Training in progress, step 9210, 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 sha256:6a9f8d5f990d64ac07c5ed0d8aa83f6d6a30b30a4d1b2c1474ba624310106615
|
| 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 sha256:267f4bf1bec61e9dce96a1d2c0c9f019a602cb6f03d9b42f59ae7d5dece2e993
|
| 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:c8062a99580576cb3724e6a268d7fb2cb9a258830d4c09deb2a5ee552a88aca6
|
| 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,
|
|
@@ -16568,6 +16568,24 @@
|
|
| 16568 |
"mean_token_accuracy": 0.6561136662960052,
|
| 16569 |
"num_tokens": 33551333.0,
|
| 16570 |
"step": 9200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16571 |
}
|
| 16572 |
],
|
| 16573 |
"logging_steps": 5,
|
|
@@ -16587,7 +16605,7 @@
|
|
| 16587 |
"attributes": {}
|
| 16588 |
}
|
| 16589 |
},
|
| 16590 |
-
"total_flos": 1.
|
| 16591 |
"train_batch_size": 4,
|
| 16592 |
"trial_name": null,
|
| 16593 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16568 |
"mean_token_accuracy": 0.6561136662960052,
|
| 16569 |
"num_tokens": 33551333.0,
|
| 16570 |
"step": 9200
|
| 16571 |
+
},
|
| 16572 |
+
{
|
| 16573 |
+
"epoch": 70.8076923076923,
|
| 16574 |
+
"grad_norm": 0.0,
|
| 16575 |
+
"learning_rate": 3.98e-06,
|
| 16576 |
+
"loss": 1.793,
|
| 16577 |
+
"mean_token_accuracy": 0.6400943785905838,
|
| 16578 |
+
"num_tokens": 33569017.0,
|
| 16579 |
+
"step": 9205
|
| 16580 |
+
},
|
| 16581 |
+
{
|
| 16582 |
+
"epoch": 70.84615384615384,
|
| 16583 |
+
"grad_norm": 0.0,
|
| 16584 |
+
"learning_rate": 3.955e-06,
|
| 16585 |
+
"loss": 1.7658,
|
| 16586 |
+
"mean_token_accuracy": 0.6454756885766983,
|
| 16587 |
+
"num_tokens": 33587052.0,
|
| 16588 |
+
"step": 9210
|
| 16589 |
}
|
| 16590 |
],
|
| 16591 |
"logging_steps": 5,
|
|
|
|
| 16605 |
"attributes": {}
|
| 16606 |
}
|
| 16607 |
},
|
| 16608 |
+
"total_flos": 1.7030689332697498e+18,
|
| 16609 |
"train_batch_size": 4,
|
| 16610 |
"trial_name": null,
|
| 16611 |
"trial_params": null
|