Training in progress, step 4390, 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:d19013a534664c4d95ad679481d9445728efaa376121d407776ce84333f90286
|
| 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 sha256:72e547bafa2ce3948582b9cdb0cb48b79df5f03e7fa7c5b6ee7a846595dfd476
|
| 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:af148651bc849809ea2c1194b1b0d814c2898ed6c8c2b2184b042f80f1344ae2
|
| 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": 33.
|
| 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,
|
|
@@ -7892,6 +7892,24 @@
|
|
| 7892 |
"mean_token_accuracy": 0.6549121081829071,
|
| 7893 |
"num_tokens": 15976927.0,
|
| 7894 |
"step": 4380
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7895 |
}
|
| 7896 |
],
|
| 7897 |
"logging_steps": 5,
|
|
@@ -7911,7 +7929,7 @@
|
|
| 7911 |
"attributes": {}
|
| 7912 |
}
|
| 7913 |
},
|
| 7914 |
-
"total_flos": 8.
|
| 7915 |
"train_batch_size": 4,
|
| 7916 |
"trial_name": null,
|
| 7917 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4390,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7892 |
"mean_token_accuracy": 0.6549121081829071,
|
| 7893 |
"num_tokens": 15976927.0,
|
| 7894 |
"step": 4380
|
| 7895 |
+
},
|
| 7896 |
+
{
|
| 7897 |
+
"epoch": 33.73076923076923,
|
| 7898 |
+
"grad_norm": 0.0,
|
| 7899 |
+
"learning_rate": 2.8080000000000002e-05,
|
| 7900 |
+
"loss": 1.8074,
|
| 7901 |
+
"mean_token_accuracy": 0.6450524151325225,
|
| 7902 |
+
"num_tokens": 15994035.0,
|
| 7903 |
+
"step": 4385
|
| 7904 |
+
},
|
| 7905 |
+
{
|
| 7906 |
+
"epoch": 33.76923076923077,
|
| 7907 |
+
"grad_norm": 0.0,
|
| 7908 |
+
"learning_rate": 2.8055000000000005e-05,
|
| 7909 |
+
"loss": 1.7169,
|
| 7910 |
+
"mean_token_accuracy": 0.6550534397363663,
|
| 7911 |
+
"num_tokens": 16012525.0,
|
| 7912 |
+
"step": 4390
|
| 7913 |
}
|
| 7914 |
],
|
| 7915 |
"logging_steps": 5,
|
|
|
|
| 7929 |
"attributes": {}
|
| 7930 |
}
|
| 7931 |
},
|
| 7932 |
+
"total_flos": 8.115064026469171e+17,
|
| 7933 |
"train_batch_size": 4,
|
| 7934 |
"trial_name": null,
|
| 7935 |
"trial_params": null
|