End of training
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_cer": 1.0,
|
| 4 |
+
"eval_loss": 3.148874282836914,
|
| 5 |
+
"eval_runtime": 37.2952,
|
| 6 |
+
"eval_samples_per_second": 13.943,
|
| 7 |
+
"eval_steps_per_second": 0.885,
|
| 8 |
+
"eval_wer": 1.0,
|
| 9 |
+
"predict_samples": 520,
|
| 10 |
+
"train_loss": 3.6673195455588545,
|
| 11 |
+
"train_runtime": 1011.7717,
|
| 12 |
+
"train_samples": 2173,
|
| 13 |
+
"train_samples_per_second": 6.443,
|
| 14 |
+
"train_steps_per_second": 0.101
|
| 15 |
+
}
|
predict_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_cer": 1.0,
|
| 4 |
+
"eval_loss": 3.148874282836914,
|
| 5 |
+
"eval_runtime": 37.2952,
|
| 6 |
+
"eval_samples_per_second": 13.943,
|
| 7 |
+
"eval_steps_per_second": 0.885,
|
| 8 |
+
"eval_wer": 1.0,
|
| 9 |
+
"predict_samples": 520
|
| 10 |
+
}
|
runs/Mar16_13-54-03_hf-paris-dgx-station-1/events.out.tfevents.1647436380.hf-paris-dgx-station-1.3978206.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1601ef9ecce6196a87644fb52e0289699a7ecb2f0f930668104626be3cc039b2
|
| 3 |
+
size 398
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 3.6673195455588545,
|
| 4 |
+
"train_runtime": 1011.7717,
|
| 5 |
+
"train_samples": 2173,
|
| 6 |
+
"train_samples_per_second": 6.443,
|
| 7 |
+
"train_steps_per_second": 0.101
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,687 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.1372523307800293,
|
| 3 |
+
"best_model_checkpoint": "xtreme_s_xlsr_mls_upd/checkpoint-100",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 102,
|
| 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": 0.0,
|
| 13 |
+
"loss": 10.1653,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.06,
|
| 18 |
+
"learning_rate": 0.0003,
|
| 19 |
+
"loss": 9.9916,
|
| 20 |
+
"step": 2
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.09,
|
| 24 |
+
"learning_rate": 0.000297029702970297,
|
| 25 |
+
"loss": 9.9785,
|
| 26 |
+
"step": 3
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.12,
|
| 30 |
+
"learning_rate": 0.000294059405940594,
|
| 31 |
+
"loss": 9.1255,
|
| 32 |
+
"step": 4
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.15,
|
| 36 |
+
"learning_rate": 0.000294059405940594,
|
| 37 |
+
"loss": 7.897,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.18,
|
| 42 |
+
"learning_rate": 0.00029108910891089107,
|
| 43 |
+
"loss": 7.7678,
|
| 44 |
+
"step": 6
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21,
|
| 48 |
+
"learning_rate": 0.00028811881188118806,
|
| 49 |
+
"loss": 6.6699,
|
| 50 |
+
"step": 7
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.24,
|
| 54 |
+
"learning_rate": 0.0002851485148514851,
|
| 55 |
+
"loss": 5.6942,
|
| 56 |
+
"step": 8
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.26,
|
| 60 |
+
"learning_rate": 0.00028217821782178216,
|
| 61 |
+
"loss": 5.0037,
|
| 62 |
+
"step": 9
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.29,
|
| 66 |
+
"learning_rate": 0.0002792079207920792,
|
| 67 |
+
"loss": 4.5539,
|
| 68 |
+
"step": 10
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.32,
|
| 72 |
+
"learning_rate": 0.0002762376237623762,
|
| 73 |
+
"loss": 4.3802,
|
| 74 |
+
"step": 11
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.35,
|
| 78 |
+
"learning_rate": 0.00027326732673267325,
|
| 79 |
+
"loss": 4.0771,
|
| 80 |
+
"step": 12
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.38,
|
| 84 |
+
"learning_rate": 0.0002702970297029703,
|
| 85 |
+
"loss": 3.9155,
|
| 86 |
+
"step": 13
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.41,
|
| 90 |
+
"learning_rate": 0.0002673267326732673,
|
| 91 |
+
"loss": 3.8023,
|
| 92 |
+
"step": 14
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.44,
|
| 96 |
+
"learning_rate": 0.00026435643564356434,
|
| 97 |
+
"loss": 3.7282,
|
| 98 |
+
"step": 15
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.47,
|
| 102 |
+
"learning_rate": 0.00026138613861386134,
|
| 103 |
+
"loss": 3.7088,
|
| 104 |
+
"step": 16
