Training in progress, step 4380, 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 sha256:5f8fad601c9da4c62fac69214282716e5995487a31bba09a913f9c486f9740c9
|
| 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:f46386941f1ec74c854d0e8eeebbb0ef90d9343a339b0d113324f132a15ed170
|
| 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 sha256:57642a0272a7e58fb0c7c63e8ce6ad7e870bf24ed85274fad5295556db13ca9f
|
| 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,
|
|
@@ -7874,6 +7874,24 @@
|
|
| 7874 |
"mean_token_accuracy": 0.6539973527193069,
|
| 7875 |
"num_tokens": 15939494.0,
|
| 7876 |
"step": 4370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7877 |
}
|
| 7878 |
],
|
| 7879 |
"logging_steps": 5,
|
|
@@ -7893,7 +7911,7 @@
|
|
| 7893 |
"attributes": {}
|
| 7894 |
}
|
| 7895 |
},
|
| 7896 |
-
"total_flos": 8.
|
| 7897 |
"train_batch_size": 4,
|
| 7898 |
"trial_name": null,
|
| 7899 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 33.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7874 |
"mean_token_accuracy": 0.6539973527193069,
|
| 7875 |
"num_tokens": 15939494.0,
|
| 7876 |
"step": 4370
|
| 7877 |
+
},
|
| 7878 |
+
{
|
| 7879 |
+
"epoch": 33.65384615384615,
|
| 7880 |
+
"grad_norm": 0.0,
|
| 7881 |
+
"learning_rate": 2.813e-05,
|
| 7882 |
+
"loss": 1.7232,
|
| 7883 |
+
"mean_token_accuracy": 0.649171131849289,
|
| 7884 |
+
"num_tokens": 15958194.0,
|
| 7885 |
+
"step": 4375
|
| 7886 |
+
},
|
| 7887 |
+
{
|
| 7888 |
+
"epoch": 33.69230769230769,
|
| 7889 |
+
"grad_norm": 0.0,
|
| 7890 |
+
"learning_rate": 2.8105000000000003e-05,
|
| 7891 |
+
"loss": 1.7117,
|
| 7892 |
+
"mean_token_accuracy": 0.6549121081829071,
|
| 7893 |
+
"num_tokens": 15976927.0,
|
| 7894 |
+
"step": 4380
|
| 7895 |
}
|
| 7896 |
],
|
| 7897 |
"logging_steps": 5,
|
|
|
|
| 7911 |
"attributes": {}
|
| 7912 |
}
|
| 7913 |
},
|
| 7914 |
+
"total_flos": 8.097129921901363e+17,
|
| 7915 |
"train_batch_size": 4,
|
| 7916 |
"trial_name": null,
|
| 7917 |
"trial_params": null
|