Commit
·
64e1c60
1
Parent(s):
e814345
All Done!
Browse files
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_cer": 0.018459579885423297,
|
| 4 |
+
"eval_loss": 0.39753007888793945,
|
| 5 |
+
"eval_runtime": 21.4096,
|
| 6 |
+
"eval_samples_per_second": 15.274,
|
| 7 |
+
"eval_steps_per_second": 0.981,
|
| 8 |
+
"total_flos": 4.694072734336942e+17,
|
| 9 |
+
"train_loss": 0.8410020301012489,
|
| 10 |
+
"train_runtime": 361.7661,
|
| 11 |
+
"train_samples_per_second": 10.847,
|
| 12 |
+
"train_steps_per_second": 0.68
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_cer": 0.018459579885423297,
|
| 4 |
+
"eval_loss": 0.39753007888793945,
|
| 5 |
+
"eval_runtime": 21.4096,
|
| 6 |
+
"eval_samples_per_second": 15.274,
|
| 7 |
+
"eval_steps_per_second": 0.981
|
| 8 |
+
}
|
runs/Aug17_04-41-03_1839c420ad0b/events.out.tfevents.1692247714.1839c420ad0b.29.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59343b73b26d2c3c2e477070cb447bb0352cbc5f9b71aa458070d85b30551231
|
| 3 |
+
size 406
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 4.694072734336942e+17,
|
| 4 |
+
"train_loss": 0.8410020301012489,
|
| 5 |
+
"train_runtime": 361.7661,
|
| 6 |
+
"train_samples_per_second": 10.847,
|
| 7 |
+
"train_steps_per_second": 0.68
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 246,
|
| 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": 4.9796747967479676e-05,
|
| 13 |
+
"loss": 13.6251,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_cer": 0.12285168682367918,
|
| 19 |
+
"eval_loss": 0.5464695692062378,
|
| 20 |
+
"eval_runtime": 26.5959,
|
| 21 |
+
"eval_samples_per_second": 12.295,
|
| 22 |
+
"eval_steps_per_second": 0.79,
|
| 23 |
+
"step": 82
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 2.0,
|
| 27 |
+
"eval_cer": 0.02737110120942075,
|
| 28 |
+
"eval_loss": 0.4406394362449646,
|
| 29 |
+
"eval_runtime": 20.9773,
|
| 30 |
+
"eval_samples_per_second": 15.588,
|
| 31 |
+
"eval_steps_per_second": 1.001,
|
| 32 |
+
"step": 164
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 3.0,
|
| 36 |
+
"eval_cer": 0.018459579885423297,
|
| 37 |
+
"eval_loss": 0.39753007888793945,
|
| 38 |
+
"eval_runtime": 20.8038,
|
| 39 |
+
"eval_samples_per_second": 15.718,
|
| 40 |
+
"eval_steps_per_second": 1.009,
|
| 41 |
+
"step": 246
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 3.0,
|
| 45 |
+
"step": 246,
|
| 46 |
+
"total_flos": 4.694072734336942e+17,
|
| 47 |
+
"train_loss": 0.8410020301012489,
|
| 48 |
+
"train_runtime": 361.7661,
|
| 49 |
+
"train_samples_per_second": 10.847,
|
| 50 |
+
"train_steps_per_second": 0.68
|
| 51 |
+
}
|
| 52 |
+
],
|
| 53 |
+
"max_steps": 246,
|
| 54 |
+
"num_train_epochs": 3,
|
| 55 |
+
"total_flos": 4.694072734336942e+17,
|
| 56 |
+
"trial_name": null,
|
| 57 |
+
"trial_params": null
|
| 58 |
+
}
|