Training in progress, step 9450, 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 sha256:365d007e53c5cfe08ae81bf54f403d53538404a3d3b54796e352a926363f55d7
|
| 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 sha256:68bc5efcc8a901d5b1d124338cec11c14a3c21fcbe4f3405f0a08fbb40c3536b
|
| 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:c43cf472d3e08495984b3d809a52f34b683d6541fd0eaf12fcf16bbae6bea730
|
| 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": 72.
|
| 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,
|
|
@@ -17000,6 +17000,24 @@
|
|
| 17000 |
"mean_token_accuracy": 0.6529299259185791,
|
| 17001 |
"num_tokens": 34427248.0,
|
| 17002 |
"step": 9440
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17003 |
}
|
| 17004 |
],
|
| 17005 |
"logging_steps": 5,
|
|
@@ -17019,7 +17037,7 @@
|
|
| 17019 |
"attributes": {}
|
| 17020 |
}
|
| 17021 |
},
|
| 17022 |
-
"total_flos": 1.
|
| 17023 |
"train_batch_size": 4,
|
| 17024 |
"trial_name": null,
|
| 17025 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.6923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9450,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17000 |
"mean_token_accuracy": 0.6529299259185791,
|
| 17001 |
"num_tokens": 34427248.0,
|
| 17002 |
"step": 9440
|
| 17003 |
+
},
|
| 17004 |
+
{
|
| 17005 |
+
"epoch": 72.65384615384616,
|
| 17006 |
+
"grad_norm": 0.0,
|
| 17007 |
+
"learning_rate": 2.78e-06,
|
| 17008 |
+
"loss": 1.7713,
|
| 17009 |
+
"mean_token_accuracy": 0.6492305964231491,
|
| 17010 |
+
"num_tokens": 34445017.0,
|
| 17011 |
+
"step": 9445
|
| 17012 |
+
},
|
| 17013 |
+
{
|
| 17014 |
+
"epoch": 72.6923076923077,
|
| 17015 |
+
"grad_norm": 0.0,
|
| 17016 |
+
"learning_rate": 2.7550000000000003e-06,
|
| 17017 |
+
"loss": 1.7775,
|
| 17018 |
+
"mean_token_accuracy": 0.6450568825006485,
|
| 17019 |
+
"num_tokens": 34462759.0,
|
| 17020 |
+
"step": 9450
|
| 17021 |
}
|
| 17022 |
],
|
| 17023 |
"logging_steps": 5,
|
|
|
|
| 17037 |
"attributes": {}
|
| 17038 |
}
|
| 17039 |
},
|
| 17040 |
+
"total_flos": 1.747467710816256e+18,
|
| 17041 |
"train_batch_size": 4,
|
| 17042 |
"trial_name": null,
|
| 17043 |
"trial_params": null
|