Training in progress, step 250
Browse files- all_results.json +10 -10
- eval_results.json +6 -6
- pytorch_model.bin +1 -1
- runs/Mar28_12-47-23_terra/events.out.tfevents.1680023505.terra.66467.2 +3 -0
- runs/Mar28_18-26-48_terra/1680028144.785447/events.out.tfevents.1680028144.terra.134316.1 +3 -0
- runs/Mar28_18-26-48_terra/events.out.tfevents.1680028144.terra.134316.0 +3 -0
- runs/Mar29_09-18-59_terra/1680081675.3416204/events.out.tfevents.1680081675.terra.179326.1 +3 -0
- runs/Mar29_09-18-59_terra/events.out.tfevents.1680081675.terra.179326.0 +3 -0
- train_results.json +4 -4
- trainer_state.json +281 -20
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
-
"eval_wer":
|
| 9 |
-
"train_loss":
|
| 10 |
-
"train_runtime":
|
| 11 |
-
"train_samples_per_second":
|
| 12 |
-
"train_steps_per_second": 0.
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.6321855187416077,
|
| 4 |
+
"eval_runtime": 71.348,
|
| 5 |
+
"eval_samples": 250,
|
| 6 |
+
"eval_samples_per_second": 3.504,
|
| 7 |
+
"eval_steps_per_second": 0.224,
|
| 8 |
+
"eval_wer": 45.68657478305258,
|
| 9 |
+
"train_loss": 1.2054000387191772,
|
| 10 |
+
"train_runtime": 15609.5124,
|
| 11 |
+
"train_samples_per_second": 4.1,
|
| 12 |
+
"train_steps_per_second": 0.064
|
| 13 |
}
|
eval_results.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"eval_loss":
|
| 4 |
-
"eval_runtime":
|
| 5 |
-
"eval_samples":
|
| 6 |
-
"eval_samples_per_second":
|
| 7 |
-
"eval_steps_per_second": 0.
|
| 8 |
-
"eval_wer":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.6321855187416077,
|
| 4 |
+
"eval_runtime": 71.348,
|
| 5 |
+
"eval_samples": 250,
|
| 6 |
+
"eval_samples_per_second": 3.504,
|
| 7 |
+
"eval_steps_per_second": 0.224,
|
| 8 |
+
"eval_wer": 45.68657478305258
|
| 9 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 151098921
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea7de59f30238f4b800e06742fc6dec544492a0f924d59aed4f2f7bd95d29979
|
| 3 |
size 151098921
|
runs/Mar28_12-47-23_terra/events.out.tfevents.1680023505.terra.66467.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:32cafa44f22c2765c1ba9b1f7116c9dfff5faa4751fe8d569325a128d4f85144
|
| 3 |
+
size 406
|
runs/Mar28_18-26-48_terra/1680028144.785447/events.out.tfevents.1680028144.terra.134316.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:caf7878e22233bb68496b95a7844174506efad9c6ae89c1841097f01d2ceb525
|
| 3 |
+
size 5980
|
runs/Mar28_18-26-48_terra/events.out.tfevents.1680028144.terra.134316.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f52eaa416605ea7cd6cdb33cb6996b79096c6ce74d8b0c186b13c8819b492d3f
|
| 3 |
+
size 5923
|
runs/Mar29_09-18-59_terra/1680081675.3416204/events.out.tfevents.1680081675.terra.179326.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9296d6f980c6f1c6d96b859618a0da9bebbdfbebf0ffd3cee909559e2a6bf587
|
| 3 |
+
size 5980
|
runs/Mar29_09-18-59_terra/events.out.tfevents.1680081675.terra.179326.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2efd1579bae671bd7558dd3de0db93dad9c66209f91375feb5735a4b2e92d4d5
|
| 3 |
+
size 6241
|
train_results.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
-
"train_loss":
|
| 4 |
-
"train_runtime":
|
| 5 |
-
"train_samples_per_second":
|
| 6 |
-
"train_steps_per_second": 0.
|
| 7 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"epoch": 1.0,
|
| 3 |
+
"train_loss": 1.2054000387191772,
|
| 4 |
+
"train_runtime": 15609.5124,
|
| 5 |
+
"train_samples_per_second": 4.1,
|
| 6 |
+
"train_steps_per_second": 0.064
|
| 7 |
}
|
trainer_state.json
CHANGED
|
@@ -1,40 +1,301 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint":
|
| 4 |
"epoch": 1.0,
|
| 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": 1.0,
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss":
|
| 14 |
-
"step":
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 1.0,
|
| 18 |
-
"eval_loss":
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second": 0.
|
| 22 |
-
"eval_wer":
|
| 23 |
-
"step":
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 1.0,
|
| 27 |
-
"step":
|
| 28 |
-
"total_flos":
|
| 29 |
-
"train_loss":
|
| 30 |
-
"train_runtime":
|
| 31 |
-
"train_samples_per_second":
|
| 32 |
-
"train_steps_per_second": 0.
