Training in progress, step 8330, 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 sha256:70d5a8e584f4b958392ac0f9ce889e4fd168178efb50f10b2a1623595b052acc
|
| 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 sha256:7e4752df61ac40b46fa855bcc4acdafe94b48b41c58a4b28d89fe45756a4a878
|
| 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 sha256:438c87cae98ce7fa401e545fd0b9836a1c697ad01943b6244853fb264a365c94
|
| 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": 64.
|
| 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,
|
|
@@ -14984,6 +14984,24 @@
|
|
| 14984 |
"mean_token_accuracy": 0.647731038928032,
|
| 14985 |
"num_tokens": 30342720.0,
|
| 14986 |
"step": 8320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14987 |
}
|
| 14988 |
],
|
| 14989 |
"logging_steps": 5,
|
|
@@ -15003,7 +15021,7 @@
|
|
| 15003 |
"attributes": {}
|
| 15004 |
}
|
| 15005 |
},
|
| 15006 |
-
"total_flos": 1.
|
| 15007 |
"train_batch_size": 4,
|
| 15008 |
"trial_name": null,
|
| 15009 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14984 |
"mean_token_accuracy": 0.647731038928032,
|
| 14985 |
"num_tokens": 30342720.0,
|
| 14986 |
"step": 8320
|
| 14987 |
+
},
|
| 14988 |
+
{
|
| 14989 |
+
"epoch": 64.03846153846153,
|
| 14990 |
+
"grad_norm": 0.0,
|
| 14991 |
+
"learning_rate": 8.380000000000001e-06,
|
| 14992 |
+
"loss": 1.7291,
|
| 14993 |
+
"mean_token_accuracy": 0.6533550292253494,
|
| 14994 |
+
"num_tokens": 30360719.0,
|
| 14995 |
+
"step": 8325
|
| 14996 |
+
},
|
| 14997 |
+
{
|
| 14998 |
+
"epoch": 64.07692307692308,
|
| 14999 |
+
"grad_norm": 0.0,
|
| 15000 |
+
"learning_rate": 8.355e-06,
|
| 15001 |
+
"loss": 1.7221,
|
| 15002 |
+
"mean_token_accuracy": 0.6565493553876877,
|
| 15003 |
+
"num_tokens": 30379966.0,
|
| 15004 |
+
"step": 8330
|
| 15005 |
}
|
| 15006 |
],
|
| 15007 |
"logging_steps": 5,
|
|
|
|
| 15021 |
"attributes": {}
|
| 15022 |
}
|
| 15023 |
},
|
| 15024 |
+
"total_flos": 1.540318561803141e+18,
|
| 15025 |
"train_batch_size": 4,
|
| 15026 |
"trial_name": null,
|
| 15027 |
"trial_params": null
|