Training in progress, step 5550, 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 sha256:06a9824786ceaa16e6b033765346cb273288f2311c3545e861cb3d00432ed1d8
|
| 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 sha256:38814f316cf08480b98595ec43e552f50ef5eafc3066e951eb2b48a142b8c35a
|
| 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:f72b52b08f4aaf0bf43be3b535b058d8f16afa33d6c672ee2df5dde607f7f6de
|
| 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": 42.
|
| 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,
|
|
@@ -9980,6 +9980,24 @@
|
|
| 9980 |
"mean_token_accuracy": 0.658808296918869,
|
| 9981 |
"num_tokens": 20203744.0,
|
| 9982 |
"step": 5540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9983 |
}
|
| 9984 |
],
|
| 9985 |
"logging_steps": 5,
|
|
@@ -9999,7 +10017,7 @@
|
|
| 9999 |
"attributes": {}
|
| 10000 |
}
|
| 10001 |
},
|
| 10002 |
-
"total_flos": 1.
|
| 10003 |
"train_batch_size": 4,
|
| 10004 |
"trial_name": null,
|
| 10005 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 42.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5550,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9980 |
"mean_token_accuracy": 0.658808296918869,
|
| 9981 |
"num_tokens": 20203744.0,
|
| 9982 |
"step": 5540
|
| 9983 |
+
},
|
| 9984 |
+
{
|
| 9985 |
+
"epoch": 42.65384615384615,
|
| 9986 |
+
"grad_norm": 0.0,
|
| 9987 |
+
"learning_rate": 2.228e-05,
|
| 9988 |
+
"loss": 1.6489,
|
| 9989 |
+
"mean_token_accuracy": 0.6704173415899277,
|
| 9990 |
+
"num_tokens": 20222753.0,
|
| 9991 |
+
"step": 5545
|
| 9992 |
+
},
|
| 9993 |
+
{
|
| 9994 |
+
"epoch": 42.69230769230769,
|
| 9995 |
+
"grad_norm": 0.0,
|
| 9996 |
+
"learning_rate": 2.2255e-05,
|
| 9997 |
+
"loss": 1.7507,
|
| 9998 |
+
"mean_token_accuracy": 0.6489108324050903,
|
| 9999 |
+
"num_tokens": 20241135.0,
|
| 10000 |
+
"step": 5550
|
| 10001 |
}
|
| 10002 |
],
|
| 10003 |
"logging_steps": 5,
|
|
|
|
| 10017 |
"attributes": {}
|
| 10018 |
}
|
| 10019 |
},
|
| 10020 |
+
"total_flos": 1.0256700967826227e+18,
|
| 10021 |
"train_batch_size": 4,
|
| 10022 |
"trial_name": null,
|
| 10023 |
"trial_params": null
|