Training in progress, step 3330, 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 sha256:1f5cb224a1785d016676daf1ab8dba090d42870ab8bce57a28164cd795285ba7
|
| 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:e476f0b6fd954296ad6fca08ae70cf5946603e0d34b740d84780f0705eac2ca7
|
| 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 sha256:6268a3afd6400a9701badd844a025e58582a996adb751dd7edcdd41f48bfcaec
|
| 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": 25.
|
| 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,
|
|
@@ -5984,6 +5984,24 @@
|
|
| 5984 |
"mean_token_accuracy": 0.6499413967132568,
|
| 5985 |
"num_tokens": 12105620.0,
|
| 5986 |
"step": 3320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5987 |
}
|
| 5988 |
],
|
| 5989 |
"logging_steps": 5,
|
|
@@ -6003,7 +6021,7 @@
|
|
| 6003 |
"attributes": {}
|
| 6004 |
}
|
| 6005 |
},
|
| 6006 |
-
"total_flos": 6.
|
| 6007 |
"train_batch_size": 4,
|
| 6008 |
"trial_name": null,
|
| 6009 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.615384615384617,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3330,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 5984 |
"mean_token_accuracy": 0.6499413967132568,
|
| 5985 |
"num_tokens": 12105620.0,
|
| 5986 |
"step": 3320
|
| 5987 |
+
},
|
| 5988 |
+
{
|
| 5989 |
+
"epoch": 25.576923076923077,
|
| 5990 |
+
"grad_norm": 0.0,
|
| 5991 |
+
"learning_rate": 3.338e-05,
|
| 5992 |
+
"loss": 1.7522,
|
| 5993 |
+
"mean_token_accuracy": 0.6516470074653625,
|
| 5994 |
+
"num_tokens": 12123634.0,
|
| 5995 |
+
"step": 3325
|
| 5996 |
+
},
|
| 5997 |
+
{
|
| 5998 |
+
"epoch": 25.615384615384617,
|
| 5999 |
+
"grad_norm": 0.0,
|
| 6000 |
+
"learning_rate": 3.3355e-05,
|
| 6001 |
+
"loss": 1.6871,
|
| 6002 |
+
"mean_token_accuracy": 0.6579142987728119,
|
| 6003 |
+
"num_tokens": 12142945.0,
|
| 6004 |
+
"step": 3330
|
| 6005 |
}
|
| 6006 |
],
|
| 6007 |
"logging_steps": 5,
|
|
|
|
| 6021 |
"attributes": {}
|
| 6022 |
}
|
| 6023 |
},
|
| 6024 |
+
"total_flos": 6.15244739691479e+17,
|
| 6025 |
"train_batch_size": 4,
|
| 6026 |
"trial_name": null,
|
| 6027 |
"trial_params": null
|