Upload 9 files
Browse files- optimizer.pt +1 -1
- pytorch_model.bin +1 -1
- rng_state.pth +2 -2
- scaler.pt +1 -1
- scheduler.pt +1 -1
- trainer_state.json +1377 -72
- training_args.bin +1 -1
optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2490593669
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8bc4f81e10c73c7ac61c3457069fbbe7bd2da9c195af5e95d48242d813a3bf1b
|
| 3 |
size 2490593669
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1262168365
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ccb46c1363e00e7ba2c503b6625e15f6b52767b331922f0e118c099984e94b3f
|
| 3 |
size 1262168365
|
rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64dff988ed5a64f29c0ad329d02de826f427335e5b6422e636e4d8d72905d91b
|
| 3 |
+
size 14575
|
scaler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 557
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f56e2d94fbf475c8ee7bb541a0c78739d0af9b9df1c40b0d2dbe8978e561b1ce
|
| 3 |
size 557
|
scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93eea870ecabb225c120efec3800c13df934b00089cdfdaa458d79acaf790660
|
| 3 |
size 627
|
trainer_state.json
CHANGED
|
@@ -1,181 +1,1486 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 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": 0.02,
|
| 12 |
"learning_rate": 1e-05,
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 2
|
| 15 |
},
|
| 16 |
{
|
| 17 |
"epoch": 0.02,
|
| 18 |
-
"eval_loss": 0.
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second":
|
| 22 |
-
"eval_wer": 0.
|
| 23 |
"step": 2
|
| 24 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
{
|
| 26 |
"epoch": 0.03,
|
| 27 |
"learning_rate": 2e-05,
|
| 28 |
-
"loss": 0.
|
| 29 |
"step": 4
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 0.03,
|
| 33 |
-
"eval_loss": 0.
|
| 34 |
-
"eval_runtime":
|
| 35 |
-
"eval_samples_per_second": 25.
|
| 36 |
-
"eval_steps_per_second": 3.
|
| 37 |
-
"eval_wer": 0.
|
| 38 |
"step": 4
|
| 39 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
{
|
| 41 |
"epoch": 0.05,
|
| 42 |
"learning_rate": 3e-05,
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 6
|
| 45 |
},
|
| 46 |
{
|
| 47 |
"epoch": 0.05,
|
| 48 |
-
"eval_loss": 0.
|
| 49 |
-
"eval_runtime": 146.
|
| 50 |
-
"eval_samples_per_second": 25.
|
| 51 |
-
"eval_steps_per_second": 3.
|
| 52 |
-
"eval_wer": 0.
|
| 53 |
"step": 6
|
| 54 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
{
|
| 56 |
"epoch": 0.06,
|
| 57 |
"learning_rate": 4e-05,
|
| 58 |
-
"loss": 0.
|
| 59 |
"step": 8
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.06,
|
| 63 |
-
"eval_loss": 0.
|
| 64 |
-
"eval_runtime":
|
| 65 |
-
"eval_samples_per_second": 25.
|
| 66 |
-
"eval_steps_per_second": 3.
|
| 67 |
-
"eval_wer": 0.
|
| 68 |
"step": 8
|
| 69 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
{
|
| 71 |
"epoch": 0.08,
|
| 72 |
"learning_rate": 5e-05,
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 10
|
| 75 |
},
|
| 76 |
{
|
| 77 |
"epoch": 0.08,
|
| 78 |
-
"eval_loss": 0.
|
| 79 |
-
"eval_runtime":
|
| 80 |
-
"eval_samples_per_second": 26.
|
| 81 |
-
"eval_steps_per_second": 3.
|
| 82 |
-
"eval_wer": 0.
|
| 83 |
"step": 10
|
| 84 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 85 |
{
|
| 86 |
"epoch": 0.09,
|
| 87 |
"learning_rate": 6e-05,
|
| 88 |
-
"loss": 0.
|
| 89 |
"step": 12
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 0.09,
|
| 93 |
-
"eval_loss": 0.
|
| 94 |
-
"eval_runtime":
|
| 95 |
-
"eval_samples_per_second": 25.
|
| 96 |
-
"eval_steps_per_second": 3.
|
| 97 |
-
"eval_wer": 0.
|
| 98 |
"step": 12
|
| 99 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 100 |
{
|
| 101 |
"epoch": 0.11,
|
| 102 |
"learning_rate": 7e-05,
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 14
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 0.11,
|
| 108 |
-
"eval_loss": 0.
|
| 109 |
-
"eval_runtime":
|
| 110 |
-
"eval_samples_per_second": 25.
|
| 111 |
-
"eval_steps_per_second": 3.
|
| 112 |
-
"eval_wer": 0.
|
| 113 |
"step": 14
|
| 114 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
{
|
| 116 |
"epoch": 0.12,
|
| 117 |
"learning_rate": 8e-05,
|
| 118 |
-
"loss": 0.
|
| 119 |
"step": 16
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 0.12,
|
| 123 |
-
"eval_loss": 0.
|
| 124 |
-
"eval_runtime":
|
| 125 |
-
"eval_samples_per_second":
|
| 126 |
-
"eval_steps_per_second": 3.
|
| 127 |
-
"eval_wer": 0.
|
| 128 |
"step": 16
|
| 129 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 130 |
{
|
| 131 |
"epoch": 0.14,
|
| 132 |
"learning_rate": 9e-05,
|
| 133 |
-
"loss": 0.
|
| 134 |
"step": 18
|
| 135 |
},
|
| 136 |
{
|
| 137 |
"epoch": 0.14,
|
| 138 |
-
"eval_loss": 0.
|
| 139 |
-
"eval_runtime":
|
| 140 |
-
"eval_samples_per_second": 25.
|
| 141 |
-
"eval_steps_per_second": 3.
|
| 142 |
-
"eval_wer": 0.
|
| 143 |
"step": 18
|
| 144 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 145 |
{
|
| 146 |
"epoch": 0.15,
|
| 147 |
"learning_rate": 0.0001,
|
| 148 |
-
"loss": 0.
|
| 149 |
"step": 20
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.15,
|
| 153 |
-
"eval_loss": 0.
|
| 154 |
-
"eval_runtime":
|
| 155 |
-
"eval_samples_per_second": 25.
|
| 156 |
-
"eval_steps_per_second": 3.
|
| 157 |
-
"eval_wer": 0.
|
| 158 |
"step": 20
|
| 159 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 160 |
{
|
| 161 |
"epoch": 0.17,
|
| 162 |
-
"learning_rate": 9.
|
| 163 |
-
"loss": 0.
|
| 164 |
"step": 22
|
| 165 |
},
|
| 166 |
{
|
| 167 |
"epoch": 0.17,
|
| 168 |
-
"eval_loss": 0.
|
| 169 |
-
"eval_runtime":
|
| 170 |
-
"eval_samples_per_second":
|
| 171 |
-
"eval_steps_per_second": 3.
|
| 172 |
-
"eval_wer": 0.
