Training in progress, step 9440, 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 sha256:56381ef4d082420d415b3ac50f7ac7c7dbc6372b7c5e8706fc9f6ff6ad73316c
|
| 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 sha256:3719fb062e0404ffb95a75d729c7a8fcc5b9a10aca807308364a0b7d0222c706
|
| 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 sha256:0c1bca82df80e9efa6f6b957c1c36125a35f61e18b8bf14b92a76375792baeac
|
| 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": 72.
|
| 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,
|
|
@@ -16982,6 +16982,24 @@
|
|
| 16982 |
"mean_token_accuracy": 0.64038887321949,
|
| 16983 |
"num_tokens": 34391352.0,
|
| 16984 |
"step": 9430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16985 |
}
|
| 16986 |
],
|
| 16987 |
"logging_steps": 5,
|
|
@@ -17001,7 +17019,7 @@
|
|
| 17001 |
"attributes": {}
|
| 17002 |
}
|
| 17003 |
},
|
| 17004 |
-
"total_flos": 1.
|
| 17005 |
"train_batch_size": 4,
|
| 17006 |
"trial_name": null,
|
| 17007 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16982 |
"mean_token_accuracy": 0.64038887321949,
|
| 16983 |
"num_tokens": 34391352.0,
|
| 16984 |
"step": 9430
|
| 16985 |
+
},
|
| 16986 |
+
{
|
| 16987 |
+
"epoch": 72.57692307692308,
|
| 16988 |
+
"grad_norm": 0.0,
|
| 16989 |
+
"learning_rate": 2.83e-06,
|
| 16990 |
+
"loss": 1.7532,
|
| 16991 |
+
"mean_token_accuracy": 0.6454617887735367,
|
| 16992 |
+
"num_tokens": 34409347.0,
|
| 16993 |
+
"step": 9435
|
| 16994 |
+
},
|
| 16995 |
+
{
|
| 16996 |
+
"epoch": 72.61538461538461,
|
| 16997 |
+
"grad_norm": 0.0,
|
| 16998 |
+
"learning_rate": 2.805e-06,
|
| 16999 |
+
"loss": 1.7184,
|
| 17000 |
+
"mean_token_accuracy": 0.6529299259185791,
|
| 17001 |
+
"num_tokens": 34427248.0,
|
| 17002 |
+
"step": 9440
|
| 17003 |
}
|
| 17004 |
],
|
| 17005 |
"logging_steps": 5,
|
|
|
|
| 17019 |
"attributes": {}
|
| 17020 |
}
|
| 17021 |
},
|
| 17022 |
+
"total_flos": 1.7457417814966272e+18,
|
| 17023 |
"train_batch_size": 4,
|
| 17024 |
"trial_name": null,
|
| 17025 |
"trial_params": null
|