Training in progress, step 520, 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 sha256:7ffd38b590308341a1f235b6f129c4a91dd4eb8e8e7a8950f51d004b7f60f9e9
|
| 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:d9d01efdf8f11e8cb4b2926f2545a309ec981bc88450c71bcbf42d8bb379aaa3
|
| 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 sha256:251541d9cc2e2e08c8990921a1e69c14cb6da848cca330e1570e24f9e353cfda
|
| 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,
|
|
@@ -926,6 +926,24 @@
|
|
| 926 |
"mean_token_accuracy": 0.6480034649372101,
|
| 927 |
"num_tokens": 1861334.0,
|
| 928 |
"step": 510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 929 |
}
|
| 930 |
],
|
| 931 |
"logging_steps": 5,
|
|
@@ -945,7 +963,7 @@
|
|
| 945 |
"attributes": {}
|
| 946 |
}
|
| 947 |
},
|
| 948 |
-
"total_flos": 9.
|
| 949 |
"train_batch_size": 4,
|
| 950 |
"trial_name": null,
|
| 951 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 520,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 926 |
"mean_token_accuracy": 0.6480034649372101,
|
| 927 |
"num_tokens": 1861334.0,
|
| 928 |
"step": 510
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 3.9615384615384617,
|
| 932 |
+
"grad_norm": 0.0,
|
| 933 |
+
"learning_rate": 4.7430000000000005e-05,
|
| 934 |
+
"loss": 1.7783,
|
| 935 |
+
"mean_token_accuracy": 0.6420908480882644,
|
| 936 |
+
"num_tokens": 1879077.0,
|
| 937 |
+
"step": 515
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 4.0,
|
| 941 |
+
"grad_norm": 0.0,
|
| 942 |
+
"learning_rate": 4.7405000000000004e-05,
|
| 943 |
+
"loss": 1.7984,
|
| 944 |
+
"mean_token_accuracy": 0.6410065919160843,
|
| 945 |
+
"num_tokens": 1896420.0,
|
| 946 |
+
"step": 520
|
| 947 |
}
|
| 948 |
],
|
| 949 |
"logging_steps": 5,
|
|
|
|
| 963 |
"attributes": {}
|
| 964 |
}
|
| 965 |
},
|
| 966 |
+
"total_flos": 9.605296818044928e+16,
|
| 967 |
"train_batch_size": 4,
|
| 968 |
"trial_name": null,
|
| 969 |
"trial_params": null
|