|
| 173 |
"step": 22
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 174 |
}
|
| 175 |
],
|
| 176 |
-
"max_steps":
|
| 177 |
-
"num_train_epochs":
|
| 178 |
-
"total_flos":
|
| 179 |
"trial_name": null,
|
| 180 |
"trial_params": null
|
| 181 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.7531219980787704,
|
| 5 |
+
"global_step": 98,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 5e-06,
|
| 13 |
+
"loss": 0.1444,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.01,
|
| 18 |
+
"eval_loss": 0.27758705615997314,
|
| 19 |
+
"eval_runtime": 210.178,
|
| 20 |
+
"eval_samples_per_second": 17.666,
|
| 21 |
+
"eval_steps_per_second": 2.212,
|
| 22 |
+
"eval_wer": 0.22257840465886627,
|
| 23 |
+
"step": 1
|
| 24 |
+
},
|
| 25 |
{
|
| 26 |
"epoch": 0.02,
|
| 27 |
"learning_rate": 1e-05,
|
| 28 |
+
"loss": 0.1768,
|
| 29 |
"step": 2
|
| 30 |
},
|
| 31 |
{
|
| 32 |
"epoch": 0.02,
|
| 33 |
+
"eval_loss": 0.27495622634887695,
|
| 34 |
+
"eval_runtime": 143.6977,
|
| 35 |
+
"eval_samples_per_second": 25.839,
|
| 36 |
+
"eval_steps_per_second": 3.236,
|
| 37 |
+
"eval_wer": 0.22263183202436287,
|
| 38 |
"step": 2
|
| 39 |
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02,
|
| 42 |
+
"learning_rate": 1.5e-05,
|
| 43 |
+
"loss": 0.1344,
|
| 44 |
+
"step": 3
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"eval_loss": 0.26992350816726685,
|
| 49 |
+
"eval_runtime": 145.0666,
|
| 50 |
+
"eval_samples_per_second": 25.595,
|
| 51 |
+
"eval_steps_per_second": 3.205,
|
| 52 |
+
"eval_wer": 0.22097558369396805,
|
| 53 |
+
"step": 3
|
| 54 |
+
},
|
| 55 |
{
|
| 56 |
"epoch": 0.03,
|
| 57 |
"learning_rate": 2e-05,
|
| 58 |
+
"loss": 0.1347,
|
| 59 |
"step": 4
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 0.03,
|
| 63 |
+
"eval_loss": 0.2631027102470398,
|
| 64 |
+
"eval_runtime": 144.3292,
|
| 65 |
+
"eval_samples_per_second": 25.726,
|
| 66 |
+
"eval_steps_per_second": 3.222,
|
| 67 |
+
"eval_wer": 0.2198001816530427,
|
| 68 |
"step": 4
|
| 69 |
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.04,
|
| 72 |
+
"learning_rate": 2.5e-05,
|
| 73 |
+
"loss": 0.1401,
|
| 74 |
+
"step": 5
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.04,
|
| 78 |
+
"eval_loss": 0.2548554539680481,
|
| 79 |
+
"eval_runtime": 145.5653,
|
| 80 |
+
"eval_samples_per_second": 25.507,
|
| 81 |
+
"eval_steps_per_second": 3.194,
|
| 82 |
+
"eval_wer": 0.21825078805364106,
|
| 83 |
+
"step": 5
|
| 84 |
+
},
|
| 85 |
{
|
| 86 |
"epoch": 0.05,
|
| 87 |
"learning_rate": 3e-05,
|
| 88 |
+
"loss": 0.122,
|
| 89 |
"step": 6
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 0.05,
|
| 93 |
+
"eval_loss": 0.24481205642223358,
|
| 94 |
+
"eval_runtime": 146.1904,
|
| 95 |
+
"eval_samples_per_second": 25.398,
|
| 96 |
+
"eval_steps_per_second": 3.181,
|
| 97 |
+
"eval_wer": 0.21627397553026662,
|
| 98 |
"step": 6
|
| 99 |
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.05,
|
| 102 |
+
"learning_rate": 3.5e-05,
|
| 103 |
+
"loss": 0.1098,
|
| 104 |
+
"step": 7
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.05,
|
| 108 |
+
"eval_loss": 0.23431816697120667,
|
| 109 |
+
"eval_runtime": 143.3943,
|
| 110 |
+
"eval_samples_per_second": 25.894,
|
| 111 |
+
"eval_steps_per_second": 3.243,
|
| 112 |
+
"eval_wer": 0.21317518833146337,
|
| 113 |
+
"step": 7
|
| 114 |
+
},
|
| 115 |
{
|
| 116 |
"epoch": 0.06,
|
| 117 |
"learning_rate": 4e-05,
|
| 118 |
+
"loss": 0.0777,
|
| 119 |
"step": 8
|
| 120 |
},
|
| 121 |
{
|
| 122 |
"epoch": 0.06,
|
| 123 |
+
"eval_loss": 0.2239282727241516,
|
| 124 |
+
"eval_runtime": 144.1351,
|
| 125 |
+
"eval_samples_per_second": 25.761,
|
| 126 |
+
"eval_steps_per_second": 3.226,
|
| 127 |
+
"eval_wer": 0.21002297376716353,
|
| 128 |
"step": 8
|
| 129 |
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.07,
|
| 132 |
+
"learning_rate": 4.5e-05,
|
| 133 |
+
"loss": 0.0987,
|
| 134 |
+
"step": 9
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.07,
|
| 138 |
+
"eval_loss": 0.2142292559146881,
|
| 139 |
+
"eval_runtime": 142.2093,
|
| 140 |
+
"eval_samples_per_second": 26.109,
|
| 141 |
+
"eval_steps_per_second": 3.27,
|
| 142 |
+
"eval_wer": 0.20703104129935354,
|
| 143 |
+
"step": 9
|
| 144 |
+
},
|
| 145 |
{
|
| 146 |
"epoch": 0.08,
|
| 147 |
"learning_rate": 5e-05,
|
| 148 |
+
"loss": 0.0827,
|
| 149 |
"step": 10
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 0.08,
|
| 153 |
+
"eval_loss": 0.2058483362197876,
|
| 154 |
+
"eval_runtime": 139.25,
|
| 155 |
+
"eval_samples_per_second": 26.664,
|
| 156 |
+
"eval_steps_per_second": 3.339,
|
| 157 |
+
"eval_wer": 0.20409253619704013,
|
| 158 |
"step": 10
|
| 159 |
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.08,
|
| 162 |
+
"learning_rate": 5.500000000000001e-05,
|
| 163 |
+
"loss": 0.0657,
|
| 164 |
+
"step": 11
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.08,
|
| 168 |
+
"eval_loss": 0.19945959746837616,
|
| 169 |
+
"eval_runtime": 143.6254,
|
| 170 |
+
"eval_samples_per_second": 25.852,
|
| 171 |
+
"eval_steps_per_second": 3.238,
|
| 172 |
+
"eval_wer": 0.2003526206122776,
|
| 173 |
+
"step": 11
|
| 174 |
+
},
|
| 175 |
{
|
| 176 |
"epoch": 0.09,
|
| 177 |
"learning_rate": 6e-05,
|
| 178 |
+
"loss": 0.0464,
|
| 179 |
"step": 12
|
| 180 |
},
|
| 181 |
{
|
| 182 |
"epoch": 0.09,
|
| 183 |
+
"eval_loss": 0.19494406878948212,
|
| 184 |
+
"eval_runtime": 145.864,
|
| 185 |
+
"eval_samples_per_second": 25.455,
|
| 186 |
+
"eval_steps_per_second": 3.188,
|
| 187 |
+
"eval_wer": 0.19869637228188278,
|
| 188 |
"step": 12
|
| 189 |
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.1,
|
| 192 |
+
"learning_rate": 6.500000000000001e-05,
|
| 193 |
+
"loss": 0.0465,
|
| 194 |
+
"step": 13
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.1,
|
| 198 |
+
"eval_loss": 0.19232189655303955,
|
| 199 |
+
"eval_runtime": 145.6174,
|
| 200 |
+
"eval_samples_per_second": 25.498,
|
| 201 |
+
"eval_steps_per_second": 3.193,
|
| 202 |
+
"eval_wer": 0.19917721857135226,
|
| 203 |
+
"step": 13
|
| 204 |
+
},
|
| 205 |
{
|
| 206 |
"epoch": 0.11,
|
| 207 |
"learning_rate": 7e-05,
|
| 208 |
+
"loss": 0.0577,
|
| 209 |
"step": 14
|
| 210 |
},
|
| 211 |
{
|
| 212 |
"epoch": 0.11,
|
| 213 |
+
"eval_loss": 0.19074703752994537,
|
| 214 |
+
"eval_runtime": 145.4558,
|
| 215 |
+
"eval_samples_per_second": 25.527,
|
| 216 |
+
"eval_steps_per_second": 3.197,
|
| 217 |
+
"eval_wer": 0.19987177432280814,
|
| 218 |
"step": 14
|
| 219 |
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.12,
|
| 222 |
+
"learning_rate": 7.500000000000001e-05,
