Training in progress, step 8070, 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:ed741aabb301cd1adde6a657a015fa6b82a210470e6337616cb60321179d06cd
|
| 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:f296e4f2a29fbfc7d6b897bc9138271a194ec485fb1345d73446ecf7069e881b
|
| 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 sha256:3ae95390229726ca7bc0fe0883ffa817e11f9a440174d6eff8fde89209fb1648
|
| 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": 62.
|
| 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,
|
|
@@ -14516,6 +14516,24 @@
|
|
| 14516 |
"mean_token_accuracy": 0.6440939038991929,
|
| 14517 |
"num_tokens": 29394510.0,
|
| 14518 |
"step": 8060
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14519 |
}
|
| 14520 |
],
|
| 14521 |
"logging_steps": 5,
|
|
@@ -14535,7 +14553,7 @@
|
|
| 14535 |
"attributes": {}
|
| 14536 |
}
|
| 14537 |
},
|
| 14538 |
-
"total_flos": 1.
|
| 14539 |
"train_batch_size": 4,
|
| 14540 |
"trial_name": null,
|
| 14541 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 62.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8070,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14516 |
"mean_token_accuracy": 0.6440939038991929,
|
| 14517 |
"num_tokens": 29394510.0,
|
| 14518 |
"step": 8060
|
| 14519 |
+
},
|
| 14520 |
+
{
|
| 14521 |
+
"epoch": 62.03846153846154,
|
| 14522 |
+
"grad_norm": 0.0,
|
| 14523 |
+
"learning_rate": 9.68e-06,
|
| 14524 |
+
"loss": 1.7601,
|
| 14525 |
+
"mean_token_accuracy": 0.6529957592487335,
|
| 14526 |
+
"num_tokens": 29412388.0,
|
| 14527 |
+
"step": 8065
|
| 14528 |
+
},
|
| 14529 |
+
{
|
| 14530 |
+
"epoch": 62.07692307692308,
|
| 14531 |
+
"grad_norm": 0.0,
|
| 14532 |
+
"learning_rate": 9.655e-06,
|
| 14533 |
+
"loss": 1.754,
|
| 14534 |
+
"mean_token_accuracy": 0.6488070756196975,
|
| 14535 |
+
"num_tokens": 29430324.0,
|
| 14536 |
+
"step": 8070
|
| 14537 |
}
|
| 14538 |
],
|
| 14539 |
"logging_steps": 5,
|
|
|
|
| 14553 |
"attributes": {}
|
| 14554 |
}
|
| 14555 |
},
|
| 14556 |
+
"total_flos": 1.4920458906466714e+18,
|
| 14557 |
"train_batch_size": 4,
|
| 14558 |
"trial_name": null,
|
| 14559 |
"trial_params": null
|