Training in progress, step 4940, 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 sha256:367be3775dc167048edeeea087bc0214052e251dd8ab75ab2a4a5350d7c14261
|
| 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 sha256:5164e42065f58bf108e938920ea653cddd83e8e337bffe83eb26d8dbab870f82
|
| 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:b075ae6d80e4c9ecd0d53580d38901d0b9340e6771f9bc11849f1e883a9b5e97
|
| 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":
|
| 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,
|
|
@@ -8882,6 +8882,24 @@
|
|
| 8882 |
"mean_token_accuracy": 0.6597955763339997,
|
| 8883 |
"num_tokens": 17979359.0,
|
| 8884 |
"step": 4930
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8885 |
}
|
| 8886 |
],
|
| 8887 |
"logging_steps": 5,
|
|
@@ -8901,7 +8919,7 @@
|
|
| 8901 |
"attributes": {}
|
| 8902 |
}
|
| 8903 |
},
|
| 8904 |
-
"total_flos": 9.
|
| 8905 |
"train_batch_size": 4,
|
| 8906 |
"trial_name": null,
|
| 8907 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4940,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8882 |
"mean_token_accuracy": 0.6597955763339997,
|
| 8883 |
"num_tokens": 17979359.0,
|
| 8884 |
"step": 4930
|
| 8885 |
+
},
|
| 8886 |
+
{
|
| 8887 |
+
"epoch": 37.96153846153846,
|
| 8888 |
+
"grad_norm": 0.0,
|
| 8889 |
+
"learning_rate": 2.5330000000000003e-05,
|
| 8890 |
+
"loss": 1.7047,
|
| 8891 |
+
"mean_token_accuracy": 0.6595474272966385,
|
| 8892 |
+
"num_tokens": 17997968.0,
|
| 8893 |
+
"step": 4935
|
| 8894 |
+
},
|
| 8895 |
+
{
|
| 8896 |
+
"epoch": 38.0,
|
| 8897 |
+
"grad_norm": 0.0,
|
| 8898 |
+
"learning_rate": 2.5305000000000003e-05,
|
| 8899 |
+
"loss": 1.7505,
|
| 8900 |
+
"mean_token_accuracy": 0.6506702989339829,
|
| 8901 |
+
"num_tokens": 18015990.0,
|
| 8902 |
+
"step": 4940
|
| 8903 |
}
|
| 8904 |
],
|
| 8905 |
"logging_steps": 5,
|
|
|
|
| 8919 |
"attributes": {}
|
| 8920 |
}
|
| 8921 |
},
|
| 8922 |
+
"total_flos": 9.130256604949709e+17,
|
| 8923 |
"train_batch_size": 4,
|
| 8924 |
"trial_name": null,
|
| 8925 |
"trial_params": null
|