|
| 223 |
+
"loss": 0.0343,
|
| 224 |
+
"step": 15
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.12,
|
| 228 |
+
"eval_loss": 0.1901196986436844,
|
| 229 |
+
"eval_runtime": 145.104,
|
| 230 |
+
"eval_samples_per_second": 25.589,
|
| 231 |
+
"eval_steps_per_second": 3.205,
|
| 232 |
+
"eval_wer": 0.1995512101298285,
|
| 233 |
+
"step": 15
|
| 234 |
+
},
|
| 235 |
{
|
| 236 |
"epoch": 0.12,
|
| 237 |
"learning_rate": 8e-05,
|
| 238 |
+
"loss": 0.0496,
|
| 239 |
"step": 16
|
| 240 |
},
|
| 241 |
{
|
| 242 |
"epoch": 0.12,
|
| 243 |
+
"eval_loss": 0.19008365273475647,
|
| 244 |
+
"eval_runtime": 145.5007,
|
| 245 |
+
"eval_samples_per_second": 25.519,
|
| 246 |
+
"eval_steps_per_second": 3.196,
|
| 247 |
+
"eval_wer": 0.19992520168830474,
|
| 248 |
"step": 16
|
| 249 |
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.13,
|
| 252 |
+
"learning_rate": 8.5e-05,
|
| 253 |
+
"loss": 0.0394,
|
| 254 |
+
"step": 17
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.13,
|
| 258 |
+
"eval_loss": 0.19069527089595795,
|
| 259 |
+
"eval_runtime": 145.1656,
|
| 260 |
+
"eval_samples_per_second": 25.578,
|
| 261 |
+
"eval_steps_per_second": 3.203,
|
| 262 |
+
"eval_wer": 0.19976491959181492,
|
| 263 |
+
"step": 17
|
| 264 |
+
},
|
| 265 |
{
|
| 266 |
"epoch": 0.14,
|
| 267 |
"learning_rate": 9e-05,
|
| 268 |
+
"loss": 0.0389,
|
| 269 |
"step": 18
|
| 270 |
},
|
| 271 |
{
|
| 272 |
"epoch": 0.14,
|
| 273 |
+
"eval_loss": 0.19175583124160767,
|
| 274 |
+
"eval_runtime": 144.0309,
|
| 275 |
+
"eval_samples_per_second": 25.779,
|
| 276 |
+
"eval_steps_per_second": 3.228,
|
| 277 |
+
"eval_wer": 0.19864294491638618,
|
| 278 |
"step": 18
|
| 279 |
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.15,
|
| 282 |
+
"learning_rate": 9.5e-05,
|
| 283 |
+
"loss": 0.0375,
|
| 284 |
+
"step": 19
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.15,
|
| 288 |
+
"eval_loss": 0.1929420530796051,
|
| 289 |
+
"eval_runtime": 155.5361,
|
| 290 |
+
"eval_samples_per_second": 23.872,
|
| 291 |
+
"eval_steps_per_second": 2.99,
|
| 292 |
+
"eval_wer": 0.19869637228188278,
|
| 293 |
+
"step": 19
|
| 294 |
+
},
|
| 295 |
{
|
| 296 |
"epoch": 0.15,
|
| 297 |
"learning_rate": 0.0001,
|
| 298 |
+
"loss": 0.0416,
|
| 299 |
"step": 20
|
| 300 |
},
|
| 301 |
{
|
| 302 |
"epoch": 0.15,
|
| 303 |
+
"eval_loss": 0.19433951377868652,
|
| 304 |
+
"eval_runtime": 145.7557,
|
| 305 |
+
"eval_samples_per_second": 25.474,
|
| 306 |
+
"eval_steps_per_second": 3.19,
|
| 307 |
+
"eval_wer": 0.19842923545439975,
|
| 308 |
"step": 20
|
| 309 |
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.16,
|
| 312 |
+
"learning_rate": 9.909090909090911e-05,
|
| 313 |
+
"loss": 0.049,
|
| 314 |
+
"step": 21
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.16,
|
| 318 |
+
"eval_loss": 0.19554230570793152,
|
| 319 |
+
"eval_runtime": 144.8351,
|
| 320 |
+
"eval_samples_per_second": 25.636,
|
| 321 |
+
"eval_steps_per_second": 3.211,
|
| 322 |
+
"eval_wer": 0.19687984185499813,
|
| 323 |
+
"step": 21
|
| 324 |
+
},
|
| 325 |
{
|
| 326 |
"epoch": 0.17,
|
| 327 |
+
"learning_rate": 9.818181818181818e-05,
|
| 328 |
+
"loss": 0.0312,
|
| 329 |
"step": 22
|
| 330 |
},
|
| 331 |
{
|
| 332 |
"epoch": 0.17,
|
| 333 |
+
"eval_loss": 0.1970851719379425,
|
| 334 |
+
"eval_runtime": 142.3937,
|
| 335 |
+
"eval_samples_per_second": 26.076,
|
| 336 |
+
"eval_steps_per_second": 3.266,
|
| 337 |
+
"eval_wer": 0.19479617460063045,
|
| 338 |
"step": 22
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.18,
|
| 342 |
+
"learning_rate": 9.727272727272728e-05,
|
| 343 |
+
"loss": 0.0455,
|
| 344 |
+
"step": 23
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.18,
|
| 348 |
+
"eval_loss": 0.19858291745185852,
|
| 349 |
+
"eval_runtime": 140.2626,
|
| 350 |
+
"eval_samples_per_second": 26.472,
|
| 351 |
+
"eval_steps_per_second": 3.315,
|
| 352 |
+
"eval_wer": 0.19330020836672543,
|
| 353 |
+
"step": 23
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.18,
|
| 357 |
+
"learning_rate": 9.636363636363637e-05,
|
| 358 |
+
"loss": 0.0532,
|
| 359 |
+
"step": 24
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.18,
|
| 363 |
+
"eval_loss": 0.19979843497276306,
|
| 364 |
+
"eval_runtime": 140.2969,
|
| 365 |
+
"eval_samples_per_second": 26.465,
|
| 366 |
+
"eval_steps_per_second": 3.314,
|
| 367 |
+
"eval_wer": 0.19105625901586792,
|
| 368 |
+
"step": 24
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.19,
|
| 372 |
+
"learning_rate": 9.545454545454546e-05,
|
| 373 |
+
"loss": 0.0442,
|
| 374 |
+
"step": 25
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.19,
|
| 378 |
+
"eval_loss": 0.20092029869556427,
|
| 379 |
+
"eval_runtime": 143.5469,
|
| 380 |
+
"eval_samples_per_second": 25.866,
|
| 381 |
+
"eval_steps_per_second": 3.239,
|
| 382 |
+
"eval_wer": 0.19052198536090184,
|
| 383 |
+
"step": 25
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 0.2,
|
| 387 |
+
"learning_rate": 9.454545454545455e-05,
|
| 388 |
+
"loss": 0.0339,
|
| 389 |
+
"step": 26
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.2,
|
| 393 |
+
"eval_loss": 0.2023477554321289,
|
| 394 |
+
"eval_runtime": 152.7348,
|
| 395 |
+
"eval_samples_per_second": 24.31,
|
| 396 |
+
"eval_steps_per_second": 3.044,
|
| 397 |
+
"eval_wer": 0.1893465833199765,
|
| 398 |
+
"step": 26
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.21,
|
| 402 |
+
"learning_rate": 9.363636363636364e-05,
|
| 403 |
+
"loss": 0.0346,
|
| 404 |
+
"step": 27
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.21,
|
| 408 |
+
"eval_loss": 0.20320531725883484,
|
| 409 |
+
"eval_runtime": 147.0625,
|
| 410 |
+
"eval_samples_per_second": 25.248,
|
| 411 |
+
"eval_steps_per_second": 3.162,
|
| 412 |
+
"eval_wer": 0.18907944649249345,
|
| 413 |
+
"step": 27
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.22,
|
| 417 |
+
"learning_rate": 9.272727272727273e-05,
|
| 418 |
+
"loss": 0.0405,
|
| 419 |
+
"step": 28
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.22,
|
| 423 |
+
"eval_loss": 0.20423929393291473,
|
| 424 |
+
"eval_runtime": 147.2712,
|
| 425 |
+
"eval_samples_per_second": 25.212,
|
| 426 |
+
"eval_steps_per_second": 3.157,
|
| 427 |
+
"eval_wer": 0.18875888229951382,
|
| 428 |
+
"step": 28
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 0.22,
|
| 432 |
+
"learning_rate": 9.181818181818183e-05,
|
| 433 |
+
"loss": 0.0273,
|
| 434 |
+
"step": 29
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.22,
|
| 438 |
+
"eval_loss": 0.20516164600849152,
|
| 439 |
+
"eval_runtime": 147.0321,
