Training in progress, step 5760, 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 sha256:576cb3c3a2a9209d4275fe95bbe8f3fcea559916554cf023d466d3e288860e9c
|
| 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 sha256:24b53fd63d5ad1bf7c58782cc035cbb03185af1221ad4163aa0287483edbf643
|
| 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 sha256:276f32b5d2686760b2efd18e82e5a18c35c250f5878f2e5583c3feb79547cedb
|
| 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": 44.
|
| 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,
|
|
@@ -10358,6 +10358,24 @@
|
|
| 10358 |
"mean_token_accuracy": 0.6396133095026016,
|
| 10359 |
"num_tokens": 20969175.0,
|
| 10360 |
"step": 5750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10361 |
}
|
| 10362 |
],
|
| 10363 |
"logging_steps": 5,
|
|
@@ -10377,7 +10395,7 @@
|
|
| 10377 |
"attributes": {}
|
| 10378 |
}
|
| 10379 |
},
|
| 10380 |
-
"total_flos": 1.
|
| 10381 |
"train_batch_size": 4,
|
| 10382 |
"trial_name": null,
|
| 10383 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 44.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5760,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10358 |
"mean_token_accuracy": 0.6396133095026016,
|
| 10359 |
"num_tokens": 20969175.0,
|
| 10360 |
"step": 5750
|
| 10361 |
+
},
|
| 10362 |
+
{
|
| 10363 |
+
"epoch": 44.26923076923077,
|
| 10364 |
+
"grad_norm": 0.0,
|
| 10365 |
+
"learning_rate": 2.123e-05,
|
| 10366 |
+
"loss": 1.7431,
|
| 10367 |
+
"mean_token_accuracy": 0.6489101707935333,
|
| 10368 |
+
"num_tokens": 20987238.0,
|
| 10369 |
+
"step": 5755
|
| 10370 |
+
},
|
| 10371 |
+
{
|
| 10372 |
+
"epoch": 44.30769230769231,
|
| 10373 |
+
"grad_norm": 0.0,
|
| 10374 |
+
"learning_rate": 2.1205e-05,
|
| 10375 |
+
"loss": 1.7022,
|
| 10376 |
+
"mean_token_accuracy": 0.658707058429718,
|
| 10377 |
+
"num_tokens": 21005379.0,
|
| 10378 |
+
"step": 5760
|
| 10379 |
}
|
| 10380 |
],
|
| 10381 |
"logging_steps": 5,
|
|
|
|
| 10395 |
"attributes": {}
|
| 10396 |
}
|
| 10397 |
},
|
| 10398 |
+
"total_flos": 1.0644833415226982e+18,
|
| 10399 |
"train_batch_size": 4,
|
| 10400 |
"trial_name": null,
|
| 10401 |
"trial_params": null
|