End of training
Browse files- all_results.json +14 -0
- eval_results.json +9 -0
- pytorch_model.bin +1 -1
- train_results.json +8 -0
- trainer_state.json +772 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 0.811100959777832,
|
| 4 |
+
"eval_runtime": 116.9266,
|
| 5 |
+
"eval_samples": 2693,
|
| 6 |
+
"eval_samples_per_second": 23.032,
|
| 7 |
+
"eval_steps_per_second": 2.882,
|
| 8 |
+
"eval_wer": 0.5176790989660266,
|
| 9 |
+
"train_loss": 1.853262206161578,
|
| 10 |
+
"train_runtime": 19140.1846,
|
| 11 |
+
"train_samples": 6176,
|
| 12 |
+
"train_samples_per_second": 16.134,
|
| 13 |
+
"train_steps_per_second": 0.504
|
| 14 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"eval_loss": 0.811100959777832,
|
| 4 |
+
"eval_runtime": 116.9266,
|
| 5 |
+
"eval_samples": 2693,
|
| 6 |
+
"eval_samples_per_second": 23.032,
|
| 7 |
+
"eval_steps_per_second": 2.882,
|
| 8 |
+
"eval_wer": 0.5176790989660266
|
| 9 |
+
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262333681
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c57a99610a4cbc4d0f130bded24e62cd471aeabc5e214d5e46e530e11a9c7d9
|
| 3 |
size 1262333681
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 50.0,
|
| 3 |
+
"train_loss": 1.853262206161578,
|
| 4 |
+
"train_runtime": 19140.1846,
|
| 5 |
+
"train_samples": 6176,
|
| 6 |
+
"train_samples_per_second": 16.134,
|
| 7 |
+
"train_steps_per_second": 0.504
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,772 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 50.0,
|
| 5 |
+
"global_step": 9650,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.52,
|
| 12 |
+
"learning_rate": 3.7125e-06,
|
| 13 |
+
"loss": 19.5412,
|
| 14 |
+
"step": 100
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.04,
|
| 18 |
+
"learning_rate": 7.4625e-06,
|
| 19 |
+
"loss": 11.0922,
|
| 20 |
+
"step": 200
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 1.55,
|
| 24 |
+
"learning_rate": 1.1212499999999998e-05,
|
| 25 |
+
"loss": 7.1984,
|
| 26 |
+
"step": 300
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 2.07,
|
| 30 |
+
"learning_rate": 1.49625e-05,
|
| 31 |
+
"loss": 5.9337,
|
| 32 |
+
"step": 400
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.59,
|
| 36 |
+
"learning_rate": 1.8712499999999997e-05,
|
| 37 |
+
"loss": 4.9733,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.59,
|
| 42 |
+
"eval_loss": 5.06973934173584,
|
| 43 |
+
"eval_runtime": 115.8922,
|
| 44 |
+
"eval_samples_per_second": 23.237,
|
| 45 |
+
"eval_steps_per_second": 2.908,
|
| 46 |
+
"eval_wer": 1.0,
|
| 47 |
+
"step": 500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 3.11,
|
| 51 |
+
"learning_rate": 2.2462499999999997e-05,
|
| 52 |
+
"loss": 4.2014,
|
| 53 |
+
"step": 600
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.63,
|
| 57 |
+
"learning_rate": 2.6212499999999997e-05,
|
| 58 |
+
"loss": 3.704,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.15,
|
| 63 |
+
"learning_rate": 2.99625e-05,
|
| 64 |
+
"loss": 3.5005,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 4.66,
|
| 69 |
+
"learning_rate": 3.37125e-05,
|
| 70 |
+
"loss": 3.4424,
|
| 71 |
+
"step": 900
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.18,
|
| 75 |
+
"learning_rate": 3.7462499999999996e-05,
|
| 76 |
+
"loss": 3.3839,
|
| 77 |
+
"step": 1000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 5.18,