|
| 440 |
+
"eval_samples_per_second": 25.253,
|
| 441 |
+
"eval_steps_per_second": 3.163,
|
| 442 |
+
"eval_wer": 0.18811775391355454,
|
| 443 |
+
"step": 29
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.23,
|
| 447 |
+
"learning_rate": 9.090909090909092e-05,
|
| 448 |
+
"loss": 0.0303,
|
| 449 |
+
"step": 30
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.23,
|
| 453 |
+
"eval_loss": 0.20583093166351318,
|
| 454 |
+
"eval_runtime": 147.1797,
|
| 455 |
+
"eval_samples_per_second": 25.228,
|
| 456 |
+
"eval_steps_per_second": 3.159,
|
| 457 |
+
"eval_wer": 0.18843831810653416,
|
| 458 |
+
"step": 30
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.24,
|
| 462 |
+
"learning_rate": 9e-05,
|
| 463 |
+
"loss": 0.0433,
|
| 464 |
+
"step": 31
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.24,
|
| 468 |
+
"eval_loss": 0.2059250921010971,
|
| 469 |
+
"eval_runtime": 149.5581,
|
| 470 |
+
"eval_samples_per_second": 24.826,
|
| 471 |
+
"eval_steps_per_second": 3.109,
|
| 472 |
+
"eval_wer": 0.1880108991825613,
|
| 473 |
+
"step": 31
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.25,
|
| 477 |
+
"learning_rate": 8.90909090909091e-05,
|
| 478 |
+
"loss": 0.0172,
|
| 479 |
+
"step": 32
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.25,
|
| 483 |
+
"eval_loss": 0.20622014999389648,
|
| 484 |
+
"eval_runtime": 147.3034,
|
| 485 |
+
"eval_samples_per_second": 25.206,
|
| 486 |
+
"eval_steps_per_second": 3.157,
|
| 487 |
+
"eval_wer": 0.18774376235507828,
|
| 488 |
+
"step": 32
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.25,
|
| 492 |
+
"learning_rate": 8.818181818181818e-05,
|
| 493 |
+
"loss": 0.0417,
|
| 494 |
+
"step": 33
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.25,
|
| 498 |
+
"eval_loss": 0.20588700473308563,
|
| 499 |
+
"eval_runtime": 147.9347,
|
| 500 |
+
"eval_samples_per_second": 25.099,
|
| 501 |
+
"eval_steps_per_second": 3.143,
|
| 502 |
+
"eval_wer": 0.18710263396911897,
|
| 503 |
+
"step": 33
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.26,
|
| 507 |
+
"learning_rate": 8.727272727272727e-05,
|
| 508 |
+
"loss": 0.0305,
|
| 509 |
+
"step": 34
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.26,
|
| 513 |
+
"eval_loss": 0.2053101509809494,
|
| 514 |
+
"eval_runtime": 147.604,
|
| 515 |
+
"eval_samples_per_second": 25.155,
|
| 516 |
+
"eval_steps_per_second": 3.15,
|
| 517 |
+
"eval_wer": 0.18624779612117326,
|
| 518 |
+
"step": 34
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 0.27,
|
| 522 |
+
"learning_rate": 8.636363636363637e-05,
|
| 523 |
+
"loss": 0.0294,
|
| 524 |
+
"step": 35
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 0.27,
|
| 528 |
+
"eval_loss": 0.2048512101173401,
|
| 529 |
+
"eval_runtime": 149.6988,
|
| 530 |
+
"eval_samples_per_second": 24.803,
|
| 531 |
+
"eval_steps_per_second": 3.106,
|
| 532 |
+
"eval_wer": 0.18624779612117326,
|
| 533 |
+
"step": 35
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.28,
|
| 537 |
+
"learning_rate": 8.545454545454545e-05,
|
| 538 |
+
"loss": 0.0344,
|
| 539 |
+
"step": 36
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.28,
|
| 543 |
+
"eval_loss": 0.20456022024154663,
|
| 544 |
+
"eval_runtime": 150.2353,
|
| 545 |
+
"eval_samples_per_second": 24.715,
|
| 546 |
+
"eval_steps_per_second": 3.095,
|
| 547 |
+
"eval_wer": 0.1863546508521665,
|
| 548 |
+
"step": 36
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.28,
|
| 552 |
+
"learning_rate": 8.454545454545455e-05,
|
| 553 |
+
"loss": 0.0352,
|
| 554 |
+
"step": 37
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.28,
|
| 558 |
+
"eval_loss": 0.20410528779029846,
|
| 559 |
+
"eval_runtime": 147.7984,
|
| 560 |
+
"eval_samples_per_second": 25.122,
|
| 561 |
+
"eval_steps_per_second": 3.146,
|
| 562 |
+
"eval_wer": 0.18539295827322755,
|
| 563 |
+
"step": 37
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.29,
|
| 567 |
+
"learning_rate": 8.363636363636364e-05,
|
| 568 |
+
"loss": 0.0379,
|
| 569 |
+
"step": 38
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.29,
|
| 573 |
+
"eval_loss": 0.2038663774728775,
|
| 574 |
+
"eval_runtime": 147.8438,
|
| 575 |
+
"eval_samples_per_second": 25.114,
|
| 576 |
+
"eval_steps_per_second": 3.145,
|
| 577 |
+
"eval_wer": 0.1857135224662072,
|
| 578 |
+
"step": 38
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.3,
|
| 582 |
+
"learning_rate": 8.272727272727273e-05,
|
| 583 |
+
"loss": 0.0413,
|
| 584 |
+
"step": 39
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.3,
|
| 588 |
+
"eval_loss": 0.20388050377368927,
|
| 589 |
+
"eval_runtime": 147.3701,
|
| 590 |
+
"eval_samples_per_second": 25.195,
|
| 591 |
+
"eval_steps_per_second": 3.155,
|
| 592 |
+
"eval_wer": 0.18427098359779878,
|
| 593 |
+
"step": 39
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.31,
|
| 597 |
+
"learning_rate": 8.181818181818183e-05,
|
| 598 |
+
"loss": 0.0317,
|
| 599 |
+
"step": 40
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.31,
|
| 603 |
+
"eval_loss": 0.20368847250938416,
|
| 604 |
+
"eval_runtime": 147.9612,
|
| 605 |
+
"eval_samples_per_second": 25.094,
|
| 606 |
+
"eval_steps_per_second": 3.143,
|
| 607 |
+
"eval_wer": 0.18384356467382593,
|
| 608 |
+
"step": 40
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.32,
|
| 612 |
+
"learning_rate": 8.090909090909092e-05,
|
| 613 |
+
"loss": 0.0406,
|
| 614 |
+
"step": 41
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 0.32,
|
| 618 |
+
"eval_loss": 0.20367969572544098,
|
| 619 |
+
"eval_runtime": 148.8012,
|
| 620 |
+
"eval_samples_per_second": 24.953,
|
| 621 |
+
"eval_steps_per_second": 3.125,
|
| 622 |
+
"eval_wer": 0.18330929101885987,
|
| 623 |
+
"step": 41
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.32,
|
| 627 |
+
"learning_rate": 8e-05,
|
| 628 |
+
"loss": 0.039,
|
| 629 |
+
"step": 42
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.32,
|
| 633 |
+
"eval_loss": 0.20352540910243988,
|
| 634 |
+
"eval_runtime": 148.6131,
|
| 635 |
+
"eval_samples_per_second": 24.984,
|
| 636 |
+
"eval_steps_per_second": 3.129,
|
| 637 |
+
"eval_wer": 0.18256130790190736,
|
| 638 |
+
"step": 42
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.33,
|
| 642 |
+
"learning_rate": 7.90909090909091e-05,
|
| 643 |
+
"loss": 0.0418,
|
| 644 |
+
"step": 43
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 0.33,
|
| 648 |
+
"eval_loss": 0.20341253280639648,
|
| 649 |
+
"eval_runtime": 148.4125,
|
| 650 |
+
"eval_samples_per_second": 25.018,
|
| 651 |
+
"eval_steps_per_second": 3.133,