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.5,
|
| 108 |
+
"learning_rate": 0.0002584158415841584,
|
| 109 |
+
"loss": 3.5787,
|
| 110 |
+
"step": 17
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.53,
|
| 114 |
+
"learning_rate": 0.00025544554455445543,
|
| 115 |
+
"loss": 3.5437,
|
| 116 |
+
"step": 18
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.56,
|
| 120 |
+
"learning_rate": 0.00025247524752475243,
|
| 121 |
+
"loss": 3.495,
|
| 122 |
+
"step": 19
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.59,
|
| 126 |
+
"learning_rate": 0.0002495049504950495,
|
| 127 |
+
"loss": 3.4678,
|
| 128 |
+
"step": 20
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.59,
|
| 132 |
+
"eval_cer": 1.0,
|
| 133 |
+
"eval_loss": 3.458103895187378,
|
| 134 |
+
"eval_runtime": 36.7504,
|
| 135 |
+
"eval_samples_per_second": 13.932,
|
| 136 |
+
"eval_steps_per_second": 0.871,
|
| 137 |
+
"eval_wer": 1.0,
|
| 138 |
+
"step": 20
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.62,
|
| 142 |
+
"learning_rate": 0.0002465346534653465,
|
| 143 |
+
"loss": 3.4143,
|
| 144 |
+
"step": 21
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.65,
|
| 148 |
+
"learning_rate": 0.00024356435643564355,
|
| 149 |
+
"loss": 3.4058,
|
| 150 |
+
"step": 22
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.68,
|
| 154 |
+
"learning_rate": 0.0002405940594059406,
|
| 155 |
+
"loss": 3.3713,
|
| 156 |
+
"step": 23
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.71,
|
| 160 |
+
"learning_rate": 0.00023762376237623762,
|
| 161 |
+
"loss": 3.3317,
|
| 162 |
+
"step": 24
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.74,
|
| 166 |
+
"learning_rate": 0.00023465346534653464,
|
| 167 |
+
"loss": 3.2929,
|
| 168 |
+
"step": 25
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.76,
|
| 172 |
+
"learning_rate": 0.00023168316831683166,
|
| 173 |
+
"loss": 3.2983,
|
| 174 |
+
"step": 26
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.79,
|
| 178 |
+
"learning_rate": 0.00022871287128712868,
|
| 179 |
+
"loss": 3.2625,
|
| 180 |
+
"step": 27
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.82,
|
| 184 |
+
"learning_rate": 0.00022574257425742573,
|
| 185 |
+
"loss": 3.3042,
|
| 186 |
+
"step": 28
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.85,
|
| 190 |
+
"learning_rate": 0.00022277227722772275,
|
| 191 |
+
"loss": 3.2494,
|
| 192 |
+
"step": 29
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.88,
|
| 196 |
+
"learning_rate": 0.00021980198019801977,
|
| 197 |
+
"loss": 3.231,
|
| 198 |
+
"step": 30
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.91,
|
| 202 |
+
"learning_rate": 0.0002168316831683168,
|
| 203 |
+
"loss": 3.2249,
|
| 204 |
+
"step": 31
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.94,
|
| 208 |
+
"learning_rate": 0.00021386138613861385,
|
| 209 |
+
"loss": 3.2355,
|
| 210 |
+
"step": 32
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.97,
|
| 214 |
+
"learning_rate": 0.00021089108910891087,
|
| 215 |
+
"loss": 3.1952,
|
| 216 |
+
"step": 33
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.0,
|
| 220 |
+
"learning_rate": 0.0002079207920792079,
|
| 221 |
+
"loss": 3.1892,
|
| 222 |
+
"step": 34
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.03,
|
| 226 |
+
"learning_rate": 0.00020495049504950494,
|
| 227 |
+
"loss": 3.1875,
|
| 228 |
+
"step": 35
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.06,
|
| 232 |
+
"learning_rate": 0.00020198019801980199,
|
| 233 |
+
"loss": 3.1733,
|
| 234 |
+
"step": 36
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.09,
|
| 238 |
+
"learning_rate": 0.000199009900990099,
|
| 239 |
+
"loss": 3.2136,
|
| 240 |
+
"step": 37
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.12,
|
| 244 |
+
"learning_rate": 0.00019603960396039603,
|
| 245 |
+
"loss": 3.1819,
|
| 246 |
+
"step": 38
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.15,
|
| 250 |
+
"learning_rate": 0.00019306930693069305,
|
| 251 |
+
"loss": 3.1764,
|
| 252 |
