Training in progress, step 8290, 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:c094f2388a53163978fac2cadb43522e26a3907b3da8dba2c74aa45c2364d6de
|
| 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 sha256:94509e146e43d17c8d2dcca044d3652702ca010616e95a30a35ccfd52ddc9bd6
|
| 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:ed947f01df69cf17cc43da23a8a591e8b118a19e470b64bd27bf0bcb416059d2
|
| 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": 63.
|
| 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,
|
|
@@ -14912,6 +14912,24 @@
|
|
| 14912 |
"mean_token_accuracy": 0.6582196593284607,
|
| 14913 |
"num_tokens": 30197308.0,
|
| 14914 |
"step": 8280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14915 |
}
|
| 14916 |
],
|
| 14917 |
"logging_steps": 5,
|
|
@@ -14931,7 +14949,7 @@
|
|
| 14931 |
"attributes": {}
|
| 14932 |
}
|
| 14933 |
},
|
| 14934 |
-
"total_flos": 1.
|
| 14935 |
"train_batch_size": 4,
|
| 14936 |
"trial_name": null,
|
| 14937 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14912 |
"mean_token_accuracy": 0.6582196593284607,
|
| 14913 |
"num_tokens": 30197308.0,
|
| 14914 |
"step": 8280
|
| 14915 |
+
},
|
| 14916 |
+
{
|
| 14917 |
+
"epoch": 63.73076923076923,
|
| 14918 |
+
"grad_norm": 0.0,
|
| 14919 |
+
"learning_rate": 8.580000000000001e-06,
|
| 14920 |
+
"loss": 1.6787,
|
| 14921 |
+
"mean_token_accuracy": 0.6678410351276398,
|
| 14922 |
+
"num_tokens": 30215988.0,
|
| 14923 |
+
"step": 8285
|
| 14924 |
+
},
|
| 14925 |
+
{
|
| 14926 |
+
"epoch": 63.76923076923077,
|
| 14927 |
+
"grad_norm": 0.0,
|
| 14928 |
+
"learning_rate": 8.555e-06,
|
| 14929 |
+
"loss": 1.7973,
|
| 14930 |
+
"mean_token_accuracy": 0.637213721871376,
|
| 14931 |
+
"num_tokens": 30233493.0,
|
| 14932 |
+
"step": 8290
|
| 14933 |
}
|
| 14934 |
],
|
| 14935 |
"logging_steps": 5,
|
|
|
|
| 14949 |
"attributes": {}
|
| 14950 |
}
|
| 14951 |
},
|
| 14952 |
+
"total_flos": 1.5329124673059226e+18,
|
| 14953 |
"train_batch_size": 4,
|
| 14954 |
"trial_name": null,
|
| 14955 |
"trial_params": null
|