Training in progress, step 8020, 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 sha256:3e66ac9dc9fd4e35fb82c902c3929cd8a0b0f58c617ab7e7437c8451cc6916cf
|
| 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:c2439094b5e816a99df321ac4d1320d7301adfe98564f4c828caa28219c350aa
|
| 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:b03b1133f5c0a9c42ea07a09ec1ff9d606278cddecd510097dda743f9a77c8ac
|
| 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": 61.
|
| 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,
|
|
@@ -14426,6 +14426,24 @@
|
|
| 14426 |
"mean_token_accuracy": 0.6574147075414658,
|
| 14427 |
"num_tokens": 29211106.0,
|
| 14428 |
"step": 8010
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14429 |
}
|
| 14430 |
],
|
| 14431 |
"logging_steps": 5,
|
|
@@ -14445,7 +14463,7 @@
|
|
| 14445 |
"attributes": {}
|
| 14446 |
}
|
| 14447 |
},
|
| 14448 |
-
"total_flos": 1.
|
| 14449 |
"train_batch_size": 4,
|
| 14450 |
"trial_name": null,
|
| 14451 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 61.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8020,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14426 |
"mean_token_accuracy": 0.6574147075414658,
|
| 14427 |
"num_tokens": 29211106.0,
|
| 14428 |
"step": 8010
|
| 14429 |
+
},
|
| 14430 |
+
{
|
| 14431 |
+
"epoch": 61.65384615384615,
|
| 14432 |
+
"grad_norm": 0.0,
|
| 14433 |
+
"learning_rate": 9.93e-06,
|
| 14434 |
+
"loss": 1.6859,
|
| 14435 |
+
"mean_token_accuracy": 0.6642335325479507,
|
| 14436 |
+
"num_tokens": 29230108.0,
|
| 14437 |
+
"step": 8015
|
| 14438 |
+
},
|
| 14439 |
+
{
|
| 14440 |
+
"epoch": 61.69230769230769,
|
| 14441 |
+
"grad_norm": 0.0,
|
| 14442 |
+
"learning_rate": 9.905000000000001e-06,
|
| 14443 |
+
"loss": 1.8063,
|
| 14444 |
+
"mean_token_accuracy": 0.6333356082439423,
|
| 14445 |
+
"num_tokens": 29247611.0,
|
| 14446 |
+
"step": 8020
|
| 14447 |
}
|
| 14448 |
],
|
| 14449 |
"logging_steps": 5,
|
|
|
|
| 14463 |
"attributes": {}
|
| 14464 |
}
|
| 14465 |
},
|
| 14466 |
+
"total_flos": 1.4828441627846246e+18,
|
| 14467 |
"train_batch_size": 4,
|
| 14468 |
"trial_name": null,
|
| 14469 |
"trial_params": null
|