+
"step": 39
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.18,
|
| 256 |
+
"learning_rate": 0.00019009900990099007,
|
| 257 |
+
"loss": 3.1713,
|
| 258 |
+
"step": 40
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.18,
|
| 262 |
+
"eval_cer": 1.0,
|
| 263 |
+
"eval_loss": 3.1816344261169434,
|
| 264 |
+
"eval_runtime": 36.1118,
|
| 265 |
+
"eval_samples_per_second": 14.178,
|
| 266 |
+
"eval_steps_per_second": 0.886,
|
| 267 |
+
"eval_wer": 1.0,
|
| 268 |
+
"step": 40
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.21,
|
| 272 |
+
"learning_rate": 0.00018712871287128712,
|
| 273 |
+
"loss": 3.176,
|
| 274 |
+
"step": 41
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.24,
|
| 278 |
+
"learning_rate": 0.00018415841584158414,
|
| 279 |
+
"loss": 3.1669,
|
| 280 |
+
"step": 42
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.26,
|
| 284 |
+
"learning_rate": 0.00018118811881188116,
|
| 285 |
+
"loss": 3.1446,
|
| 286 |
+
"step": 43
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.29,
|
| 290 |
+
"learning_rate": 0.00017821782178217819,
|
| 291 |
+
"loss": 3.1556,
|
| 292 |
+
"step": 44
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.32,
|
| 296 |
+
"learning_rate": 0.0001752475247524752,
|
| 297 |
+
"loss": 3.1447,
|
| 298 |
+
"step": 45
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.35,
|
| 302 |
+
"learning_rate": 0.00017227722772277226,
|
| 303 |
+
"loss": 3.1412,
|
| 304 |
+
"step": 46
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.38,
|
| 308 |
+
"learning_rate": 0.00016930693069306928,
|
| 309 |
+
"loss": 3.1521,
|
| 310 |
+
"step": 47
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.41,
|
| 314 |
+
"learning_rate": 0.00016633663366336633,
|
| 315 |
+
"loss": 3.1493,
|
| 316 |
+
"step": 48
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.44,
|
| 320 |
+
"learning_rate": 0.00016336633663366338,
|
| 321 |
+
"loss": 3.1494,
|
| 322 |
+
"step": 49
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 1.47,
|
| 326 |
+
"learning_rate": 0.0001603960396039604,
|
| 327 |
+
"loss": 3.1419,
|
| 328 |
+
"step": 50
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 1.5,
|
| 332 |
+
"learning_rate": 0.00015742574257425742,
|
| 333 |
+
"loss": 3.1407,
|
| 334 |
+
"step": 51
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 1.53,
|
| 338 |
+
"learning_rate": 0.00015445544554455444,
|
| 339 |
+
"loss": 3.1456,
|
| 340 |
+
"step": 52
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.56,
|
| 344 |
+
"learning_rate": 0.00015148514851485146,
|
| 345 |
+
"loss": 3.1317,
|
| 346 |
+
"step": 53
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.59,
|
| 350 |
+
"learning_rate": 0.0001485148514851485,
|
| 351 |
+
"loss": 3.1369,
|
| 352 |
+
"step": 54
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.62,
|
| 356 |
+
"learning_rate": 0.00014554455445544553,
|
| 357 |
+
"loss": 3.1547,
|
| 358 |
+
"step": 55
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.65,
|
| 362 |
+
"learning_rate": 0.00014257425742574255,
|
| 363 |
+
"loss": 3.1356,
|
| 364 |
+
"step": 56
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.68,
|
| 368 |
+
"learning_rate": 0.0001396039603960396,
|
| 369 |
+
"loss": 3.1538,
|
| 370 |
+
"step": 57
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.71,
|
| 374 |
+
"learning_rate": 0.00013663366336633662,
|
| 375 |
+
"loss": 3.1549,
|
| 376 |
+
"step": 58
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 1.74,
|
| 380 |
+
"learning_rate": 0.00013366336633663365,
|
| 381 |
+
"loss": 3.1275,
|
| 382 |
+
"step": 59
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.76,
|
| 386 |
+
"learning_rate": 0.00013069306930693067,
|
| 387 |
+
"loss": 3.134,
|
| 388 |
+
"step": 60
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.76,
|
| 392 |
+
"eval_cer": 1.0,
|
| 393 |
+
"eval_loss": 3.153820276260376,
|
| 394 |
+
"eval_runtime": 36.2824,
|
| 395 |
+
"eval_samples_per_second": 14.112,
|
| 396 |
+
"eval_steps_per_second": 0.882,
|
| 397 |
+
