Training in progress, step 1960, 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 sha256:4ee4db074f7a4f31c15aad76c2cd01d8a7298f540c6a11f0833dadcc165afeee
|
| 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:c28072ea9fe82cd18d1a6568215b156d2aaa97c8882648a133942429e4bd4775
|
| 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 sha256:9d7ab53aa7ad18f00c3d3335f301bef121722a496da7eb551e83e42fb217bab4
|
| 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": 15.
|
| 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,
|
|
@@ -3518,6 +3518,24 @@
|
|
| 3518 |
"mean_token_accuracy": 0.6624333202838898,
|
| 3519 |
"num_tokens": 7111575.0,
|
| 3520 |
"step": 1950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3521 |
}
|
| 3522 |
],
|
| 3523 |
"logging_steps": 5,
|
|
@@ -3537,7 +3555,7 @@
|
|
| 3537 |
"attributes": {}
|
| 3538 |
}
|
| 3539 |
},
|
| 3540 |
-
"total_flos": 3.
|
| 3541 |
"train_batch_size": 4,
|
| 3542 |
"trial_name": null,
|
| 3543 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 15.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1960,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3518 |
"mean_token_accuracy": 0.6624333202838898,
|
| 3519 |
"num_tokens": 7111575.0,
|
| 3520 |
"step": 1950
|
| 3521 |
+
},
|
| 3522 |
+
{
|
| 3523 |
+
"epoch": 15.038461538461538,
|
| 3524 |
+
"grad_norm": 0.0,
|
| 3525 |
+
"learning_rate": 4.023e-05,
|
| 3526 |
+
"loss": 1.7382,
|
| 3527 |
+
"mean_token_accuracy": 0.6494399189949036,
|
| 3528 |
+
"num_tokens": 7130012.0,
|
| 3529 |
+
"step": 1955
|
| 3530 |
+
},
|
| 3531 |
+
{
|
| 3532 |
+
"epoch": 15.076923076923077,
|
| 3533 |
+
"grad_norm": 0.0,
|
| 3534 |
+
"learning_rate": 4.0205000000000006e-05,
|
| 3535 |
+
"loss": 1.7673,
|
| 3536 |
+
"mean_token_accuracy": 0.6474148839712143,
|
| 3537 |
+
"num_tokens": 7147764.0,
|
| 3538 |
+
"step": 1960
|
| 3539 |
}
|
| 3540 |
],
|
| 3541 |
"logging_steps": 5,
|
|
|
|
| 3555 |
"attributes": {}
|
| 3556 |
}
|
| 3557 |
},
|
| 3558 |
+
"total_flos": 3.621029880619008e+17,
|
| 3559 |
"train_batch_size": 4,
|
| 3560 |
"trial_name": null,
|
| 3561 |
"trial_params": null
|