Training in progress, step 9200, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e082a919c3564b7f976194188cc740ffe117da28614bb65505a06eb634a65223
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9a2db68b1d61761df8270265cb01791dddf38a38d1fa3a9895ccd741a40551a
|
| 3 |
size 14709
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61271585fcf1946937c9c79c19f082a86aa8686835f01061150bb7624930d0b8
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 70.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -16550,6 +16550,24 @@
|
|
| 16550 |
"mean_token_accuracy": 0.6407651424407959,
|
| 16551 |
"num_tokens": 33515029.0,
|
| 16552 |
"step": 9190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16553 |
}
|
| 16554 |
],
|
| 16555 |
"logging_steps": 5,
|
|
@@ -16569,7 +16587,7 @@
|
|
| 16569 |
"attributes": {}
|
| 16570 |
}
|
| 16571 |
},
|
| 16572 |
-
"total_flos": 1.
|
| 16573 |
"train_batch_size": 4,
|
| 16574 |
"trial_name": null,
|
| 16575 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16550 |
"mean_token_accuracy": 0.6407651424407959,
|
| 16551 |
"num_tokens": 33515029.0,
|
| 16552 |
"step": 9190
|
| 16553 |
+
},
|
| 16554 |
+
{
|
| 16555 |
+
"epoch": 70.73076923076923,
|
| 16556 |
+
"grad_norm": 0.0,
|
| 16557 |
+
"learning_rate": 4.03e-06,
|
| 16558 |
+
"loss": 1.677,
|
| 16559 |
+
"mean_token_accuracy": 0.6583020657300949,
|
| 16560 |
+
"num_tokens": 33533481.0,
|
| 16561 |
+
"step": 9195
|
| 16562 |
+
},
|
| 16563 |
+
{
|
| 16564 |
+
"epoch": 70.76923076923077,
|
| 16565 |
+
"grad_norm": 0.0,
|
| 16566 |
+
"learning_rate": 4.005000000000001e-06,
|
| 16567 |
+
"loss": 1.7266,
|
| 16568 |
+
"mean_token_accuracy": 0.6561136662960052,
|
| 16569 |
+
"num_tokens": 33551333.0,
|
| 16570 |
+
"step": 9200
|
| 16571 |
}
|
| 16572 |
],
|
| 16573 |
"logging_steps": 5,
|
|
|
|
| 16587 |
"attributes": {}
|
| 16588 |
}
|
| 16589 |
},
|
| 16590 |
+
"total_flos": 1.7012798098499174e+18,
|
| 16591 |
"train_batch_size": 4,
|
| 16592 |
"trial_name": null,
|
| 16593 |
"trial_params": null
|