"eval_wer": 1.0,
|
| 398 |
+
"step": 60
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.79,
|
| 402 |
+
"learning_rate": 0.00012772277227722772,
|
| 403 |
+
"loss": 3.1667,
|
| 404 |
+
"step": 61
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.82,
|
| 408 |
+
"learning_rate": 0.00012475247524752474,
|
| 409 |
+
"loss": 3.1346,
|
| 410 |
+
"step": 62
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.85,
|
| 414 |
+
"learning_rate": 0.00012178217821782177,
|
| 415 |
+
"loss": 3.1247,
|
| 416 |
+
"step": 63
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.88,
|
| 420 |
+
"learning_rate": 0.00011881188118811881,
|
| 421 |
+
"loss": 3.1358,
|
| 422 |
+
"step": 64
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.91,
|
| 426 |
+
"learning_rate": 0.00011584158415841583,
|
| 427 |
+
"loss": 3.1382,
|
| 428 |
+
"step": 65
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.94,
|
| 432 |
+
"learning_rate": 0.00011287128712871287,
|
| 433 |
+
"loss": 3.1455,
|
| 434 |
+
"step": 66
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.97,
|
| 438 |
+
"learning_rate": 0.00010990099009900989,
|
| 439 |
+
"loss": 3.1397,
|
| 440 |
+
"step": 67
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.0,
|
| 444 |
+
"learning_rate": 0.00010693069306930692,
|
| 445 |
+
"loss": 3.1402,
|
| 446 |
+
"step": 68
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.03,
|
| 450 |
+
"learning_rate": 0.00010396039603960394,
|
| 451 |
+
"loss": 3.1163,
|
| 452 |
+
"step": 69
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.06,
|
| 456 |
+
"learning_rate": 0.00010099009900990099,
|
| 457 |
+
"loss": 3.1175,
|
| 458 |
+
"step": 70
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.09,
|
| 462 |
+
"learning_rate": 9.801980198019801e-05,
|
| 463 |
+
"loss": 3.1169,
|
| 464 |
+
"step": 71
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.12,
|
| 468 |
+
"learning_rate": 9.504950495049504e-05,
|
| 469 |
+
"loss": 3.1242,
|
| 470 |
+
"step": 72
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 2.15,
|
| 474 |
+
"learning_rate": 9.207920792079207e-05,
|
| 475 |
+
"loss": 3.1326,
|
| 476 |
+
"step": 73
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 2.18,
|
| 480 |
+
"learning_rate": 8.910891089108909e-05,
|
| 481 |
+
"loss": 3.1394,
|
| 482 |
+
"step": 74
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 2.21,
|
| 486 |
+
"learning_rate": 8.613861386138613e-05,
|
| 487 |
+
"loss": 3.1369,
|
| 488 |
+
"step": 75
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.24,
|
| 492 |
+
"learning_rate": 8.316831683168316e-05,
|
| 493 |
+
"loss": 3.1284,
|
| 494 |
+
"step": 76
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.26,
|
| 498 |
+
"learning_rate": 8.01980198019802e-05,
|
| 499 |
+
"loss": 3.1203,
|
| 500 |
+
"step": 77
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 2.29,
|
| 504 |
+
"learning_rate": 7.722772277227722e-05,
|
| 505 |
+
"loss": 3.1245,
|
| 506 |
+
"step": 78
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.32,
|
| 510 |
+
"learning_rate": 7.425742574257426e-05,
|
| 511 |
+
"loss": 3.1243,
|
| 512 |
+
"step": 79
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 2.35,
|
| 516 |
+
"learning_rate": 7.128712871287128e-05,
|
| 517 |
+
"loss": 3.132,
|
| 518 |
+
"step": 80
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.35,
|
| 522 |
+
"eval_cer": 1.0,
|
| 523 |
+
"eval_loss": 3.1410903930664062,
|
| 524 |
+
"eval_runtime": 36.0623,
|
| 525 |
+
"eval_samples_per_second": 14.198,
|
| 526 |
+
"eval_steps_per_second": 0.887,
|
| 527 |
+
"eval_wer": 1.0,
|
| 528 |
+
"step": 80
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 2.38,
|
| 532 |
+
"learning_rate": 6.831683168316831e-05,
|
| 533 |
+
"loss": 3.1249,
|
| 534 |
+
"step": 81
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.41,
|
| 538 |
+
"learning_rate": 6.534653465346533e-05,
|
| 539 |
+
"loss": 3.1271,
|
| 540 |
+
"step": 82
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 2.44,
|
| 544 |
+
"learning_rate": 6.237623762376237e-05,
