Training in progress, step 4210, 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 sha256:45690abaa0d1d843d71345a528f76919425cfa97e2488c1d60397bf396d04f5a
|
| 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 sha256:07223aa391999e4b3fa90c3d184d4f2220c8e70847c23bb1da0c389b49862822
|
| 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 sha256:1e005244e84c74f5153c110c03f71466e9ba97b8c67f516534e1d543d8700735
|
| 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,
|
|
@@ -7568,6 +7568,24 @@
|
|
| 7568 |
"mean_token_accuracy": 0.642947056889534,
|
| 7569 |
"num_tokens": 15317120.0,
|
| 7570 |
"step": 4200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7571 |
}
|
| 7572 |
],
|
| 7573 |
"logging_steps": 5,
|
|
@@ -7587,7 +7605,7 @@
|
|
| 7587 |
"attributes": {}
|
| 7588 |
}
|
| 7589 |
},
|
| 7590 |
-
"total_flos": 7.
|
| 7591 |
"train_batch_size": 4,
|
| 7592 |
"trial_name": null,
|
| 7593 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 32.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7568 |
"mean_token_accuracy": 0.642947056889534,
|
| 7569 |
"num_tokens": 15317120.0,
|
| 7570 |
"step": 4200
|
| 7571 |
+
},
|
| 7572 |
+
{
|
| 7573 |
+
"epoch": 32.34615384615385,
|
| 7574 |
+
"grad_norm": 0.0,
|
| 7575 |
+
"learning_rate": 2.898e-05,
|
| 7576 |
+
"loss": 1.7569,
|
| 7577 |
+
"mean_token_accuracy": 0.648267537355423,
|
| 7578 |
+
"num_tokens": 15335733.0,
|
| 7579 |
+
"step": 4205
|
| 7580 |
+
},
|
| 7581 |
+
{
|
| 7582 |
+
"epoch": 32.38461538461539,
|
| 7583 |
+
"grad_norm": 0.0,
|
| 7584 |
+
"learning_rate": 2.8955e-05,
|
| 7585 |
+
"loss": 1.6314,
|
| 7586 |
+
"mean_token_accuracy": 0.6678825885057449,
|
| 7587 |
+
"num_tokens": 15355227.0,
|
| 7588 |
+
"step": 4210
|
| 7589 |
}
|
| 7590 |
],
|
| 7591 |
"logging_steps": 5,
|
|
|
|
| 7605 |
"attributes": {}
|
| 7606 |
}
|
| 7607 |
},
|
| 7608 |
+
"total_flos": 7.782683700687667e+17,
|
| 7609 |
"train_batch_size": 4,
|
| 7610 |
"trial_name": null,
|
| 7611 |
"trial_params": null
|