|
| 81 |
+
"eval_loss": 3.3517656326293945,
|
| 82 |
+
"eval_runtime": 115.48,
|
| 83 |
+
"eval_samples_per_second": 23.32,
|
| 84 |
+
"eval_steps_per_second": 2.918,
|
| 85 |
+
"eval_wer": 1.0,
|
| 86 |
+
"step": 1000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 5.7,
|
| 90 |
+
"learning_rate": 4.12125e-05,
|
| 91 |
+
"loss": 3.3036,
|
| 92 |
+
"step": 1100
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 6.22,
|
| 96 |
+
"learning_rate": 4.4962499999999995e-05,
|
| 97 |
+
"loss": 3.2565,
|
| 98 |
+
"step": 1200
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.74,
|
| 102 |
+
"learning_rate": 4.871249999999999e-05,
|
| 103 |
+
"loss": 2.9583,
|
| 104 |
+
"step": 1300
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.25,
|
| 108 |
+
"learning_rate": 5.2462499999999994e-05,
|
| 109 |
+
"loss": 2.3824,
|
| 110 |
+
"step": 1400
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 7.77,
|
| 114 |
+
"learning_rate": 5.62125e-05,
|
| 115 |
+
"loss": 2.0596,
|
| 116 |
+
"step": 1500
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 7.77,
|
| 120 |
+
"eval_loss": 1.3991833925247192,
|
| 121 |
+
"eval_runtime": 116.0149,
|
| 122 |
+
"eval_samples_per_second": 23.213,
|
| 123 |
+
"eval_steps_per_second": 2.905,
|
| 124 |
+
"eval_wer": 0.7869276218611522,
|
| 125 |
+
"step": 1500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 8.29,
|
| 129 |
+
"learning_rate": 5.9962499999999994e-05,
|
| 130 |
+
"loss": 1.9024,
|
| 131 |
+
"step": 1600
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 8.81,
|
| 135 |
+
"learning_rate": 6.37125e-05,
|
| 136 |
+
"loss": 1.7879,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 9.33,
|
| 141 |
+
"learning_rate": 6.746249999999999e-05,
|
| 142 |
+
"loss": 1.7072,
|
| 143 |
+
"step": 1800
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 9.84,
|
| 147 |
+
"learning_rate": 7.121249999999999e-05,
|
| 148 |
+
"loss": 1.6689,
|
| 149 |
+
"step": 1900
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 10.36,
|
| 153 |
+
"learning_rate": 7.49625e-05,
|
| 154 |
+
"loss": 1.6102,
|
| 155 |
+
"step": 2000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 10.36,
|
| 159 |
+
"eval_loss": 1.0711737871170044,
|
| 160 |
+
"eval_runtime": 115.3994,
|
| 161 |
+
"eval_samples_per_second": 23.336,
|
| 162 |
+
"eval_steps_per_second": 2.92,
|
| 163 |
+
"eval_wer": 0.6754062038404727,
|
| 164 |
+
"step": 2000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 10.88,
|
| 168 |
+
"learning_rate": 7.40392156862745e-05,
|
| 169 |
+
"loss": 1.5881,
|
| 170 |
+
"step": 2100
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 11.4,
|
| 174 |
+
"learning_rate": 7.305882352941176e-05,
|
| 175 |
+
"loss": 1.5371,
|
| 176 |
+
"step": 2200
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 11.92,
|
| 180 |
+
"learning_rate": 7.208823529411764e-05,
|
| 181 |
+
"loss": 1.5062,
|
| 182 |
+
"step": 2300
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 12.44,
|
| 186 |
+
"learning_rate": 7.11078431372549e-05,
|
| 187 |
+
"loss": 1.4704,
|
| 188 |
+
"step": 2400
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 12.95,
|
| 192 |
+
"learning_rate": 7.012745098039215e-05,
|
| 193 |
+
"loss": 1.4587,
|
| 194 |
+
"step": 2500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 12.95,
|
| 198 |
+
"eval_loss": 0.9280298352241516,