|
| 652 |
+
"eval_wer": 0.18229417107442433,
|
| 653 |
+
"step": 43
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.34,
|
| 657 |
+
"learning_rate": 7.818181818181818e-05,
|
| 658 |
+
"loss": 0.0424,
|
| 659 |
+
"step": 44
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.34,
|
| 663 |
+
"eval_loss": 0.20320875942707062,
|
| 664 |
+
"eval_runtime": 148.7795,
|
| 665 |
+
"eval_samples_per_second": 24.956,
|
| 666 |
+
"eval_steps_per_second": 3.125,
|
| 667 |
+
"eval_wer": 0.18202703424694128,
|
| 668 |
+
"step": 44
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.35,
|
| 672 |
+
"learning_rate": 7.727272727272727e-05,
|
| 673 |
+
"loss": 0.0262,
|
| 674 |
+
"step": 45
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.35,
|
| 678 |
+
"eval_loss": 0.20320919156074524,
|
| 679 |
+
"eval_runtime": 149.2065,
|
| 680 |
+
"eval_samples_per_second": 24.885,
|
| 681 |
+
"eval_steps_per_second": 3.116,
|
| 682 |
+
"eval_wer": 0.18170647005396165,
|
| 683 |
+
"step": 45
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.35,
|
| 687 |
+
"learning_rate": 7.636363636363637e-05,
|
| 688 |
+
"loss": 0.0333,
|
| 689 |
+
"step": 46
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.35,
|
| 693 |
+
"eval_loss": 0.20314393937587738,
|
| 694 |
+
"eval_runtime": 148.5201,
|
| 695 |
+
"eval_samples_per_second": 25.0,
|
| 696 |
+
"eval_steps_per_second": 3.131,
|
| 697 |
+
"eval_wer": 0.18181332478495485,
|
| 698 |
+
"step": 46
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.36,
|
| 702 |
+
"learning_rate": 7.545454545454545e-05,
|
| 703 |
+
"loss": 0.0217,
|
| 704 |
+
"step": 47
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.36,
|
| 708 |
+
"eval_loss": 0.20316116511821747,
|
| 709 |
+
"eval_runtime": 149.0026,
|
| 710 |
+
"eval_samples_per_second": 24.919,
|
| 711 |
+
"eval_steps_per_second": 3.121,
|
| 712 |
+
"eval_wer": 0.18186675215045145,
|
| 713 |
+
"step": 47
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.37,
|
| 717 |
+
"learning_rate": 7.454545454545455e-05,
|
| 718 |
+
"loss": 0.0324,
|
| 719 |
+
"step": 48
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.37,
|
| 723 |
+
"eval_loss": 0.20341037213802338,
|
| 724 |
+
"eval_runtime": 151.4038,
|
| 725 |
+
"eval_samples_per_second": 24.524,
|
| 726 |
+
"eval_steps_per_second": 3.071,
|
| 727 |
+
"eval_wer": 0.18175989741945825,
|
| 728 |
+
"step": 48
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 0.38,
|
| 732 |
+
"learning_rate": 7.363636363636364e-05,
|
| 733 |
+
"loss": 0.0438,
|
| 734 |
+
"step": 49
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 0.38,
|
| 738 |
+
"eval_loss": 0.20362479984760284,
|
| 739 |
+
"eval_runtime": 147.9041,
|
| 740 |
+
"eval_samples_per_second": 25.104,
|
| 741 |
+
"eval_steps_per_second": 3.144,
|
| 742 |
+
"eval_wer": 0.18154618795747182,
|
| 743 |
+
"step": 49
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.38,
|
| 747 |
+
"learning_rate": 7.272727272727273e-05,
|
| 748 |
+
"loss": 0.0435,
|
| 749 |
+
"step": 50
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.38,
|
| 753 |
+
"eval_loss": 0.20351320505142212,
|
| 754 |
+
"eval_runtime": 150.6257,
|
| 755 |
+
"eval_samples_per_second": 24.651,
|
| 756 |
+
"eval_steps_per_second": 3.087,
|
| 757 |
+
"eval_wer": 0.18192017951594808,
|
| 758 |
+
"step": 50
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.39,
|
| 762 |
+
"learning_rate": 7.181818181818182e-05,
|
| 763 |
+
"loss": 0.0386,
|
| 764 |
+
"step": 51
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 0.39,
|
| 768 |
+
"eval_loss": 0.20342397689819336,
|
| 769 |
+
"eval_runtime": 149.3494,
|
| 770 |
+
"eval_samples_per_second": 24.861,
|
| 771 |
+
"eval_steps_per_second": 3.114,
|
| 772 |
+
"eval_wer": 0.18202703424694128,
|
| 773 |
+
"step": 51
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.4,
|
| 777 |
+
"learning_rate": 7.090909090909092e-05,
|
| 778 |
+
"loss": 0.034,
|
| 779 |
+
"step": 52
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.4,
|
| 783 |
+
"eval_loss": 0.20335783064365387,
|
| 784 |
+
"eval_runtime": 148.8221,
|
| 785 |
+
"eval_samples_per_second": 24.949,
|
| 786 |
+
"eval_steps_per_second": 3.125,
|
| 787 |
+
"eval_wer": 0.18245445317091413,
|
| 788 |
+
"step": 52
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.41,
|
| 792 |
+
"learning_rate": 7e-05,
|
| 793 |
+
"loss": 0.0308,
|
| 794 |
+
"step": 53
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.41,
|
| 798 |
+
"eval_loss": 0.20360249280929565,
|
| 799 |
+
"eval_runtime": 148.86,
|
| 800 |
+
"eval_samples_per_second": 24.943,
|
| 801 |
+
"eval_steps_per_second": 3.124,
|
| 802 |
+
"eval_wer": 0.18250788053641076,
|
| 803 |
+
"step": 53
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.41,
|
| 807 |
+
"learning_rate": 6.90909090909091e-05,
|
| 808 |
+
"loss": 0.0334,
|
| 809 |
+
"step": 54
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.41,
|
| 813 |
+
"eval_loss": 0.2034262865781784,
|
| 814 |
+
"eval_runtime": 149.0445,
|
| 815 |
+
"eval_samples_per_second": 24.912,
|
| 816 |
+
"eval_steps_per_second": 3.12,
|
| 817 |
+
"eval_wer": 0.1828284447293904,
|
| 818 |
+
"step": 54
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.42,
|
| 822 |
+
"learning_rate": 6.818181818181818e-05,
|
| 823 |
+
"loss": 0.0334,
|
| 824 |
+
"step": 55
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.42,
|
| 828 |
+
"eval_loss": 0.20335279405117035,
|
| 829 |
+
"eval_runtime": 149.9535,
|
| 830 |
+
"eval_samples_per_second": 24.761,
|
| 831 |
+
"eval_steps_per_second": 3.101,
|
| 832 |
+
"eval_wer": 0.18240102580541753,
|
| 833 |
+
"step": 55
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.43,
|
| 837 |
+
"learning_rate": 6.727272727272727e-05,
|
| 838 |
+
"loss": 0.0502,
|
| 839 |
+
"step": 56
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 0.43,
|
| 843 |
+
"eval_loss": 0.20316840708255768,
|
| 844 |
+
"eval_runtime": 150.4496,
|
| 845 |
+
"eval_samples_per_second": 24.679,
|
| 846 |
+
"eval_steps_per_second": 3.091,
|
| 847 |
+
"eval_wer": 0.18256130790190736,
|
| 848 |
+
"step": 56
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 0.44,
|
| 852 |
+
"learning_rate": 6.636363636363638e-05,
|
| 853 |
+
"loss": 0.0341,
|
| 854 |
+
"step": 57
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.44,
|
| 858 |
+
"eval_loss": 0.20272959768772125,
|
| 859 |
+
"eval_runtime": 149.4094,
|
| 860 |
+
"eval_samples_per_second": 24.851,
|
| 861 |
+
"eval_steps_per_second": 3.112,
|
| 862 |
+
"eval_wer": 0.1821873163434311,
|
| 863 |
+
"step": 57
