Training in progress, step 8300, 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:f83a5934049777c22a2d76e0fc14cc1c3f0daf892365f23db4b665f2ec72073c
|
| 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 sha256:1fc22bdbe6d3ca4bffd1f34d079a0e511d8d6b2830b7a4963440076dd2892fda
|
| 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 sha256:2acd7e8df3ebd11462c274d378c4d64146902f7d8fa47225c0556e6e1ef81cd9
|
| 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,
|
|
@@ -14930,6 +14930,24 @@
|
|
| 14930 |
"mean_token_accuracy": 0.637213721871376,
|
| 14931 |
"num_tokens": 30233493.0,
|
| 14932 |
"step": 8290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14933 |
}
|
| 14934 |
],
|
| 14935 |
"logging_steps": 5,
|
|
@@ -14949,7 +14967,7 @@
|
|
| 14949 |
"attributes": {}
|
| 14950 |
}
|
| 14951 |
},
|
| 14952 |
-
"total_flos": 1.
|
| 14953 |
"train_batch_size": 4,
|
| 14954 |
"trial_name": null,
|
| 14955 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14930 |
"mean_token_accuracy": 0.637213721871376,
|
| 14931 |
"num_tokens": 30233493.0,
|
| 14932 |
"step": 8290
|
| 14933 |
+
},
|
| 14934 |
+
{
|
| 14935 |
+
"epoch": 63.80769230769231,
|
| 14936 |
+
"grad_norm": 0.0,
|
| 14937 |
+
"learning_rate": 8.53e-06,
|
| 14938 |
+
"loss": 1.7189,
|
| 14939 |
+
"mean_token_accuracy": 0.656983396410942,
|
| 14940 |
+
"num_tokens": 30251845.0,
|
| 14941 |
+
"step": 8295
|
| 14942 |
+
},
|
| 14943 |
+
{
|
| 14944 |
+
"epoch": 63.84615384615385,
|
| 14945 |
+
"grad_norm": 0.0,
|
| 14946 |
+
"learning_rate": 8.505e-06,
|
| 14947 |
+
"loss": 1.8205,
|
| 14948 |
+
"mean_token_accuracy": 0.6382214099168777,
|
| 14949 |
+
"num_tokens": 30268899.0,
|
| 14950 |
+
"step": 8300
|
| 14951 |
}
|
| 14952 |
],
|
| 14953 |
"logging_steps": 5,
|
|
|
|
| 14967 |
"attributes": {}
|
| 14968 |
}
|
| 14969 |
},
|
| 14970 |
+
"total_flos": 1.534677773853819e+18,
|
| 14971 |
"train_batch_size": 4,
|
| 14972 |
"trial_name": null,
|
| 14973 |
"trial_params": null
|