|
| 199 |
+
"eval_runtime": 115.6447,
|
| 200 |
+
"eval_samples_per_second": 23.287,
|
| 201 |
+
"eval_steps_per_second": 2.914,
|
| 202 |
+
"eval_wer": 0.6361244460856721,
|
| 203 |
+
"step": 2500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 13.47,
|
| 207 |
+
"learning_rate": 6.91470588235294e-05,
|
| 208 |
+
"loss": 1.4201,
|
| 209 |
+
"step": 2600
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 13.99,
|
| 213 |
+
"learning_rate": 6.81764705882353e-05,
|
| 214 |
+
"loss": 1.4221,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 14.51,
|
| 219 |
+
"learning_rate": 6.719607843137255e-05,
|
| 220 |
+
"loss": 1.3937,
|
| 221 |
+
"step": 2800
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 15.03,
|
| 225 |
+
"learning_rate": 6.62156862745098e-05,
|
| 226 |
+
"loss": 1.3984,
|
| 227 |
+
"step": 2900
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 15.54,
|
| 231 |
+
"learning_rate": 6.523529411764705e-05,
|
| 232 |
+
"loss": 1.3667,
|
| 233 |
+
"step": 3000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.54,
|
| 237 |
+
"eval_loss": 0.9280989766120911,
|
| 238 |
+
"eval_runtime": 115.1284,
|
| 239 |
+
"eval_samples_per_second": 23.391,
|
| 240 |
+
"eval_steps_per_second": 2.927,
|
| 241 |
+
"eval_wer": 0.6155372968980798,
|
| 242 |
+
"step": 3000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 16.06,
|
| 246 |
+
"learning_rate": 6.425490196078431e-05,
|
| 247 |
+
"loss": 1.367,
|
| 248 |
+
"step": 3100
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 16.58,
|
| 252 |
+
"learning_rate": 6.327450980392156e-05,
|
| 253 |
+
"loss": 1.3535,
|
| 254 |
+
"step": 3200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 17.1,
|
| 258 |
+
"learning_rate": 6.229411764705881e-05,
|
| 259 |
+
"loss": 1.3265,
|
| 260 |
+
"step": 3300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 17.62,
|
| 264 |
+
"learning_rate": 6.131372549019608e-05,
|
| 265 |
+
"loss": 1.3202,
|
| 266 |
+
"step": 3400
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 18.13,
|
| 270 |
+
"learning_rate": 6.033333333333333e-05,
|
| 271 |
+
"loss": 1.3042,
|
| 272 |
+
"step": 3500
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 18.13,
|
| 276 |
+
"eval_loss": 0.9037219882011414,
|
| 277 |
+
"eval_runtime": 114.717,
|
| 278 |
+
"eval_samples_per_second": 23.475,
|
| 279 |
+
"eval_steps_per_second": 2.938,
|
| 280 |
+
"eval_wer": 0.5921344165435746,
|
| 281 |
+
"step": 3500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 18.65,
|
| 285 |
+
"learning_rate": 5.9352941176470584e-05,
|
| 286 |
+
"loss": 1.3016,
|
| 287 |
+
"step": 3600
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 19.17,
|
| 291 |
+
"learning_rate": 5.837254901960784e-05,
|
| 292 |
+
"loss": 1.2862,
|
| 293 |
+
"step": 3700
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 19.69,
|
| 297 |
+
"learning_rate": 5.739215686274509e-05,
|
| 298 |
+
"loss": 1.2773,
|
| 299 |
+
"step": 3800
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 20.21,
|
| 303 |
+
"learning_rate": 5.641176470588235e-05,
|
| 304 |
+
"loss": 1.2543,
|
| 305 |
+
"step": 3900
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 20.73,
|
| 309 |
+
"learning_rate": 5.54313725490196e-05,
|
| 310 |
+
"loss": 1.2544,
|
| 311 |
+
"step": 4000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 20.73,
|
| 315 |
+
