Training in progress, step 6660, 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 sha256:4d59be5b9b2441a7c794a6368e4f42cc213fd55e453fb3901dcedd7f2a7c8c37
|
| 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:cb7d1b32a7f4dbaec40cd6ce21bd3e377aae08c1a232fcb346709f1039389367
|
| 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 sha256:5feb6d03038304d32def737b8debb69c5dc683765e49c92dd9bb804339a007f1
|
| 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": 51.
|
| 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,
|
|
@@ -11978,6 +11978,24 @@
|
|
| 11978 |
"mean_token_accuracy": 0.64230475127697,
|
| 11979 |
"num_tokens": 24252383.0,
|
| 11980 |
"step": 6650
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11981 |
}
|
| 11982 |
],
|
| 11983 |
"logging_steps": 5,
|
|
@@ -11997,7 +12015,7 @@
|
|
| 11997 |
"attributes": {}
|
| 11998 |
}
|
| 11999 |
},
|
| 12000 |
-
"total_flos": 1.
|
| 12001 |
"train_batch_size": 4,
|
| 12002 |
"trial_name": null,
|
| 12003 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6660,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11978 |
"mean_token_accuracy": 0.64230475127697,
|
| 11979 |
"num_tokens": 24252383.0,
|
| 11980 |
"step": 6650
|
| 11981 |
+
},
|
| 11982 |
+
{
|
| 11983 |
+
"epoch": 51.19230769230769,
|
| 11984 |
+
"grad_norm": 0.0,
|
| 11985 |
+
"learning_rate": 1.673e-05,
|
| 11986 |
+
"loss": 1.7651,
|
| 11987 |
+
"mean_token_accuracy": 0.6459890872240066,
|
| 11988 |
+
"num_tokens": 24270356.0,
|
| 11989 |
+
"step": 6655
|
| 11990 |
+
},
|
| 11991 |
+
{
|
| 11992 |
+
"epoch": 51.23076923076923,
|
| 11993 |
+
"grad_norm": 0.0,
|
| 11994 |
+
"learning_rate": 1.6705e-05,
|
| 11995 |
+
"loss": 1.7523,
|
| 11996 |
+
"mean_token_accuracy": 0.6558059513568878,
|
| 11997 |
+
"num_tokens": 24288236.0,
|
| 11998 |
+
"step": 6660
|
| 11999 |
}
|
| 12000 |
],
|
| 12001 |
"logging_steps": 5,
|
|
|
|
| 12015 |
"attributes": {}
|
| 12016 |
}
|
| 12017 |
},
|
| 12018 |
+
"total_flos": 1.231327039379374e+18,
|
| 12019 |
"train_batch_size": 4,
|
| 12020 |
"trial_name": null,
|
| 12021 |
"trial_params": null
|