Training in progress, step 4180, 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 sha256:56aaca147b7b96b9c534d3a12a3a81b4a10c45ebdfd027278add86654e6cd2d5
|
| 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 sha256:61cc9de6f50d5e06dcd50311b88ee0bccf7b0325b9bd0679bcc2fcbcb7c11bd7
|
| 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:ac831dd9b33cee3a24a791892e958f40f1f2a626d875af6ff6e6d4e8b5875d94
|
| 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,
|
|
@@ -7514,6 +7514,24 @@
|
|
| 7514 |
"mean_token_accuracy": 0.6571320801973343,
|
| 7515 |
"num_tokens": 15208356.0,
|
| 7516 |
"step": 4170
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7517 |
}
|
| 7518 |
],
|
| 7519 |
"logging_steps": 5,
|
|
@@ -7533,7 +7551,7 @@
|
|
| 7533 |
"attributes": {}
|
| 7534 |
}
|
| 7535 |
},
|
| 7536 |
-
"total_flos": 7.
|
| 7537 |
"train_batch_size": 4,
|
| 7538 |
"trial_name": null,
|
| 7539 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4180,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7514 |
"mean_token_accuracy": 0.6571320801973343,
|
| 7515 |
"num_tokens": 15208356.0,
|
| 7516 |
"step": 4170
|
| 7517 |
+
},
|
| 7518 |
+
{
|
| 7519 |
+
"epoch": 32.11538461538461,
|
| 7520 |
+
"grad_norm": 0.0,
|
| 7521 |
+
"learning_rate": 2.913e-05,
|
| 7522 |
+
"loss": 1.7331,
|
| 7523 |
+
"mean_token_accuracy": 0.6546037912368774,
|
| 7524 |
+
"num_tokens": 15225973.0,
|
| 7525 |
+
"step": 4175
|
| 7526 |
+
},
|
| 7527 |
+
{
|
| 7528 |
+
"epoch": 32.15384615384615,
|
| 7529 |
+
"grad_norm": 0.0,
|
| 7530 |
+
"learning_rate": 2.9105e-05,
|
| 7531 |
+
"loss": 1.7188,
|
| 7532 |
+
"mean_token_accuracy": 0.6566130489110946,
|
| 7533 |
+
"num_tokens": 15244498.0,
|
| 7534 |
+
"step": 4180
|
| 7535 |
}
|
| 7536 |
],
|
| 7537 |
"logging_steps": 5,
|
|
|
|
| 7551 |
"attributes": {}
|
| 7552 |
}
|
| 7553 |
},
|
| 7554 |
+
"total_flos": 7.726537806785741e+17,
|
| 7555 |
"train_batch_size": 4,
|
| 7556 |
"trial_name": null,
|
| 7557 |
"trial_params": null
|