"eval_loss": 0.8996412754058838,
|
| 316 |
+
"eval_runtime": 115.5118,
|
| 317 |
+
"eval_samples_per_second": 23.314,
|
| 318 |
+
"eval_steps_per_second": 2.917,
|
| 319 |
+
"eval_wer": 0.5824409158050221,
|
| 320 |
+
"step": 4000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 21.24,
|
| 324 |
+
"learning_rate": 5.445098039215686e-05,
|
| 325 |
+
"loss": 1.2419,
|
| 326 |
+
"step": 4100
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 21.76,
|
| 330 |
+
"learning_rate": 5.347058823529411e-05,
|
| 331 |
+
"loss": 1.2347,
|
| 332 |
+
"step": 4200
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 22.28,
|
| 336 |
+
"learning_rate": 5.2490196078431365e-05,
|
| 337 |
+
"loss": 1.2373,
|
| 338 |
+
"step": 4300
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 22.8,
|
| 342 |
+
"learning_rate": 5.150980392156863e-05,
|
| 343 |
+
"loss": 1.2337,
|
| 344 |
+
"step": 4400
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 23.32,
|
| 348 |
+
"learning_rate": 5.052941176470588e-05,
|
| 349 |
+
"loss": 1.2274,
|
| 350 |
+
"step": 4500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 23.32,
|
| 354 |
+
"eval_loss": 0.8933804631233215,
|
| 355 |
+
"eval_runtime": 115.4101,
|
| 356 |
+
"eval_samples_per_second": 23.334,
|
| 357 |
+
"eval_steps_per_second": 2.92,
|
| 358 |
+
"eval_wer": 0.5797175036927622,
|
| 359 |
+
"step": 4500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 23.83,
|
| 363 |
+
"learning_rate": 4.9549019607843137e-05,
|
| 364 |
+
"loss": 1.2091,
|
| 365 |
+
"step": 4600
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 24.35,
|
| 369 |
+
"learning_rate": 4.856862745098039e-05,
|
| 370 |
+
"loss": 1.1947,
|
| 371 |
+
"step": 4700
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 24.87,
|
| 375 |
+
"learning_rate": 4.759803921568627e-05,
|
| 376 |
+
"loss": 1.1901,
|
| 377 |
+
"step": 4800
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 25.39,
|
| 381 |
+
"learning_rate": 4.6617647058823525e-05,
|
| 382 |
+
"loss": 1.1731,
|
| 383 |
+
"step": 4900
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 25.91,
|
| 387 |
+
"learning_rate": 4.5637254901960776e-05,
|
| 388 |
+
"loss": 1.1763,
|
| 389 |
+
"step": 5000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 25.91,
|
| 393 |
+
"eval_loss": 0.8642701506614685,
|
| 394 |
+
"eval_runtime": 115.2886,
|
| 395 |
+
"eval_samples_per_second": 23.359,
|
| 396 |
+
"eval_steps_per_second": 2.923,
|
| 397 |
+
"eval_wer": 0.5759785819793205,
|
| 398 |
+
"step": 5000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 26.42,
|
| 402 |
+
"learning_rate": 4.465686274509803e-05,
|
| 403 |
+
"loss": 1.1661,
|
| 404 |
+
"step": 5100
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 26.94,
|
| 408 |
+
"learning_rate": 4.367647058823529e-05,
|
| 409 |
+
"loss": 1.1628,
|
| 410 |
+
"step": 5200
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 27.46,
|
| 414 |
+
"learning_rate": 4.269607843137254e-05,
|
| 415 |
+
"loss": 1.1618,
|
| 416 |
+
"step": 5300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 27.98,
|
| 420 |
+
"learning_rate": 4.1715686274509805e-05,
|
| 421 |
+
"loss": 1.1468,
|
| 422 |
+
"step": 5400
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 28.5,
|
| 426 |
+
"learning_rate": 4.0735294117647055e-05,
|
| 427 |
+
"loss": 1.149,
|
| 428 |
+
"step": 5500
