Training in progress, step 2480, 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 sha256:9e06b8209bf17b9b5e4a9914e27d23e6b8fa6faf6cd160a00c725dca665728f8
|
| 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:c8df067eaf1c2fd0c350b95ed692617c4fea0974b4fbd48fa49e3c64abae3672
|
| 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:e3baab88a21c1850cc4adc5bfcc6a97648cd7979b0be3f392cf99aa5ac3728ff
|
| 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,
|
|
@@ -4454,6 +4454,24 @@
|
|
| 4454 |
"mean_token_accuracy": 0.634514644742012,
|
| 4455 |
"num_tokens": 9007995.0,
|
| 4456 |
"step": 2470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4457 |
}
|
| 4458 |
],
|
| 4459 |
"logging_steps": 5,
|
|
@@ -4473,7 +4491,7 @@
|
|
| 4473 |
"attributes": {}
|
| 4474 |
}
|
| 4475 |
},
|
| 4476 |
-
"total_flos": 4.
|
| 4477 |
"train_batch_size": 4,
|
| 4478 |
"trial_name": null,
|
| 4479 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.076923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4454 |
"mean_token_accuracy": 0.634514644742012,
|
| 4455 |
"num_tokens": 9007995.0,
|
| 4456 |
"step": 2470
|
| 4457 |
+
},
|
| 4458 |
+
{
|
| 4459 |
+
"epoch": 19.03846153846154,
|
| 4460 |
+
"grad_norm": 0.0,
|
| 4461 |
+
"learning_rate": 3.7630000000000004e-05,
|
| 4462 |
+
"loss": 1.7192,
|
| 4463 |
+
"mean_token_accuracy": 0.6563860654830933,
|
| 4464 |
+
"num_tokens": 9026162.0,
|
| 4465 |
+
"step": 2475
|
| 4466 |
+
},
|
| 4467 |
+
{
|
| 4468 |
+
"epoch": 19.076923076923077,
|
| 4469 |
+
"grad_norm": 0.0,
|
| 4470 |
+
"learning_rate": 3.7605e-05,
|
| 4471 |
+
"loss": 1.7035,
|
| 4472 |
+
"mean_token_accuracy": 0.6546828061342239,
|
| 4473 |
+
"num_tokens": 9044982.0,
|
| 4474 |
+
"step": 2480
|
| 4475 |
}
|
| 4476 |
],
|
| 4477 |
"logging_steps": 5,
|
|
|
|
| 4491 |
"attributes": {}
|
| 4492 |
}
|
| 4493 |
},
|
| 4494 |
+
"total_flos": 4.583961890906112e+17,
|
| 4495 |
"train_batch_size": 4,
|
| 4496 |
"trial_name": null,
|
| 4497 |
"trial_params": null
|