Commit
•
80e7ea9
1
Parent(s):
bd15bf6
All Done!
Browse files
runs/May28_17-53-36_4c3713f55386/events.out.tfevents.1685300987.4c3713f55386.345.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:820944909434db9bd042d172e7d1a4c9bbc4d476d968590a9c7271efd735bd98
|
| 3 |
+
size 406
|
trainer_state.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 1085,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 4.9953917050691245e-05,
|
| 13 |
+
"loss": 11.8912,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_cer": 0.07741935483870968,
|
| 19 |
+
"eval_loss": 0.23858200013637543,
|
| 20 |
+
"eval_runtime": 140.9135,
|
| 21 |
+
"eval_samples_per_second": 0.979,
|
| 22 |
+
"eval_steps_per_second": 0.128,
|
| 23 |
+
"step": 217
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"eval_cer": 0.04516129032258064,
|
| 28 |
+
"eval_loss": 0.15434867143630981,
|
| 29 |
+
"eval_runtime": 37.8243,
|
| 30 |
+
"eval_samples_per_second": 3.648,
|
| 31 |
+
"eval_steps_per_second": 0.476,
|
| 32 |
+
"step": 434
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.3,
|
| 36 |
+
"learning_rate": 2.6958525345622122e-05,
|
| 37 |
+
"loss": 0.4293,
|
| 38 |
+
"step": 500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 3.0,
|
| 42 |
+
"eval_cer": 0.01935483870967742,
|
| 43 |
+
"eval_loss": 0.10877370089292526,
|
| 44 |
+
"eval_runtime": 35.4493,
|
| 45 |
+
"eval_samples_per_second": 3.893,
|
| 46 |
+
"eval_steps_per_second": 0.508,
|
| 47 |
+
"step": 651
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 4.0,
|
| 51 |
+
"eval_cer": 0.03225806451612903,
|
| 52 |
+
"eval_loss": 0.12325212359428406,
|
| 53 |
+
"eval_runtime": 35.8699,
|
| 54 |
+
"eval_samples_per_second": 3.847,
|
| 55 |
+
"eval_steps_per_second": 0.502,
|
| 56 |
+
"step": 868
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 4.61,
|
| 60 |
+
"learning_rate": 3.9170506912442395e-06,
|
| 61 |
+
"loss": 0.0775,
|
| 62 |
+
"step": 1000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 5.0,
|
| 66 |
+
"eval_cer": 0.016129032258064516,
|
| 67 |
+
"eval_loss": 0.10414960980415344,
|
| 68 |
+
"eval_runtime": 37.8862,
|
| 69 |
+
"eval_samples_per_second": 3.642,
|
| 70 |
+
"eval_steps_per_second": 0.475,
|
| 71 |
+
"step": 1085
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 5.0,
|
| 75 |
+
"step": 1085,
|
| 76 |
+
"total_flos": 6.483891179980063e+18,
|
| 77 |
+
"train_loss": 0.246805760827482,
|
| 78 |
+
"train_runtime": 4287.6356,
|
| 79 |
+
"train_samples_per_second": 2.021,
|
| 80 |
+
"train_steps_per_second": 0.253
|
| 81 |
+
}
|
| 82 |
+
],
|
| 83 |
+
"max_steps": 1085,
|
| 84 |
+
"num_train_epochs": 5,
|
| 85 |
+
"total_flos": 6.483891179980063e+18,
|
| 86 |
+
"trial_name": null,
|
| 87 |
+
"trial_params": null
|
| 88 |
+
}
|