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 28.5,
|
| 432 |
+
"eval_loss": 0.8251490592956543,
|
| 433 |
+
"eval_runtime": 116.3124,
|
| 434 |
+
"eval_samples_per_second": 23.153,
|
| 435 |
+
"eval_steps_per_second": 2.897,
|
| 436 |
+
"eval_wer": 0.5543759231905465,
|
| 437 |
+
"step": 5500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 29.02,
|
| 441 |
+
"learning_rate": 3.975490196078431e-05,
|
| 442 |
+
"loss": 1.1572,
|
| 443 |
+
"step": 5600
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 29.53,
|
| 447 |
+
"learning_rate": 3.877450980392157e-05,
|
| 448 |
+
"loss": 1.1389,
|
| 449 |
+
"step": 5700
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 30.05,
|
| 453 |
+
"learning_rate": 3.779411764705882e-05,
|
| 454 |
+
"loss": 1.1337,
|
| 455 |
+
"step": 5800
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 30.57,
|
| 459 |
+
"learning_rate": 3.681372549019607e-05,
|
| 460 |
+
"loss": 1.1226,
|
| 461 |
+
"step": 5900
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 31.09,
|
| 465 |
+
"learning_rate": 3.5833333333333335e-05,
|
| 466 |
+
"loss": 1.1207,
|
| 467 |
+
"step": 6000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 31.09,
|
| 471 |
+
"eval_loss": 0.8505932092666626,
|
| 472 |
+
"eval_runtime": 115.2841,
|
| 473 |
+
"eval_samples_per_second": 23.36,
|
| 474 |
+
"eval_steps_per_second": 2.923,
|
| 475 |
+
"eval_wer": 0.5527141802067946,
|
| 476 |
+
"step": 6000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 31.61,
|
| 480 |
+
"learning_rate": 3.4852941176470585e-05,
|
| 481 |
+
"loss": 1.1243,
|
| 482 |
+
"step": 6100
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 32.12,
|
| 486 |
+
"learning_rate": 3.387254901960784e-05,
|
| 487 |
+
"loss": 1.1156,
|
| 488 |
+
"step": 6200
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 32.64,
|
| 492 |
+
"learning_rate": 3.289215686274509e-05,
|
| 493 |
+
"loss": 1.1158,
|
| 494 |
+
"step": 6300
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 33.16,
|
| 498 |
+
"learning_rate": 3.191176470588235e-05,
|
| 499 |
+
"loss": 1.0918,
|
| 500 |
+
"step": 6400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 33.68,
|
| 504 |
+
"learning_rate": 3.09313725490196e-05,
|
| 505 |
+
"loss": 1.091,
|
| 506 |
+
"step": 6500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 33.68,
|
| 510 |
+
"eval_loss": 0.8370497822761536,
|
| 511 |
+
"eval_runtime": 115.5394,
|
| 512 |
+
"eval_samples_per_second": 23.308,
|
| 513 |
+
"eval_steps_per_second": 2.917,
|
| 514 |
+
"eval_wer": 0.5365583456425406,
|
| 515 |
+
"step": 6500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 34.2,
|
| 519 |
+
"learning_rate": 2.995098039215686e-05,
|
| 520 |
+
"loss": 1.0892,
|
| 521 |
+
"step": 6600
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 34.72,
|
| 525 |
+
"learning_rate": 2.8980392156862746e-05,
|
| 526 |
+
"loss": 1.0799,
|
| 527 |
+
"step": 6700
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 35.23,
|
| 531 |
+
"learning_rate": 2.8e-05,
|
| 532 |
+
"loss": 1.0671,
|
| 533 |
+
"step": 6800
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 35.75,
|
| 537 |
+
"learning_rate": 2.7019607843137253e-05,
|
| 538 |
+
"loss": 1.07,
|
| 539 |
+
"step": 6900
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 36.27,
|
| 543 |
+
"learning_rate": 2.6049019607843135e-05,
|
| 544 |
+
"loss": 1.0613,
|
