0624501705169678,
|
| 112 |
-
"eval_rouge1": 16.1453,
|
| 113 |
-
"eval_rouge2": 3.0026,
|
| 114 |
-
"eval_rougeL": 10.272,
|
| 115 |
-
"eval_rougeLsum": 14.0716,
|
| 116 |
-
"eval_runtime": 279.7235,
|
| 117 |
-
"eval_samples_per_second": 1.022,
|
| 118 |
-
"eval_steps_per_second": 1.022,
|
| 119 |
-
"step": 6075
|
| 120 |
-
},
|
| 121 |
-
{
|
| 122 |
-
"epoch": 3.21,
|
| 123 |
-
"learning_rate": 1.7901234567901236e-05,
|
| 124 |
-
"loss": 0.1927,
|
| 125 |
-
"step": 6500
|
| 126 |
-
},
|
| 127 |
-
{
|
| 128 |
-
"epoch": 3.46,
|
| 129 |
-
"learning_rate": 1.54320987654321e-05,
|
| 130 |
-
"loss": 0.1607,
|
| 131 |
-
"step": 7000
|
| 132 |
-
},
|
| 133 |
-
{
|
| 134 |
-
"epoch": 3.7,
|
| 135 |
-
"learning_rate": 1.2962962962962962e-05,
|
| 136 |
-
"loss": 0.1621,
|
| 137 |
-
"step": 7500
|
| 138 |
-
},
|
| 139 |
-
{
|
| 140 |
-
"epoch": 3.95,
|
| 141 |
-
"learning_rate": 1.0493827160493827e-05,
|
| 142 |
-
"loss": 0.1576,
|
| 143 |
-
"step": 8000
|
| 144 |
-
},
|
| 145 |
-
{
|
| 146 |
-
"epoch": 4.0,
|
| 147 |
-
"eval_gen_len": 88.3986013986014,
|
| 148 |
-
"eval_loss": 3.2307794094085693,
|
| 149 |
-
"eval_rouge1": 17.8409,
|
| 150 |
-
"eval_rouge2": 2.9937,
|
| 151 |
-
"eval_rougeL": 10.8765,
|
| 152 |
-
"eval_rougeLsum": 15.6203,
|
| 153 |
-
"eval_runtime": 323.891,
|
| 154 |
-
"eval_samples_per_second": 0.883,
|
| 155 |
-
"eval_steps_per_second": 0.883,
|
| 156 |
-
"step": 8100
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 4.2,
|
| 160 |
-
"learning_rate": 8.02469135802469e-06,
|
| 161 |
-
"loss": 0.1289,
|
| 162 |
-
"step": 8500
|
| 163 |
-
},
|
| 164 |
-
{
|
| 165 |
-
"epoch": 4.44,
|
| 166 |
-
"learning_rate": 5.555555555555556e-06,
|
| 167 |
-
"loss": 0.1385,
|
| 168 |
-
"step": 9000
|
| 169 |
-
},
|
| 170 |
-
{
|
| 171 |
-
"epoch": 4.69,
|
| 172 |
-
"learning_rate": 3.0864197530864196e-06,
|
| 173 |
-
"loss": 0.1315,
|
| 174 |
-
"step": 9500
|
| 175 |
-
},
|
| 176 |
-
{
|
| 177 |
-
"epoch": 4.94,
|
| 178 |
-
"learning_rate": 6.17283950617284e-07,
|
| 179 |
-
"loss": 0.1055,
|
| 180 |
-
"step": 10000
|
| 181 |
-
},
|
| 182 |
{
|
| 183 |
"epoch": 5.0,
|
| 184 |
-
"eval_gen_len":
|
| 185 |
-
"eval_loss":
|
| 186 |
-
"eval_rouge1":
|
| 187 |
-
"eval_rouge2":
|
| 188 |
-
"eval_rougeL": 10.