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.45,
|
| 867 |
+
"learning_rate": 6.545454545454546e-05,
|
| 868 |
+
"loss": 0.0595,
|
| 869 |
+
"step": 58
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.45,
|
| 873 |
+
"eval_loss": 0.20200660824775696,
|
| 874 |
+
"eval_runtime": 150.4398,
|
| 875 |
+
"eval_samples_per_second": 24.681,
|
| 876 |
+
"eval_steps_per_second": 3.091,
|
| 877 |
+
"eval_wer": 0.18245445317091413,
|
| 878 |
+
"step": 58
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.45,
|
| 882 |
+
"learning_rate": 6.454545454545455e-05,
|
| 883 |
+
"loss": 0.0337,
|
| 884 |
+
"step": 59
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.45,
|
| 888 |
+
"eval_loss": 0.2010081559419632,
|
| 889 |
+
"eval_runtime": 149.7401,
|
| 890 |
+
"eval_samples_per_second": 24.796,
|
| 891 |
+
"eval_steps_per_second": 3.105,
|
| 892 |
+
"eval_wer": 0.18304215419137682,
|
| 893 |
+
"step": 59
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.46,
|
| 897 |
+
"learning_rate": 6.363636363636364e-05,
|
| 898 |
+
"loss": 0.0504,
|
| 899 |
+
"step": 60
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.46,
|
| 903 |
+
"eval_loss": 0.20022302865982056,
|
| 904 |
+
"eval_runtime": 150.2278,
|
| 905 |
+
"eval_samples_per_second": 24.716,
|
| 906 |
+
"eval_steps_per_second": 3.095,
|
| 907 |
+
"eval_wer": 0.18341614574985307,
|
| 908 |
+
"step": 60
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.47,
|
| 912 |
+
"learning_rate": 6.272727272727273e-05,
|
| 913 |
+
"loss": 0.0298,
|
| 914 |
+
"step": 61
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.47,
|
| 918 |
+
"eval_loss": 0.19969654083251953,
|
| 919 |
+
"eval_runtime": 149.9979,
|
| 920 |
+
"eval_samples_per_second": 24.754,
|
| 921 |
+
"eval_steps_per_second": 3.1,
|
| 922 |
+
"eval_wer": 0.18336271838435647,
|
| 923 |
+
"step": 61
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 0.48,
|
| 927 |
+
"learning_rate": 6.181818181818182e-05,
|
| 928 |
+
"loss": 0.0216,
|
| 929 |
+
"step": 62
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.48,
|
| 933 |
+
"eval_loss": 0.19924180209636688,
|
| 934 |
+
"eval_runtime": 149.7227,
|
| 935 |
+
"eval_samples_per_second": 24.799,
|
| 936 |
+
"eval_steps_per_second": 3.106,
|
| 937 |
+
"eval_wer": 0.18411070150130898,
|
| 938 |
+
"step": 62
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.48,
|
| 942 |
+
"learning_rate": 6.090909090909091e-05,
|
| 943 |
+
"loss": 0.0262,
|
| 944 |
+
"step": 63
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 0.48,
|
| 948 |
+
"eval_loss": 0.19875453412532806,
|
| 949 |
+
"eval_runtime": 151.0436,
|
| 950 |
+
"eval_samples_per_second": 24.582,
|
| 951 |
+
"eval_steps_per_second": 3.079,
|
| 952 |
+
"eval_wer": 0.18464497515627504,
|
| 953 |
+
"step": 63
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 0.49,
|
| 957 |
+
"learning_rate": 6e-05,
|
| 958 |
+
"loss": 0.012,
|
| 959 |
+
"step": 64
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 0.49,
|
| 963 |
+
"eval_loss": 0.19849465787410736,
|
| 964 |
+
"eval_runtime": 150.8245,
|
| 965 |
+
"eval_samples_per_second": 24.618,
|
| 966 |
+
"eval_steps_per_second": 3.083,
|
| 967 |
+
"eval_wer": 0.18528610354223432,
|
| 968 |
+
"step": 64
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.5,
|
| 972 |
+
"learning_rate": 5.90909090909091e-05,
|
| 973 |
+
"loss": 0.026,
|
| 974 |
+
"step": 65
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 0.5,
|
| 978 |
+
"eval_loss": 0.19816958904266357,
|
| 979 |
+
"eval_runtime": 152.5115,
|
| 980 |
+
"eval_samples_per_second": 24.346,
|
| 981 |
+
"eval_steps_per_second": 3.049,
|
| 982 |
+
"eval_wer": 0.185873804562697,
|
| 983 |
+
"step": 65
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.51,
|
| 987 |
+
"learning_rate": 5.818181818181818e-05,
|
| 988 |
+
"loss": 0.0382,
|
| 989 |
+
"step": 66
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.51,
|
| 993 |
+
"eval_loss": 0.19807423651218414,
|
| 994 |
+
"eval_runtime": 154.494,
|
| 995 |
+
"eval_samples_per_second": 24.033,
|
| 996 |
+
"eval_steps_per_second": 3.01,
|
| 997 |
+
"eval_wer": 0.18528610354223432,
|
| 998 |
+
"step": 66
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.51,
|
| 1002 |
+
"learning_rate": 5.727272727272728e-05,
|
| 1003 |
+
"loss": 0.0284,
|
| 1004 |
+
"step": 67
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.51,
|
| 1008 |
+
"eval_loss": 0.1981343924999237,
|
| 1009 |
+
"eval_runtime": 151.1093,
|
| 1010 |
+
"eval_samples_per_second": 24.572,
|
| 1011 |
+
"eval_steps_per_second": 3.077,
|
| 1012 |
+
"eval_wer": 0.1849121119837581,
|
| 1013 |
+
"step": 67
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.52,
|
| 1017 |
+
"learning_rate": 5.636363636363636e-05,
|
| 1018 |
+
"loss": 0.0273,
|
| 1019 |
+
"step": 68
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.52,
|
| 1023 |
+
"eval_loss": 0.19824360311031342,
|
| 1024 |
+
"eval_runtime": 151.8867,
|
| 1025 |
+
"eval_samples_per_second": 24.446,
|
| 1026 |
+
"eval_steps_per_second": 3.061,
|
| 1027 |
+
"eval_wer": 0.18421755623230218,
|
| 1028 |
+
"step": 68
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 0.53,
|
| 1032 |
+
"learning_rate": 5.545454545454546e-05,
|
| 1033 |
+
"loss": 0.0248,
|
| 1034 |
+
"step": 69
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.53,
|
| 1038 |
+
"eval_loss": 0.19854041934013367,
|
| 1039 |
+
"eval_runtime": 150.4994,
|
| 1040 |
+
"eval_samples_per_second": 24.671,
|
| 1041 |
+
"eval_steps_per_second": 3.09,
|
| 1042 |
+
"eval_wer": 0.1844312656942886,
|
| 1043 |
+
"step": 69
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 0.54,
|
| 1047 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 1048 |
+
"loss": 0.0315,
|
| 1049 |
+
"step": 70
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 0.54,
|
| 1053 |
+
"eval_loss": 0.19896994531154633,
|
| 1054 |
+
"eval_runtime": 150.9218,
|
| 1055 |
+
"eval_samples_per_second": 24.602,
|
| 1056 |
+
"eval_steps_per_second": 3.081,
|
| 1057 |
+
"eval_wer": 0.18405727413581235,
|
| 1058 |
+
"step": 70
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.55,
|
| 1062 |
+
"learning_rate": 5.363636363636364e-05,
|
| 1063 |
+
"loss": 0.0443,
|
| 1064 |
+
"step": 71
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 0.55,
|
| 1068 |
+
"eval_loss": 0.1993587613105774,
|
| 1069 |
+
"eval_runtime": 151.464,
|
| 1070 |
+
"eval_samples_per_second": 24.514,
|
| 1071 |
+
"eval_steps_per_second": 3.07,
|
| 1072 |
+
"eval_wer": 0.1835764278463429,
|
| 1073 |
+
"step": 71
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.55,