| 545 |
+
"step": 7000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 36.27,
|
| 549 |
+
"eval_loss": 0.8345041275024414,
|
| 550 |
+
"eval_runtime": 116.5707,
|
| 551 |
+
"eval_samples_per_second": 23.102,
|
| 552 |
+
"eval_steps_per_second": 2.891,
|
| 553 |
+
"eval_wer": 0.5351735598227474,
|
| 554 |
+
"step": 7000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 36.79,
|
| 558 |
+
"learning_rate": 2.506862745098039e-05,
|
| 559 |
+
"loss": 1.0797,
|
| 560 |
+
"step": 7100
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 37.31,
|
| 564 |
+
"learning_rate": 2.4088235294117646e-05,
|
| 565 |
+
"loss": 1.0787,
|
| 566 |
+
"step": 7200
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 37.82,
|
| 570 |
+
"learning_rate": 2.31078431372549e-05,
|
| 571 |
+
"loss": 1.0706,
|
| 572 |
+
"step": 7300
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 38.34,
|
| 576 |
+
"learning_rate": 2.2127450980392153e-05,
|
| 577 |
+
"loss": 1.0585,
|
| 578 |
+
"step": 7400
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 38.86,
|
| 582 |
+
"learning_rate": 2.114705882352941e-05,
|
| 583 |
+
"loss": 1.0495,
|
| 584 |
+
"step": 7500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 38.86,
|
| 588 |
+
"eval_loss": 0.8380374908447266,
|
| 589 |
+
"eval_runtime": 115.7848,
|
| 590 |
+
"eval_samples_per_second": 23.259,
|
| 591 |
+
"eval_steps_per_second": 2.911,
|
| 592 |
+
"eval_wer": 0.5321270310192023,
|
| 593 |
+
"step": 7500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 39.38,
|
| 597 |
+
"learning_rate": 2.0166666666666664e-05,
|
| 598 |
+
"loss": 1.0456,
|
| 599 |
+
"step": 7600
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 39.9,
|
| 603 |
+
"learning_rate": 1.9186274509803922e-05,
|
| 604 |
+
"loss": 1.0446,
|
| 605 |
+
"step": 7700
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 40.41,
|
| 609 |
+
"learning_rate": 1.8205882352941176e-05,
|
| 610 |
+
"loss": 1.0353,
|
| 611 |
+
"step": 7800
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 40.93,
|
| 615 |
+
"learning_rate": 1.722549019607843e-05,
|
| 616 |
+
"loss": 1.0375,
|
| 617 |
+
"step": 7900
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 41.45,
|
| 621 |
+
"learning_rate": 1.6245098039215687e-05,
|
| 622 |
+
"loss": 1.0345,
|
| 623 |
+
"step": 8000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 41.45,
|
| 627 |
+
"eval_loss": 0.828546941280365,
|
| 628 |
+
"eval_runtime": 115.0908,
|
| 629 |
+
"eval_samples_per_second": 23.399,
|
| 630 |
+
"eval_steps_per_second": 2.928,
|
| 631 |
+
"eval_wer": 0.5269110044313147,
|
| 632 |
+
"step": 8000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 41.97,
|
| 636 |
+
"learning_rate": 1.526470588235294e-05,
|
| 637 |
+
"loss": 1.0196,
|
| 638 |
+
"step": 8100
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 42.49,
|
| 642 |
+
"learning_rate": 1.4284313725490196e-05,
|
| 643 |
+
"loss": 1.0265,
|
| 644 |
+
"step": 8200
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 43.01,
|
| 648 |
+
"learning_rate": 1.330392156862745e-05,
|
| 649 |
+
"loss": 1.028,
|
| 650 |
+
"step": 8300
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 43.52,
|
| 654 |
+
"learning_rate": 1.2323529411764704e-05,
|
| 655 |
+
"loss": 1.0281,
|
| 656 |
+
"step": 8400
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 44.04,
|
| 660 |
+
