Training in progress, step 8340, 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:cf4afc00292f9ee33bac17d555767bb8fc9747e68bbe9275a19bde1ae9ea32d2
|
| 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 sha256:2e38bcce26ab8b876d5e0d037743818f9412dc2721a7494776417061d06a3aa3
|
| 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:f677fd17db22bfc045fd62fec7ec4975f9e06c151949c15afe1db81e69e2f1b6
|
| 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,
|
|
@@ -15002,6 +15002,24 @@
|
|
| 15002 |
"mean_token_accuracy": 0.6565493553876877,
|
| 15003 |
"num_tokens": 30379966.0,
|
| 15004 |
"step": 8330
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15005 |
}
|
| 15006 |
],
|
| 15007 |
"logging_steps": 5,
|
|
@@ -15021,7 +15039,7 @@
|
|
| 15021 |
"attributes": {}
|
| 15022 |
}
|
| 15023 |
},
|
| 15024 |
-
"total_flos": 1.
|
| 15025 |
"train_batch_size": 4,
|
| 15026 |
"trial_name": null,
|
| 15027 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 64.15384615384616,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8340,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15002 |
"mean_token_accuracy": 0.6565493553876877,
|
| 15003 |
"num_tokens": 30379966.0,
|
| 15004 |
"step": 8330
|
| 15005 |
+
},
|
| 15006 |
+
{
|
| 15007 |
+
"epoch": 64.11538461538461,
|
| 15008 |
+
"grad_norm": 0.0,
|
| 15009 |
+
"learning_rate": 8.33e-06,
|
| 15010 |
+
"loss": 1.6687,
|
| 15011 |
+
"mean_token_accuracy": 0.6646548688411713,
|
| 15012 |
+
"num_tokens": 30398817.0,
|
| 15013 |
+
"step": 8335
|
| 15014 |
+
},
|
| 15015 |
+
{
|
| 15016 |
+
"epoch": 64.15384615384616,
|
| 15017 |
+
"grad_norm": 0.0,
|
| 15018 |
+
"learning_rate": 8.305000000000001e-06,
|
| 15019 |
+
"loss": 1.8145,
|
| 15020 |
+
"mean_token_accuracy": 0.6381383389234543,
|
| 15021 |
+
"num_tokens": 30416271.0,
|
| 15022 |
+
"step": 8340
|
| 15023 |
}
|
| 15024 |
],
|
| 15025 |
"logging_steps": 5,
|
|
|
|
| 15039 |
"attributes": {}
|
| 15040 |
}
|
| 15041 |
},
|
| 15042 |
+
"total_flos": 1.5421526197213594e+18,
|
| 15043 |
"train_batch_size": 4,
|
| 15044 |
"trial_name": null,
|
| 15045 |
"trial_params": null
|