Training in progress, step 2520, 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 sha256:4a3293738941a25a2e0d5b2918082cc55660b754a12af1570d1175b1414259a4
|
| 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 sha256:0e75e9d59a9921f9c17e532c7f73f228c09faf8e8bef5d9bb2a0a5a5a2a3acca
|
| 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:ca321c7fda77c2e77a4e2e8305d327cce1c67c9d49aa660420826ccbf2d2c129
|
| 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": 19.
|
| 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,
|
|
@@ -4526,6 +4526,24 @@
|
|
| 4526 |
"mean_token_accuracy": 0.6623701632022858,
|
| 4527 |
"num_tokens": 9154044.0,
|
| 4528 |
"step": 2510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4529 |
}
|
| 4530 |
],
|
| 4531 |
"logging_steps": 5,
|
|
@@ -4545,7 +4563,7 @@
|
|
| 4545 |
"attributes": {}
|
| 4546 |
}
|
| 4547 |
},
|
| 4548 |
-
"total_flos": 4.
|
| 4549 |
"train_batch_size": 4,
|
| 4550 |
"trial_name": null,
|
| 4551 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2520,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4526 |
"mean_token_accuracy": 0.6623701632022858,
|
| 4527 |
"num_tokens": 9154044.0,
|
| 4528 |
"step": 2510
|
| 4529 |
+
},
|
| 4530 |
+
{
|
| 4531 |
+
"epoch": 19.346153846153847,
|
| 4532 |
+
"grad_norm": 0.0,
|
| 4533 |
+
"learning_rate": 3.7430000000000006e-05,
|
| 4534 |
+
"loss": 1.7474,
|
| 4535 |
+
"mean_token_accuracy": 0.6527136623859405,
|
| 4536 |
+
"num_tokens": 9172242.0,
|
| 4537 |
+
"step": 2515
|
| 4538 |
+
},
|
| 4539 |
+
{
|
| 4540 |
+
"epoch": 19.384615384615383,
|
| 4541 |
+
"grad_norm": 0.0,
|
| 4542 |
+
"learning_rate": 3.7405e-05,
|
| 4543 |
+
"loss": 1.7387,
|
| 4544 |
+
"mean_token_accuracy": 0.647335684299469,
|
| 4545 |
+
"num_tokens": 9190090.0,
|
| 4546 |
+
"step": 2520
|
| 4547 |
}
|
| 4548 |
],
|
| 4549 |
"logging_steps": 5,
|
|
|
|
| 4563 |
"attributes": {}
|
| 4564 |
}
|
| 4565 |
},
|
| 4566 |
+
"total_flos": 4.6570225272569856e+17,
|
| 4567 |
"train_batch_size": 4,
|
| 4568 |
"trial_name": null,
|
| 4569 |
"trial_params": null
|