|
| 33 |
}
|
| 34 |
],
|
| 35 |
-
"max_steps":
|
| 36 |
"num_train_epochs": 9223372036854775807,
|
| 37 |
-
"total_flos":
|
| 38 |
"trial_name": null,
|
| 39 |
"trial_params": null
|
| 40 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 45.68657478305258,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-1000",
|
| 4 |
"epoch": 1.0,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 4.6000000000000004e-07,
|
| 13 |
+
"loss": 3.7453,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.05,
|
| 18 |
+
"learning_rate": 9.600000000000001e-07,
|
| 19 |
+
"loss": 3.4563,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 1.46e-06,
|
| 25 |
+
"loss": 3.1538,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1,
|
| 30 |
+
"learning_rate": 1.9600000000000003e-06,
|
| 31 |
+
"loss": 2.6311,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.12,
|
| 36 |
+
"learning_rate": 2.46e-06,
|
| 37 |
+
"loss": 2.1979,
|
| 38 |
+
"step": 125
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.15,
|
| 42 |
+
"learning_rate": 2.96e-06,
|
| 43 |
+
"loss": 1.9003,
|
| 44 |
+
"step": 150
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17,
|
| 48 |
+
"learning_rate": 3.46e-06,
|
| 49 |
+
"loss": 1.7659,
|
| 50 |
+
"step": 175
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.2,
|
| 54 |
+
"learning_rate": 3.96e-06,
|
| 55 |
+
"loss": 1.5471,
|
| 56 |
+
"step": 200
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.23,
|
| 60 |
+
"learning_rate": 4.4600000000000005e-06,
|
| 61 |
+
"loss": 1.3988,
|
| 62 |
+
"step": 225
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.25,
|
| 66 |
+
"learning_rate": 4.960000000000001e-06,
|
| 67 |
+
"loss": 1.4343,
|
| 68 |
+
"step": 250
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.25,
|
| 72 |
+
"eval_loss": 1.5133659839630127,
|
| 73 |
+
"eval_runtime": 49.0888,
|
| 74 |
+
"eval_samples_per_second": 5.093,
|
| 75 |
+
"eval_steps_per_second": 0.326,
|
| 76 |
+
"eval_wer": 79.0199081163859,
|
| 77 |
+
"step": 250
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.28,
|
| 81 |
+
"learning_rate": 5.460000000000001e-06,
|
| 82 |
+
"loss": 1.2074,
|
| 83 |
+
"step": 275
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.3,
|
| 87 |
+
"learning_rate": 5.9600000000000005e-06,
|
| 88 |
+
"loss": 1.3248,
|
| 89 |
+
"step": 300
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.33,
|
| 93 |
+
"learning_rate": 6.460000000000001e-06,
|
| 94 |
+
"loss": 1.2724,
|
| 95 |
+
"step": 325
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.35,
|
| 99 |
+
"learning_rate": 6.96e-06,
|
| 100 |
+
"loss": 1.15,
|
| 101 |
+
"step": 350
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.38,
|
| 105 |
+
"learning_rate": 7.4600000000000006e-06,
|
| 106 |
+
"loss": 1.0426,
|
| 107 |
+
"step": 375
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.4,
|
| 111 |
+
"learning_rate": 7.960000000000002e-06,
|
| 112 |
+
"loss": 1.0967,
|
| 113 |
+
"step": 400
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.42,
|
| 117 |
+
"learning_rate": 8.46e-06,
|
| 118 |
+
"loss": 1.0666,
|
| 119 |
+
"step": 425
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.45,
|
| 123 |
+
"learning_rate": 8.96e-06,
|
| 124 |
+
"loss": 0.9832,
|
| 125 |
+
"step": 450
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.47,
|
| 129 |
+
"learning_rate": 9.460000000000001e-06,
|
| 130 |
+
"loss": 0.6704,
|
| 131 |
+
"step": 475
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.5,
|
| 135 |
+
"learning_rate": 9.960000000000001e-06,
|
| 136 |
+
"loss": 0.7719,
|
| 137 |
+
"step": 500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5,
|
| 141 |
+
"eval_loss": 0.8723946213722229,
|
| 142 |
+
"eval_runtime": 42.8226,
|
| 143 |
+
"eval_samples_per_second": 5.838,
|
| 144 |
+
"eval_steps_per_second": 0.374,
|
| 145 |
+
"eval_wer": 61.20469627360898,
|
| 146 |
+
"step": 500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.53,
|
| 150 |
+
"learning_rate": 9.54e-06,
|
| 151 |
+
"loss": 1.0086,
|
| 152 |
+
"step": 525
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.55,
|
| 156 |
+
"learning_rate": 9.040000000000002e-06,
|
