Training in progress, step 2720, 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:c39892338b65c2ddce4775be314f6210b5007181c29c89be1739a22060e7a7ae
|
| 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:a4500332adc0b19cf93c0b1bf8fe386ef6af4eef6f6c9978ee5ee5c4e81b11a5
|
| 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:c3ee512abfcae1a3fd8e03e4e0ed24621c0259854d2f42461523460dff455f62
|
| 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": 20.
|
| 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,
|
|
@@ -4886,6 +4886,24 @@
|
|
| 4886 |
"mean_token_accuracy": 0.6505689769983292,
|
| 4887 |
"num_tokens": 9881953.0,
|
| 4888 |
"step": 2710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4889 |
}
|
| 4890 |
],
|
| 4891 |
"logging_steps": 5,
|
|
@@ -4905,7 +4923,7 @@
|
|
| 4905 |
"attributes": {}
|
| 4906 |
}
|
| 4907 |
},
|
| 4908 |
-
"total_flos": 5.
|
| 4909 |
"train_batch_size": 4,
|
| 4910 |
"trial_name": null,
|
| 4911 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 20.923076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4886 |
"mean_token_accuracy": 0.6505689769983292,
|
| 4887 |
"num_tokens": 9881953.0,
|
| 4888 |
"step": 2710
|
| 4889 |
+
},
|
| 4890 |
+
{
|
| 4891 |
+
"epoch": 20.884615384615383,
|
| 4892 |
+
"grad_norm": 0.0,
|
| 4893 |
+
"learning_rate": 3.643e-05,
|
| 4894 |
+
"loss": 1.7447,
|
| 4895 |
+
"mean_token_accuracy": 0.650253239274025,
|
| 4896 |
+
"num_tokens": 9900170.0,
|
| 4897 |
+
"step": 2715
|
| 4898 |
+
},
|
| 4899 |
+
{
|
| 4900 |
+
"epoch": 20.923076923076923,
|
| 4901 |
+
"grad_norm": 0.0,
|
| 4902 |
+
"learning_rate": 3.6405e-05,
|
| 4903 |
+
"loss": 1.7563,
|
| 4904 |
+
"mean_token_accuracy": 0.6442853361368179,
|
| 4905 |
+
"num_tokens": 9918308.0,
|
| 4906 |
+
"step": 2720
|
| 4907 |
}
|
| 4908 |
],
|
| 4909 |
"logging_steps": 5,
|
|
|
|
| 4923 |
"attributes": {}
|
| 4924 |
}
|
| 4925 |
},
|
| 4926 |
+
"total_flos": 5.0252869400887296e+17,
|
| 4927 |
"train_batch_size": 4,
|
| 4928 |
"trial_name": null,
|
| 4929 |
"trial_params": null
|