|
| 189 |
-
"eval_rougeLsum":
|
| 190 |
-
"eval_runtime":
|
| 191 |
-
"eval_samples_per_second":
|
| 192 |
-
"eval_steps_per_second":
|
| 193 |
-
"step":
|
| 194 |
},
|
| 195 |
{
|
| 196 |
"epoch": 5.0,
|
| 197 |
-
"step":
|
| 198 |
-
"total_flos":
|
| 199 |
-
"train_loss":
|
| 200 |
-
"train_runtime":
|
| 201 |
-
"train_samples_per_second":
|
| 202 |
-
"train_steps_per_second":
|
| 203 |
}
|
| 204 |
],
|
| 205 |
-
"max_steps":
|
| 206 |
"num_train_epochs": 5,
|
| 207 |
-
"total_flos":
|
| 208 |
"trial_name": null,
|
| 209 |
"trial_params": null
|
| 210 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 15.5769,
|
| 3 |
+
"best_model_checkpoint": "saved/tobyoki-pairwise-wo_space/bart-base-japanese/BaseModel/checkpoint-2868",
|
| 4 |
"epoch": 5.0,
|
| 5 |
+
"global_step": 3585,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.7,
|
| 12 |
+
"learning_rate": 4.302649930264993e-05,
|
| 13 |
+
"loss": 2.1701,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_gen_len": 47.7375,
|
| 19 |
+
"eval_loss": 1.9507354497909546,
|
| 20 |
+
"eval_rouge1": 12.6467,
|
| 21 |
+
"eval_rouge2": 2.901,
|
| 22 |
+
"eval_rougeL": 10.0035,
|
| 23 |
+
"eval_rougeLsum": 11.1471,
|
| 24 |
+
"eval_runtime": 49.6131,
|
| 25 |
+
"eval_samples_per_second": 1.612,
|
| 26 |
+
"eval_steps_per_second": 1.612,
|
| 27 |
+
"step": 717
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.39,
|
| 31 |
+
"learning_rate": 3.6052998605299864e-05,
|
| 32 |
+
"loss": 1.4042,
|
| 33 |
"step": 1000
|
| 34 |
},
|
| 35 |
{
|
| 36 |
+
"epoch": 2.0,
|
| 37 |
+
"eval_gen_len": 21.1375,
|
| 38 |
+
"eval_loss": 1.9519145488739014,
|
| 39 |
+
"eval_rouge1": 11.9515,
|
| 40 |
+
"eval_rouge2": 3.096,
|
| 41 |
+
"eval_rougeL": 10.2259,
|
| 42 |
+
"eval_rougeLsum": 10.8478,
|
| 43 |
+
"eval_runtime": 36.7295,
|
| 44 |
+
"eval_samples_per_second": 2.178,
|
| 45 |
+
"eval_steps_per_second": 2.178,
|
| 46 |
+
"step": 1434
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.09,
|
| 50 |
+
"learning_rate": 2.9079497907949792e-05,
|
| 51 |
+
"loss": 1.1417,
|
| 52 |
"step": 1500
|
| 53 |
},
|
| 54 |
{
|
| 55 |
+
"epoch": 2.79,
|
| 56 |
+
"learning_rate": 2.2105997210599723e-05,
|
| 57 |
+
"loss": 0.8952,
|
| 58 |
"step": 2000
|
| 59 |
},
|
| 60 |
{
|
| 61 |
+
"epoch": 3.0,
|
| 62 |
+
"eval_gen_len": 76.35,
|
| 63 |
+
"eval_loss": 2.0322935581207275,
|
| 64 |
+
"eval_rouge1": 15.5721,
|
| 65 |
+
"eval_rouge2": 3.5875,
|
| 66 |
+
"eval_rougeL": 10.6382,
|
| 67 |
+
"eval_rougeLsum": 12.9346,
|
| 68 |
+
"eval_runtime": 127.0578,
|
| 69 |
+
"eval_samples_per_second": 0.63,
|
| 70 |
+
"eval_steps_per_second": 0.63,
|
| 71 |
+
"step": 2151
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.49,
|
| 75 |
+
"learning_rate": 1.5132496513249652e-05,
|
| 76 |
+
"loss": 0.7489,
|
| 77 |
"step": 2500
|
| 78 |
},
|
| 79 |
{
|
| 80 |
+
"epoch": 4.0,
|
| 81 |
+
"eval_gen_len": 63.7625,
|
| 82 |
+
"eval_loss": 2.0723605155944824,
|
| 83 |
+
"eval_rouge1": 15.5769,
|
| 84 |
+
"eval_rouge2": 3.3042,
|
| 85 |
+
"eval_rougeL": 11.0176,
|
| 86 |
+
"eval_rougeLsum": 12.8107,
|
| 87 |
+
"eval_runtime": 79.609,
|
| 88 |
+
"eval_samples_per_second": 1.005,
|
| 89 |
+
"eval_steps_per_second": 1.005,
|
| 90 |
+
"step": 2868
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 4.18,
|
| 94 |
+
"learning_rate": 8.158995815899583e-06,
|
| 95 |
+
"loss": 0.6757,
|
| 96 |
"step": 3000
|
| 97 |
},
|
| 98 |
{
|
| 99 |
+
"epoch": 4.88,
|
| 100 |
+
"learning_rate": 1.185495118549512e-06,
|
| 101 |
+
"loss": 0.5941,
|
| 102 |
"step": 3500
|
| 103 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 104 |
{
|
| 105 |
"epoch": 5.0,
|
| 106 |
+
"eval_gen_len": 66.075,
|
| 107 |
+
"eval_loss": 2.0849809646606445,
|
| 108 |
+
"eval_rouge1": 15.3454,
|
| 109 |
+
"eval_rouge2": 2.9489,
|
| 110 |
+
"eval_rougeL": 10.7691,
|
| 111 |
+
"eval_rougeLsum": 12.7028,
|
| 112 |
+
"eval_runtime": 76.3627,
|
| 113 |
+
"eval_samples_per_second": 1.048,
|
| 114 |
+
"eval_steps_per_second": 1.048,
|
| 115 |
+
"step": 3585
|
| 116 |
},
|
| 117 |
{
|
| 118 |
"epoch": 5.0,
|
| 119 |
+
"step": 3585,
|
| 120 |
+
"total_flos": 682678854881280.0,
|
| 121 |
+
"train_loss": 1.0774688316355856,
|
| 122 |
+
"train_runtime": 820.1414,
|
| 123 |
+
"train_samples_per_second": 4.371,
|
| 124 |
+
"train_steps_per_second": 4.371
|
| 125 |
}
|
| 126 |
],
|
| 127 |
+
"max_steps": 3585,
|
| 128 |
"num_train_epochs": 5,
|
| 129 |
+
"total_flos": 682678854881280.0,
|
| 130 |
"trial_name": null,
|
| 131 |
"trial_params": null
|
| 132 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4475
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6030a0c82b601891bd894a96708a17ba86168c75bb195657482dcd66f486273
|
| 3 |
size 4475
|