| 157 |
+
"loss": 0.7805,
|
| 158 |
+
"step": 550
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.57,
|
| 162 |
+
"learning_rate": 8.540000000000001e-06,
|
| 163 |
+
"loss": 0.7918,
|
| 164 |
+
"step": 575
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.6,
|
| 168 |
+
"learning_rate": 8.040000000000001e-06,
|
| 169 |
+
"loss": 0.8321,
|
| 170 |
+
"step": 600
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.62,
|
| 174 |
+
"learning_rate": 7.540000000000001e-06,
|
| 175 |
+
"loss": 0.7615,
|
| 176 |
+
"step": 625
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.65,
|
| 180 |
+
"learning_rate": 7.04e-06,
|
| 181 |
+
"loss": 0.6704,
|
| 182 |
+
"step": 650
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.68,
|
| 186 |
+
"learning_rate": 6.540000000000001e-06,
|
| 187 |
+
"loss": 0.6398,
|
| 188 |
+
"step": 675
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.7,
|
| 192 |
+
"learning_rate": 6.040000000000001e-06,
|
| 193 |
+
"loss": 0.7214,
|
| 194 |
+
"step": 700
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.72,
|
| 198 |
+
"learning_rate": 5.540000000000001e-06,
|
| 199 |
+
"loss": 0.7312,
|
| 200 |
+
"step": 725
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.75,
|
| 204 |
+
"learning_rate": 5.04e-06,
|
| 205 |
+
"loss": 0.7181,
|
| 206 |
+
"step": 750
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.75,
|
| 210 |
+
"eval_loss": 0.6546878814697266,
|
| 211 |
+
"eval_runtime": 41.6435,
|
| 212 |
+
"eval_samples_per_second": 6.003,
|
| 213 |
+
"eval_steps_per_second": 0.384,
|
| 214 |
+
"eval_wer": 47.32006125574272,
|
| 215 |
+
"step": 750
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.78,
|
| 219 |
+
"learning_rate": 4.540000000000001e-06,
|
| 220 |
+
"loss": 0.9827,
|
| 221 |
+
"step": 775
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.8,
|
| 225 |
+
"learning_rate": 4.04e-06,
|
| 226 |
+
"loss": 0.8042,
|
| 227 |
+
"step": 800
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.82,
|
| 231 |
+
"learning_rate": 3.54e-06,
|
| 232 |
+
"loss": 0.6615,
|
| 233 |
+
"step": 825
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.85,
|
| 237 |
+
"learning_rate": 3.04e-06,
|
| 238 |
+
"loss": 0.663,
|
| 239 |
+
"step": 850
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.88,
|
| 243 |
+
"learning_rate": 2.5400000000000002e-06,
|
| 244 |
+
"loss": 0.6304,
|
| 245 |
+
"step": 875
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.9,
|
| 249 |
+
"learning_rate": 2.04e-06,
|
| 250 |
+
"loss": 0.6005,
|
| 251 |
+
"step": 900
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 0.93,
|
| 255 |
+
"learning_rate": 1.54e-06,
|
| 256 |
+
"loss": 0.6095,
|
| 257 |
+
"step": 925
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 0.95,
|
| 261 |
+
"learning_rate": 1.04e-06,
|
| 262 |
+
"loss": 0.6342,
|
| 263 |
+
"step": 950
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.97,
|
| 267 |
+
"learning_rate": 5.4e-07,
|
| 268 |
+
"loss": 0.5841,
|
| 269 |
+
"step": 975
|
| 270 |
+
},
|
| 271 |
{
|
| 272 |
"epoch": 1.0,
|
| 273 |
+
"learning_rate": 4e-08,
|
| 274 |
+
"loss": 0.5734,
|
| 275 |
+
"step": 1000
|
| 276 |
},
|
| 277 |
{
|
| 278 |
"epoch": 1.0,
|
| 279 |
+
"eval_loss": 0.6321855187416077,
|
| 280 |
+
"eval_runtime": 76.4524,
|
| 281 |
+
"eval_samples_per_second": 3.27,
|
| 282 |
+
"eval_steps_per_second": 0.209,
|
| 283 |
+
"eval_wer": 45.68657478305258,
|
| 284 |
+
"step": 1000
|
| 285 |
},
|
| 286 |
{
|
| 287 |
"epoch": 1.0,
|
| 288 |
+
"step": 1000,
|
| 289 |
+
"total_flos": 1.57560864768e+18,
|
| 290 |
+
"train_loss": 1.2054000387191772,
|
| 291 |
+
"train_runtime": 15609.5124,
|
| 292 |
+
"train_samples_per_second": 4.1,
|
| 293 |
+
"train_steps_per_second": 0.064
|
| 294 |
}
|
| 295 |
],
|
| 296 |
+
"max_steps": 1000,
|
| 297 |
"num_train_epochs": 9223372036854775807,
|
| 298 |
+
"total_flos": 1.57560864768e+18,
|
| 299 |
"trial_name": null,
|
| 300 |
"trial_params": null
|
| 301 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3707
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abb13985bfd676bc1d0554ae1032e15bf1e1d8a296d7a08c1c0cdaa54ed7fa49
|
| 3 |
size 3707
|