|
| 1077 |
+
"learning_rate": 5.272727272727272e-05,
|
| 1078 |
+
"loss": 0.0473,
|
| 1079 |
+
"step": 72
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 0.55,
|
| 1083 |
+
"eval_loss": 0.1994282454252243,
|
| 1084 |
+
"eval_runtime": 151.2775,
|
| 1085 |
+
"eval_samples_per_second": 24.544,
|
| 1086 |
+
"eval_steps_per_second": 3.074,
|
| 1087 |
+
"eval_wer": 0.18379013730832933,
|
| 1088 |
+
"step": 72
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.56,
|
| 1092 |
+
"learning_rate": 5.181818181818182e-05,
|
| 1093 |
+
"loss": 0.0366,
|
| 1094 |
+
"step": 73
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.56,
|
| 1098 |
+
"eval_loss": 0.19968333840370178,
|
| 1099 |
+
"eval_runtime": 151.4205,
|
| 1100 |
+
"eval_samples_per_second": 24.521,
|
| 1101 |
+
"eval_steps_per_second": 3.071,
|
| 1102 |
+
"eval_wer": 0.18298872682588022,
|
| 1103 |
+
"step": 73
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 0.57,
|
| 1107 |
+
"learning_rate": 5.090909090909091e-05,
|
| 1108 |
+
"loss": 0.0337,
|
| 1109 |
+
"step": 74
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.57,
|
| 1113 |
+
"eval_loss": 0.19987201690673828,
|
| 1114 |
+
"eval_runtime": 151.4399,
|
| 1115 |
+
"eval_samples_per_second": 24.518,
|
| 1116 |
+
"eval_steps_per_second": 3.071,
|
| 1117 |
+
"eval_wer": 0.18309558155687344,
|
| 1118 |
+
"step": 74
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.58,
|
| 1122 |
+
"learning_rate": 5e-05,
|
| 1123 |
+
"loss": 0.0304,
|
| 1124 |
+
"step": 75
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 0.58,
|
| 1128 |
+
"eval_loss": 0.2001255452632904,
|
| 1129 |
+
"eval_runtime": 152.4344,
|
| 1130 |
+
"eval_samples_per_second": 24.358,
|
| 1131 |
+
"eval_steps_per_second": 3.05,
|
| 1132 |
+
"eval_wer": 0.18346957311534967,
|
| 1133 |
+
"step": 75
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.58,
|
| 1137 |
+
"learning_rate": 4.909090909090909e-05,
|
| 1138 |
+
"loss": 0.0362,
|
| 1139 |
+
"step": 76
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.58,
|
| 1143 |
+
"eval_loss": 0.20033375918865204,
|
| 1144 |
+
"eval_runtime": 151.5547,
|
| 1145 |
+
"eval_samples_per_second": 24.499,
|
| 1146 |
+
"eval_steps_per_second": 3.068,
|
| 1147 |
+
"eval_wer": 0.18293529946038362,
|
| 1148 |
+
"step": 76
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.59,
|
| 1152 |
+
"learning_rate": 4.8181818181818186e-05,
|
| 1153 |
+
"loss": 0.0482,
|
| 1154 |
+
"step": 77
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.59,
|
| 1158 |
+
"eval_loss": 0.20038414001464844,
|
| 1159 |
+
"eval_runtime": 151.9532,
|
| 1160 |
+
"eval_samples_per_second": 24.435,
|
| 1161 |
+
"eval_steps_per_second": 3.06,
|
| 1162 |
+
"eval_wer": 0.18250788053641076,
|
| 1163 |
+
"step": 77
|
| 1164 |
+
},
|
| 1165 |
+
{
|
| 1166 |
+
"epoch": 0.6,
|
| 1167 |
+
"learning_rate": 4.7272727272727275e-05,
|
| 1168 |
+
"loss": 0.0362,
|
| 1169 |
+
"step": 78
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 0.6,
|
| 1173 |
+
"eval_loss": 0.20029421150684357,
|
| 1174 |
+
"eval_runtime": 153.417,
|
| 1175 |
+
"eval_samples_per_second": 24.202,
|
| 1176 |
+
"eval_steps_per_second": 3.031,
|
| 1177 |
+
"eval_wer": 0.1828284447293904,
|
| 1178 |
+
"step": 78
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.61,
|
| 1182 |
+
"learning_rate": 4.636363636363636e-05,
|
| 1183 |
+
"loss": 0.0301,
|
| 1184 |
+
"step": 79
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.61,
|
| 1188 |
+
"eval_loss": 0.20029130578041077,
|
| 1189 |
+
"eval_runtime": 151.1667,
|
| 1190 |
+
"eval_samples_per_second": 24.562,
|
| 1191 |
+
"eval_steps_per_second": 3.076,
|
| 1192 |
+
"eval_wer": 0.18293529946038362,
|
| 1193 |
+
"step": 79
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.61,
|
| 1197 |
+
"learning_rate": 4.545454545454546e-05,
|
| 1198 |
+
"loss": 0.031,
|
| 1199 |
+
"step": 80
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.61,
|
| 1203 |
+
"eval_loss": 0.200118288397789,
|
| 1204 |
+
"eval_runtime": 152.5561,
|
| 1205 |
+
"eval_samples_per_second": 24.339,
|
| 1206 |
+
"eval_steps_per_second": 3.048,
|
| 1207 |
+
"eval_wer": 0.18330929101885987,
|
| 1208 |
+
"step": 80
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 0.62,
|
| 1212 |
+
"learning_rate": 4.454545454545455e-05,
|
| 1213 |
+
"loss": 0.0377,
|
| 1214 |
+
"step": 81
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.62,
|
| 1218 |
+
"eval_loss": 0.1998458057641983,
|
| 1219 |
+
"eval_runtime": 152.057,
|
| 1220 |
+
"eval_samples_per_second": 24.418,
|
| 1221 |
+
"eval_steps_per_second": 3.058,
|
| 1222 |
+
"eval_wer": 0.18234759843992093,
|
| 1223 |
+
"step": 81
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.63,
|
| 1227 |
+
"learning_rate": 4.3636363636363636e-05,
|
| 1228 |
+
"loss": 0.0372,
|
| 1229 |
+
"step": 82
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 0.63,
|
| 1233 |
+
"eval_loss": 0.19953805208206177,
|
| 1234 |
+
"eval_runtime": 152.6899,
|
| 1235 |
+
"eval_samples_per_second": 24.317,
|
| 1236 |
+
"eval_steps_per_second": 3.045,
|
| 1237 |
+
"eval_wer": 0.18256130790190736,
|
| 1238 |
+
"step": 82
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.64,
|
| 1242 |
+
"learning_rate": 4.2727272727272724e-05,
|
| 1243 |
+
"loss": 0.0234,
|
| 1244 |
+
"step": 83
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.64,
|
| 1248 |
+
"eval_loss": 0.19939135015010834,
|
| 1249 |
+
"eval_runtime": 152.3549,
|
| 1250 |
+
"eval_samples_per_second": 24.371,
|
| 1251 |
+
"eval_steps_per_second": 3.052,
|
| 1252 |
+
"eval_wer": 0.18202703424694128,
|
| 1253 |
+
"step": 83
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 0.65,
|
| 1257 |
+
"learning_rate": 4.181818181818182e-05,
|
| 1258 |
+
"loss": 0.0539,
|
| 1259 |
+
"step": 84
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.65,
|
| 1263 |
+
"eval_loss": 0.19920985400676727,
|
| 1264 |
+
"eval_runtime": 151.8121,
|
| 1265 |
+
"eval_samples_per_second": 24.458,
|
| 1266 |
+
"eval_steps_per_second": 3.063,
|
| 1267 |
+
"eval_wer": 0.18154618795747182,
|
| 1268 |
+
"step": 84
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 0.65,
|
| 1272 |
+
"learning_rate": 4.0909090909090915e-05,
|
| 1273 |
+
"loss": 0.0446,
|
| 1274 |
+
"step": 85
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.65,
|
| 1278 |
+
"eval_loss": 0.19903059303760529,
|
| 1279 |
+
"eval_runtime": 153.3501,
|
| 1280 |
+
"eval_samples_per_second": 24.213,
|
| 1281 |
+
"eval_steps_per_second": 3.032,
|
| 1282 |
+
"eval_wer": 0.18181332478495485,
