Training in progress, step 6410, 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 sha256:7dc6a8576a66569f958cd45a5a9575f2c626b318dfd4753740515e1f47f03d85
|
| 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 sha256:1d9a8dbf6b99c289e5ff8dc860ed9ca21c25a50dfccd8af4ae066d3afdf960e2
|
| 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 sha256:092974285fbb4faf86eb11d1013043918d42c2f032482701ad95d483f984a4f2
|
| 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": 49.
|
| 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,
|
|
@@ -11528,6 +11528,24 @@
|
|
| 11528 |
"mean_token_accuracy": 0.6581353217363357,
|
| 11529 |
"num_tokens": 23342349.0,
|
| 11530 |
"step": 6400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11531 |
}
|
| 11532 |
],
|
| 11533 |
"logging_steps": 5,
|
|
@@ -11547,7 +11565,7 @@
|
|
| 11547 |
"attributes": {}
|
| 11548 |
}
|
| 11549 |
},
|
| 11550 |
-
"total_flos": 1.
|
| 11551 |
"train_batch_size": 4,
|
| 11552 |
"trial_name": null,
|
| 11553 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 49.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6410,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11528 |
"mean_token_accuracy": 0.6581353217363357,
|
| 11529 |
"num_tokens": 23342349.0,
|
| 11530 |
"step": 6400
|
| 11531 |
+
},
|
| 11532 |
+
{
|
| 11533 |
+
"epoch": 49.26923076923077,
|
| 11534 |
+
"grad_norm": 0.0,
|
| 11535 |
+
"learning_rate": 1.798e-05,
|
| 11536 |
+
"loss": 1.739,
|
| 11537 |
+
"mean_token_accuracy": 0.6524305224418641,
|
| 11538 |
+
"num_tokens": 23360368.0,
|
| 11539 |
+
"step": 6405
|
| 11540 |
+
},
|
| 11541 |
+
{
|
| 11542 |
+
"epoch": 49.30769230769231,
|
| 11543 |
+
"grad_norm": 0.0,
|
| 11544 |
+
"learning_rate": 1.7955e-05,
|
| 11545 |
+
"loss": 1.7507,
|
| 11546 |
+
"mean_token_accuracy": 0.6451392889022827,
|
| 11547 |
+
"num_tokens": 23378793.0,
|
| 11548 |
+
"step": 6410
|
| 11549 |
}
|
| 11550 |
],
|
| 11551 |
"logging_steps": 5,
|
|
|
|
| 11565 |
"attributes": {}
|
| 11566 |
}
|
| 11567 |
},
|
| 11568 |
+
"total_flos": 1.1851708942422835e+18,
|
| 11569 |
"train_batch_size": 4,
|
| 11570 |
"trial_name": null,
|
| 11571 |
"trial_params": null
|