Training in progress, step 4970, 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:b8da5c5771db7c2bedf607622dd8e9e7c909f05d6803f91752fb6a4447de5ad6
|
| 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 sha256:85c11deaa6dc12716755dd53d827b9122fb30f3c560d15975b28ce83ed589cb1
|
| 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 sha256:748dd115ee552741d6f4872a2295ed4d9aa0afd2e63f26d60e8b394b29b096e8
|
| 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": 38.
|
| 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,
|
|
@@ -8936,6 +8936,24 @@
|
|
| 8936 |
"mean_token_accuracy": 0.6499431103467941,
|
| 8937 |
"num_tokens": 18089731.0,
|
| 8938 |
"step": 4960
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8939 |
}
|
| 8940 |
],
|
| 8941 |
"logging_steps": 5,
|
|
@@ -8955,7 +8973,7 @@
|
|
| 8955 |
"attributes": {}
|
| 8956 |
}
|
| 8957 |
},
|
| 8958 |
-
"total_flos": 9.
|
| 8959 |
"train_batch_size": 4,
|
| 8960 |
"trial_name": null,
|
| 8961 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4970,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8936 |
"mean_token_accuracy": 0.6499431103467941,
|
| 8937 |
"num_tokens": 18089731.0,
|
| 8938 |
"step": 4960
|
| 8939 |
+
},
|
| 8940 |
+
{
|
| 8941 |
+
"epoch": 38.19230769230769,
|
| 8942 |
+
"grad_norm": 0.0,
|
| 8943 |
+
"learning_rate": 2.5180000000000003e-05,
|
| 8944 |
+
"loss": 1.7363,
|
| 8945 |
+
"mean_token_accuracy": 0.652138090133667,
|
| 8946 |
+
"num_tokens": 18107784.0,
|
| 8947 |
+
"step": 4965
|
| 8948 |
+
},
|
| 8949 |
+
{
|
| 8950 |
+
"epoch": 38.23076923076923,
|
| 8951 |
+
"grad_norm": 0.0,
|
| 8952 |
+
"learning_rate": 2.5155000000000002e-05,
|
| 8953 |
+
"loss": 1.6622,
|
| 8954 |
+
"mean_token_accuracy": 0.6630479246377945,
|
| 8955 |
+
"num_tokens": 18126899.0,
|
| 8956 |
+
"step": 4970
|
| 8957 |
}
|
| 8958 |
],
|
| 8959 |
"logging_steps": 5,
|
|
|
|
| 8973 |
"attributes": {}
|
| 8974 |
}
|
| 8975 |
},
|
| 8976 |
+
"total_flos": 9.185959505033626e+17,
|
| 8977 |
"train_batch_size": 4,
|
| 8978 |
"trial_name": null,
|
| 8979 |
"trial_params": null
|