Training in progress, step 9190, 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 sha256:9e7674f4ec3b6e5d24230d0c9d0eb1a7a4d1e537dcfd3c2ab3848e2cd095709a
|
| 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 sha256:71a92e7474c24291e9e19cbfeca1b0ed4d58093ce03ea9baad19155460c32d3f
|
| 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 sha256:4ba9625c17ccd223b15f3e8328cb9eb747df3d69baa91ee43702461889516f95
|
| 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": 70.
|
| 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,
|
|
@@ -16532,6 +16532,24 @@
|
|
| 16532 |
"mean_token_accuracy": 0.6452891588211059,
|
| 16533 |
"num_tokens": 33479921.0,
|
| 16534 |
"step": 9180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16535 |
}
|
| 16536 |
],
|
| 16537 |
"logging_steps": 5,
|
|
@@ -16551,7 +16569,7 @@
|
|
| 16551 |
"attributes": {}
|
| 16552 |
}
|
| 16553 |
},
|
| 16554 |
-
"total_flos": 1.
|
| 16555 |
"train_batch_size": 4,
|
| 16556 |
"trial_name": null,
|
| 16557 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 70.6923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9190,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16532 |
"mean_token_accuracy": 0.6452891588211059,
|
| 16533 |
"num_tokens": 33479921.0,
|
| 16534 |
"step": 9180
|
| 16535 |
+
},
|
| 16536 |
+
{
|
| 16537 |
+
"epoch": 70.65384615384616,
|
| 16538 |
+
"grad_norm": 0.0,
|
| 16539 |
+
"learning_rate": 4.080000000000001e-06,
|
| 16540 |
+
"loss": 1.7462,
|
| 16541 |
+
"mean_token_accuracy": 0.6508474260568619,
|
| 16542 |
+
"num_tokens": 33497623.0,
|
| 16543 |
+
"step": 9185
|
| 16544 |
+
},
|
| 16545 |
+
{
|
| 16546 |
+
"epoch": 70.6923076923077,
|
| 16547 |
+
"grad_norm": 0.0,
|
| 16548 |
+
"learning_rate": 4.055e-06,
|
| 16549 |
+
"loss": 1.7899,
|
| 16550 |
+
"mean_token_accuracy": 0.6407651424407959,
|
| 16551 |
+
"num_tokens": 33515029.0,
|
| 16552 |
+
"step": 9190
|
| 16553 |
}
|
| 16554 |
],
|
| 16555 |
"logging_steps": 5,
|
|
|
|
| 16569 |
"attributes": {}
|
| 16570 |
}
|
| 16571 |
},
|
| 16572 |
+
"total_flos": 1.69939335481344e+18,
|
| 16573 |
"train_batch_size": 4,
|
| 16574 |
"trial_name": null,
|
| 16575 |
"trial_params": null
|