Training in progress, step 2560, 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 sha256:8973d45c28924aab59eb249f2923c8b22c953cc67f54976f8d9437508a81704f
|
| 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 sha256:5c75a9706e6e6ba58e25d1c18b9335538abb438d4f97180ee9e78d6f0642aba0
|
| 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:ebfa81ce252ed90aa80204049fa611e50ac4e4f9c72618a3929aefdf1996f26e
|
| 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": 19.
|
| 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,
|
|
@@ -4598,6 +4598,24 @@
|
|
| 4598 |
"mean_token_accuracy": 0.6443462133407593,
|
| 4599 |
"num_tokens": 9299236.0,
|
| 4600 |
"step": 2550
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4601 |
}
|
| 4602 |
],
|
| 4603 |
"logging_steps": 5,
|
|
@@ -4617,7 +4635,7 @@
|
|
| 4617 |
"attributes": {}
|
| 4618 |
}
|
| 4619 |
},
|
| 4620 |
-
"total_flos": 4.
|
| 4621 |
"train_batch_size": 4,
|
| 4622 |
"trial_name": null,
|
| 4623 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.692307692307693,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2560,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4598 |
"mean_token_accuracy": 0.6443462133407593,
|
| 4599 |
"num_tokens": 9299236.0,
|
| 4600 |
"step": 2550
|
| 4601 |
+
},
|
| 4602 |
+
{
|
| 4603 |
+
"epoch": 19.653846153846153,
|
| 4604 |
+
"grad_norm": 0.0,
|
| 4605 |
+
"learning_rate": 3.723e-05,
|
| 4606 |
+
"loss": 1.7594,
|
| 4607 |
+
"mean_token_accuracy": 0.6466510325670243,
|
| 4608 |
+
"num_tokens": 9317391.0,
|
| 4609 |
+
"step": 2555
|
| 4610 |
+
},
|
| 4611 |
+
{
|
| 4612 |
+
"epoch": 19.692307692307693,
|
| 4613 |
+
"grad_norm": 0.0,
|
| 4614 |
+
"learning_rate": 3.7205e-05,
|
| 4615 |
+
"loss": 1.6792,
|
| 4616 |
+
"mean_token_accuracy": 0.6581139594316483,
|
| 4617 |
+
"num_tokens": 9336860.0,
|
| 4618 |
+
"step": 2560
|
| 4619 |
}
|
| 4620 |
],
|
| 4621 |
"logging_steps": 5,
|
|
|
|
| 4635 |
"attributes": {}
|
| 4636 |
}
|
| 4637 |
},
|
| 4638 |
+
"total_flos": 4.7319694598651904e+17,
|
| 4639 |
"train_batch_size": 4,
|
| 4640 |
"trial_name": null,
|
| 4641 |
"trial_params": null
|