"learning_rate": 1.1343137254901961e-05,
|
| 661 |
+
"loss": 1.0297,
|
| 662 |
+
"step": 8500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 44.04,
|
| 666 |
+
"eval_loss": 0.7836087346076965,
|
| 667 |
+
"eval_runtime": 116.6272,
|
| 668 |
+
"eval_samples_per_second": 23.091,
|
| 669 |
+
"eval_steps_per_second": 2.89,
|
| 670 |
+
"eval_wer": 0.5141248153618907,
|
| 671 |
+
"step": 8500
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 44.56,
|
| 675 |
+
"learning_rate": 1.0362745098039215e-05,
|
| 676 |
+
"loss": 1.0097,
|
| 677 |
+
"step": 8600
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 45.08,
|
| 681 |
+
"learning_rate": 9.382352941176469e-06,
|
| 682 |
+
"loss": 1.0046,
|
| 683 |
+
"step": 8700
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 45.6,
|
| 687 |
+
"learning_rate": 8.401960784313724e-06,
|
| 688 |
+
"loss": 1.0082,
|
| 689 |
+
"step": 8800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 46.11,
|
| 693 |
+
"learning_rate": 7.42156862745098e-06,
|
| 694 |
+
"loss": 1.0065,
|
| 695 |
+
"step": 8900
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 46.63,
|
| 699 |
+
"learning_rate": 6.4411764705882346e-06,
|
| 700 |
+
"loss": 1.027,
|
| 701 |
+
"step": 9000
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 46.63,
|
| 705 |
+
"eval_loss": 0.8119935989379883,
|
| 706 |
+
"eval_runtime": 115.6592,
|
| 707 |
+
"eval_samples_per_second": 23.284,
|
| 708 |
+
"eval_steps_per_second": 2.914,
|
| 709 |
+
"eval_wer": 0.5179560561299852,
|
| 710 |
+
"step": 9000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 47.15,
|
| 714 |
+
"learning_rate": 5.460784313725489e-06,
|
| 715 |
+
"loss": 0.9917,
|
| 716 |
+
"step": 9100
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 47.67,
|
| 720 |
+
"learning_rate": 4.480392156862745e-06,
|
| 721 |
+
"loss": 0.9925,
|
| 722 |
+
"step": 9200
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 48.19,
|
| 726 |
+
"learning_rate": 3.5e-06,
|
| 727 |
+
"loss": 0.9924,
|
| 728 |
+
"step": 9300
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 48.7,
|
| 732 |
+
"learning_rate": 2.5196078431372547e-06,
|
| 733 |
+
"loss": 0.983,
|
| 734 |
+
"step": 9400
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 49.22,
|
| 738 |
+
"learning_rate": 1.5392156862745098e-06,
|
| 739 |
+
"loss": 0.9876,
|
| 740 |
+
"step": 9500
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 49.22,
|
| 744 |
+
"eval_loss": 0.8109092116355896,
|
| 745 |
+
"eval_runtime": 115.9344,
|
| 746 |
+
"eval_samples_per_second": 23.229,
|
| 747 |
+
"eval_steps_per_second": 2.907,
|
| 748 |
+
"eval_wer": 0.5187869276218612,
|
| 749 |
+
"step": 9500
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 49.74,
|
| 753 |
+
"learning_rate": 5.588235294117647e-07,
|
| 754 |
+
"loss": 0.973,
|
| 755 |
+
"step": 9600
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 50.0,
|
| 759 |
+
"step": 9650,
|
| 760 |
+
"total_flos": 4.0125393308879946e+19,
|
| 761 |
+
"train_loss": 1.853262206161578,
|
| 762 |
+
"train_runtime": 19140.1846,
|
| 763 |
+
"train_samples_per_second": 16.134,
|
| 764 |
+
"train_steps_per_second": 0.504
|
| 765 |
+
}
|
| 766 |
+
],
|
| 767 |
+
"max_steps": 9650,
|
| 768 |
+
"num_train_epochs": 50,
|
| 769 |
+
"total_flos": 4.0125393308879946e+19,
|
| 770 |
+
"trial_name": null,
|
| 771 |
+
"trial_params": null
|
| 772 |
+
}
|