|
| 1283 |
+
"step": 85
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.66,
|
| 1287 |
+
"learning_rate": 4e-05,
|
| 1288 |
+
"loss": 0.0373,
|
| 1289 |
+
"step": 86
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 0.66,
|
| 1293 |
+
"eval_loss": 0.19874274730682373,
|
| 1294 |
+
"eval_runtime": 153.2828,
|
| 1295 |
+
"eval_samples_per_second": 24.223,
|
| 1296 |
+
"eval_steps_per_second": 3.034,
|
| 1297 |
+
"eval_wer": 0.18154618795747182,
|
| 1298 |
+
"step": 86
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.67,
|
| 1302 |
+
"learning_rate": 3.909090909090909e-05,
|
| 1303 |
+
"loss": 0.0347,
|
| 1304 |
+
"step": 87
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.67,
|
| 1308 |
+
"eval_loss": 0.1984863579273224,
|
| 1309 |
+
"eval_runtime": 153.5045,
|
| 1310 |
+
"eval_samples_per_second": 24.188,
|
| 1311 |
+
"eval_steps_per_second": 3.029,
|
| 1312 |
+
"eval_wer": 0.1814393332264786,
|
| 1313 |
+
"step": 87
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.68,
|
| 1317 |
+
"learning_rate": 3.818181818181819e-05,
|
| 1318 |
+
"loss": 0.0477,
|
| 1319 |
+
"step": 88
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.68,
|
| 1323 |
+
"eval_loss": 0.19823090732097626,
|
| 1324 |
+
"eval_runtime": 153.2343,
|
| 1325 |
+
"eval_samples_per_second": 24.231,
|
| 1326 |
+
"eval_steps_per_second": 3.035,
|
| 1327 |
+
"eval_wer": 0.18186675215045145,
|
| 1328 |
+
"step": 88
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.68,
|
| 1332 |
+
"learning_rate": 3.7272727272727276e-05,
|
| 1333 |
+
"loss": 0.0365,
|
| 1334 |
+
"step": 89
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.68,
|
| 1338 |
+
"eval_loss": 0.1978393793106079,
|
| 1339 |
+
"eval_runtime": 153.4002,
|
| 1340 |
+
"eval_samples_per_second": 24.205,
|
| 1341 |
+
"eval_steps_per_second": 3.031,
|
| 1342 |
+
"eval_wer": 0.1814393332264786,
|
| 1343 |
+
"step": 89
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.69,
|
| 1347 |
+
"learning_rate": 3.6363636363636364e-05,
|
| 1348 |
+
"loss": 0.0255,
|
| 1349 |
+
"step": 90
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.69,
|
| 1353 |
+
"eval_loss": 0.1975974142551422,
|
| 1354 |
+
"eval_runtime": 153.949,
|
| 1355 |
+
"eval_samples_per_second": 24.118,
|
| 1356 |
+
"eval_steps_per_second": 3.02,
|
| 1357 |
+
"eval_wer": 0.18101191430250574,
|
| 1358 |
+
"step": 90
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 0.7,
|
| 1362 |
+
"learning_rate": 3.545454545454546e-05,
|
| 1363 |
+
"loss": 0.0205,
|
| 1364 |
+
"step": 91
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.7,
|
| 1368 |
+
"eval_loss": 0.19747106730937958,
|
| 1369 |
+
"eval_runtime": 153.3875,
|
| 1370 |
+
"eval_samples_per_second": 24.207,
|
| 1371 |
+
"eval_steps_per_second": 3.032,
|
| 1372 |
+
"eval_wer": 0.18063792274402948,
|
| 1373 |
+
"step": 91
|
| 1374 |
+
},
|
| 1375 |
+
{
|
| 1376 |
+
"epoch": 0.71,
|
| 1377 |
+
"learning_rate": 3.454545454545455e-05,
|
| 1378 |
+
"loss": 0.053,
|
| 1379 |
+
"step": 92
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 0.71,
|
| 1383 |
+
"eval_loss": 0.19707681238651276,
|
| 1384 |
+
"eval_runtime": 151.9804,
|
| 1385 |
+
"eval_samples_per_second": 24.431,
|
| 1386 |
+
"eval_steps_per_second": 3.06,
|
| 1387 |
+
"eval_wer": 0.18031735855104986,
|
| 1388 |
+
"step": 92
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.71,
|
| 1392 |
+
"learning_rate": 3.3636363636363636e-05,
|
| 1393 |
+
"loss": 0.0188,
|
| 1394 |
+
"step": 93
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.71,
|
| 1398 |
+
"eval_loss": 0.19678995013237,
|
| 1399 |
+
"eval_runtime": 156.2042,
|
| 1400 |
+
"eval_samples_per_second": 23.77,
|
| 1401 |
+
"eval_steps_per_second": 2.977,
|
| 1402 |
+
"eval_wer": 0.18053106801303628,
|
| 1403 |
+
"step": 93
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.72,
|
| 1407 |
+
"learning_rate": 3.272727272727273e-05,
|
| 1408 |
+
"loss": 0.018,
|
| 1409 |
+
"step": 94
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.72,
|
| 1413 |
+
"eval_loss": 0.1968337893486023,
|
| 1414 |
+
"eval_runtime": 151.8471,
|
| 1415 |
+
"eval_samples_per_second": 24.452,
|
| 1416 |
+
"eval_steps_per_second": 3.062,
|
| 1417 |
+
"eval_wer": 0.18015707645456003,
|
| 1418 |
+
"step": 94
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.73,
|
| 1422 |
+
"learning_rate": 3.181818181818182e-05,
|
| 1423 |
+
"loss": 0.0135,
|
| 1424 |
+
"step": 95
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.73,
|
| 1428 |
+
"eval_loss": 0.19669164717197418,
|
| 1429 |
+
"eval_runtime": 153.6158,
|
| 1430 |
+
"eval_samples_per_second": 24.171,
|
| 1431 |
+
"eval_steps_per_second": 3.027,
|
| 1432 |
+
"eval_wer": 0.18042421328204306,
|
| 1433 |
+
"step": 95
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.74,
|
| 1437 |
+
"learning_rate": 3.090909090909091e-05,
|
| 1438 |
+
"loss": 0.0099,
|
| 1439 |
+
"step": 96
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 0.74,
|
| 1443 |
+
"eval_loss": 0.1966254860162735,
|
| 1444 |
+
"eval_runtime": 153.1791,
|
| 1445 |
+
"eval_samples_per_second": 24.24,
|
| 1446 |
+
"eval_steps_per_second": 3.036,
|
| 1447 |
+
"eval_wer": 0.18010364908906343,
|
| 1448 |
+
"step": 96
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 0.75,
|
| 1452 |
+
"learning_rate": 3e-05,
|
| 1453 |
+
"loss": 0.0283,
|
| 1454 |
+
"step": 97
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 0.75,
|
| 1458 |
+
"eval_loss": 0.19664821028709412,
|
| 1459 |
+
"eval_runtime": 152.9205,
|
| 1460 |
+
"eval_samples_per_second": 24.281,
|
| 1461 |
+
"eval_steps_per_second": 3.041,
|
| 1462 |
+
"eval_wer": 0.18042421328204306,
|
| 1463 |
+
"step": 97
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.75,
|
| 1467 |
+
"learning_rate": 2.909090909090909e-05,
|
| 1468 |
+
"loss": 0.0345,
|
| 1469 |
+
"step": 98
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 0.75,
|
| 1473 |
+
"eval_loss": 0.19662834703922272,
|
| 1474 |
+
"eval_runtime": 153.3485,
|
| 1475 |
+
"eval_samples_per_second": 24.213,
|
| 1476 |
+
"eval_steps_per_second": 3.032,
|
| 1477 |
+
"eval_wer": 0.1799433669925736,
|
| 1478 |
+
"step": 98
|
| 1479 |
}
|
| 1480 |
],
|
| 1481 |
+
"max_steps": 130,
|
| 1482 |
+
"num_train_epochs": 1,
|
| 1483 |
+
"total_flos": 2.245784209200768e+18,
|
| 1484 |
"trial_name": null,
|
| 1485 |
"trial_params": null
|
| 1486 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3323
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:157b26c01ed722d6f5c5a4023fabc27a6bacfd61d977a05834d3adf2dfe8a9ac
|
| 3 |
size 3323
|