Training in progress, step 2540, 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 sha256:783f0fd773c0815862a7301080ef81ae70bfdaa4c554adc2b2102b41192923e6
|
| 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 sha256:7da09f088cc5ee1bf663b40f335cdcc624f5841eae85db14e2a96f7fac41ff62
|
| 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:aa91e532d73c2cc7182e10c768643c074b600fedac2a71a549a2909ea3e17e43
|
| 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,
|
|
@@ -4562,6 +4562,24 @@
|
|
| 4562 |
"mean_token_accuracy": 0.6388478010892868,
|
| 4563 |
"num_tokens": 9224815.0,
|
| 4564 |
"step": 2530
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4565 |
}
|
| 4566 |
],
|
| 4567 |
"logging_steps": 5,
|
|
@@ -4581,7 +4599,7 @@
|
|
| 4581 |
"attributes": {}
|
| 4582 |
}
|
| 4583 |
},
|
| 4584 |
-
"total_flos": 4.
|
| 4585 |
"train_batch_size": 4,
|
| 4586 |
"trial_name": null,
|
| 4587 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 19.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2540,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4562 |
"mean_token_accuracy": 0.6388478010892868,
|
| 4563 |
"num_tokens": 9224815.0,
|
| 4564 |
"step": 2530
|
| 4565 |
+
},
|
| 4566 |
+
{
|
| 4567 |
+
"epoch": 19.5,
|
| 4568 |
+
"grad_norm": 0.0,
|
| 4569 |
+
"learning_rate": 3.7330000000000003e-05,
|
| 4570 |
+
"loss": 1.6962,
|
| 4571 |
+
"mean_token_accuracy": 0.6541598588228226,
|
| 4572 |
+
"num_tokens": 9244225.0,
|
| 4573 |
+
"step": 2535
|
| 4574 |
+
},
|
| 4575 |
+
{
|
| 4576 |
+
"epoch": 19.53846153846154,
|
| 4577 |
+
"grad_norm": 0.0,
|
| 4578 |
+
"learning_rate": 3.7305e-05,
|
| 4579 |
+
"loss": 1.7581,
|
| 4580 |
+
"mean_token_accuracy": 0.6506271123886108,
|
| 4581 |
+
"num_tokens": 9262267.0,
|
| 4582 |
+
"step": 2540
|
| 4583 |
}
|
| 4584 |
],
|
| 4585 |
"logging_steps": 5,
|
|
|
|
| 4599 |
"attributes": {}
|
| 4600 |
}
|
| 4601 |
},
|
| 4602 |
+
"total_flos": 4.693043164372992e+17,
|
| 4603 |
"train_batch_size": 4,
|
| 4604 |
"trial_name": null,
|
| 4605 |
"trial_params": null
|