|
| 545 |
+
"loss": 3.1245,
|
| 546 |
+
"step": 83
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 2.47,
|
| 550 |
+
"learning_rate": 5.9405940594059404e-05,
|
| 551 |
+
"loss": 3.1242,
|
| 552 |
+
"step": 84
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 2.5,
|
| 556 |
+
"learning_rate": 5.643564356435643e-05,
|
| 557 |
+
"loss": 3.126,
|
| 558 |
+
"step": 85
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 2.53,
|
| 562 |
+
"learning_rate": 5.346534653465346e-05,
|
| 563 |
+
"loss": 3.1327,
|
| 564 |
+
"step": 86
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.56,
|
| 568 |
+
"learning_rate": 5.0495049504950497e-05,
|
| 569 |
+
"loss": 3.1214,
|
| 570 |
+
"step": 87
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 2.59,
|
| 574 |
+
"learning_rate": 4.752475247524752e-05,
|
| 575 |
+
"loss": 3.1513,
|
| 576 |
+
"step": 88
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 2.62,
|
| 580 |
+
"learning_rate": 4.4554455445544547e-05,
|
| 581 |
+
"loss": 3.128,
|
| 582 |
+
"step": 89
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 2.65,
|
| 586 |
+
"learning_rate": 4.158415841584158e-05,
|
| 587 |
+
"loss": 3.1243,
|
| 588 |
+
"step": 90
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 2.68,
|
| 592 |
+
"learning_rate": 3.861386138613861e-05,
|
| 593 |
+
"loss": 3.1342,
|
| 594 |
+
"step": 91
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 2.71,
|
| 598 |
+
"learning_rate": 3.564356435643564e-05,
|
| 599 |
+
"loss": 3.1474,
|
| 600 |
+
"step": 92
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 2.74,
|
| 604 |
+
"learning_rate": 3.267326732673267e-05,
|
| 605 |
+
"loss": 3.1259,
|
| 606 |
+
"step": 93
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.76,
|
| 610 |
+
"learning_rate": 2.9702970297029702e-05,
|
| 611 |
+
"loss": 3.1205,
|
| 612 |
+
"step": 94
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 2.79,
|
| 616 |
+
"learning_rate": 2.673267326732673e-05,
|
| 617 |
+
"loss": 3.1273,
|
| 618 |
+
"step": 95
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 2.82,
|
| 622 |
+
"learning_rate": 2.376237623762376e-05,
|
| 623 |
+
"loss": 3.1177,
|
| 624 |
+
"step": 96
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 2.85,
|
| 628 |
+
"learning_rate": 2.079207920792079e-05,
|
| 629 |
+
"loss": 3.1179,
|
| 630 |
+
"step": 97
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 2.88,
|
| 634 |
+
"learning_rate": 1.782178217821782e-05,
|
| 635 |
+
"loss": 3.1272,
|
| 636 |
+
"step": 98
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 2.91,
|
| 640 |
+
"learning_rate": 1.4851485148514851e-05,
|
| 641 |
+
"loss": 3.1404,
|
| 642 |
+
"step": 99
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.94,
|
| 646 |
+
"learning_rate": 1.188118811881188e-05,
|
| 647 |
+
"loss": 3.1295,
|
| 648 |
+
"step": 100
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.94,
|
| 652 |
+
"eval_cer": 1.0,
|
| 653 |
+
"eval_loss": 3.1372523307800293,
|
| 654 |
+
"eval_runtime": 36.088,
|
| 655 |
+
"eval_samples_per_second": 14.188,
|
| 656 |
+
"eval_steps_per_second": 0.887,
|
| 657 |
+
"eval_wer": 1.0,
|
| 658 |
+
"step": 100
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 2.97,
|
| 662 |
+
"learning_rate": 8.91089108910891e-06,
|
| 663 |
+
"loss": 3.1441,
|
| 664 |
+
"step": 101
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 3.0,
|
| 668 |
+
"learning_rate": 5.94059405940594e-06,
|
| 669 |
+
"loss": 3.1193,
|
| 670 |
+
"step": 102
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 3.0,
|
| 674 |
+
"step": 102,
|
| 675 |
+
"total_flos": 3.102653790168285e+18,
|
| 676 |
+
"train_loss": 3.6673195455588545,
|
| 677 |
+
"train_runtime": 1011.7717,
|
| 678 |
+
"train_samples_per_second": 6.443,
|
| 679 |
+
"train_steps_per_second": 0.101
|
| 680 |
+
}
|
| 681 |
+
],
|
| 682 |
+
"max_steps": 102,
|
| 683 |
+
"num_train_epochs": 3,
|
| 684 |
+
"total_flos": 3.102653790168285e+18,
|
| 685 |
+
"trial_name": null,
|
| 686 |
+
"trial_params": null
|
| 687 |
+
}
|