Training in progress, step 5200, 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:f0702d85594ce6ee514a0e0692d371e1bc94d6c46ec49d359fe65d794755e17f
|
| 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 sha256:2a995bc9f14f43eeb41ca1ce255085c8fde14b40bdbcc4e45d52a30319b044a0
|
| 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 sha256:83255ff76b8ac807dd1f713bebeaf80ad6e4b35445f83355101327f5253d02f7
|
| 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":
|
| 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,
|
|
@@ -9350,6 +9350,24 @@
|
|
| 9350 |
"mean_token_accuracy": 0.6525659114122391,
|
| 9351 |
"num_tokens": 18928215.0,
|
| 9352 |
"step": 5190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9353 |
}
|
| 9354 |
],
|
| 9355 |
"logging_steps": 5,
|
|
@@ -9369,7 +9387,7 @@
|
|
| 9369 |
"attributes": {}
|
| 9370 |
}
|
| 9371 |
},
|
| 9372 |
-
"total_flos": 9.
|
| 9373 |
"train_batch_size": 4,
|
| 9374 |
"trial_name": null,
|
| 9375 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 40.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9350 |
"mean_token_accuracy": 0.6525659114122391,
|
| 9351 |
"num_tokens": 18928215.0,
|
| 9352 |
"step": 5190
|
| 9353 |
+
},
|
| 9354 |
+
{
|
| 9355 |
+
"epoch": 39.96153846153846,
|
| 9356 |
+
"grad_norm": 0.0,
|
| 9357 |
+
"learning_rate": 2.4030000000000002e-05,
|
| 9358 |
+
"loss": 1.705,
|
| 9359 |
+
"mean_token_accuracy": 0.6562006801366806,
|
| 9360 |
+
"num_tokens": 18946708.0,
|
| 9361 |
+
"step": 5195
|
| 9362 |
+
},
|
| 9363 |
+
{
|
| 9364 |
+
"epoch": 40.0,
|
| 9365 |
+
"grad_norm": 0.0,
|
| 9366 |
+
"learning_rate": 2.4005e-05,
|
| 9367 |
+
"loss": 1.7572,
|
| 9368 |
+
"mean_token_accuracy": 0.6535427123308182,
|
| 9369 |
+
"num_tokens": 18964200.0,
|
| 9370 |
+
"step": 5200
|
| 9371 |
}
|
| 9372 |
],
|
| 9373 |
"logging_steps": 5,
|
|
|
|
| 9387 |
"attributes": {}
|
| 9388 |
}
|
| 9389 |
},
|
| 9390 |
+
"total_flos": 9.609502877628826e+17,
|
| 9391 |
"train_batch_size": 4,
|
| 9392 |
"trial_name": null,
|
| 9393 |
"trial_params": null
|