Training in progress, step 4170, 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:c05d825a0e5c91190ea47cbe99e31d6447f1ef8e7c98902328919fd45e587d88
|
| 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 sha256:97a1be281ebffb518a1486a85541a7c4baca587dabb63864a97049bf046a4551
|
| 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:f181ffc3df1fd257fbc3907860a48f1e803cd2d2a2a38f646821bb97a17ef80e
|
| 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": 32.
|
| 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,
|
|
@@ -7496,6 +7496,24 @@
|
|
| 7496 |
"mean_token_accuracy": 0.6500423729419709,
|
| 7497 |
"num_tokens": 15171360.0,
|
| 7498 |
"step": 4160
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7499 |
}
|
| 7500 |
],
|
| 7501 |
"logging_steps": 5,
|
|
@@ -7515,7 +7533,7 @@
|
|
| 7515 |
"attributes": {}
|
| 7516 |
}
|
| 7517 |
},
|
| 7518 |
-
"total_flos": 7.
|
| 7519 |
"train_batch_size": 4,
|
| 7520 |
"trial_name": null,
|
| 7521 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4170,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7496 |
"mean_token_accuracy": 0.6500423729419709,
|
| 7497 |
"num_tokens": 15171360.0,
|
| 7498 |
"step": 4160
|
| 7499 |
+
},
|
| 7500 |
+
{
|
| 7501 |
+
"epoch": 32.03846153846154,
|
| 7502 |
+
"grad_norm": 0.0,
|
| 7503 |
+
"learning_rate": 2.9180000000000002e-05,
|
| 7504 |
+
"loss": 1.7394,
|
| 7505 |
+
"mean_token_accuracy": 0.6556807518005371,
|
| 7506 |
+
"num_tokens": 15189772.0,
|
| 7507 |
+
"step": 4165
|
| 7508 |
+
},
|
| 7509 |
+
{
|
| 7510 |
+
"epoch": 32.07692307692308,
|
| 7511 |
+
"grad_norm": 0.0,
|
| 7512 |
+
"learning_rate": 2.9154999999999998e-05,
|
| 7513 |
+
"loss": 1.6884,
|
| 7514 |
+
"mean_token_accuracy": 0.6571320801973343,
|
| 7515 |
+
"num_tokens": 15208356.0,
|
| 7516 |
+
"step": 4170
|
| 7517 |
}
|
| 7518 |
],
|
| 7519 |
"logging_steps": 5,
|
|
|
|
| 7533 |
"attributes": {}
|
| 7534 |
}
|
| 7535 |
},
|
| 7536 |
+
"total_flos": 7.708055914163405e+17,
|
| 7537 |
"train_batch_size": 4,
|
| 7538 |
"trial_name": null,
|
| 7539 |
"trial_params": null
|