Training in progress, step 6720, 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:cb3107d84a42a5a3b48c9b1fc0d6a6389661d61eb26fa4bd53d2265b30c5c76e
|
| 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:b18e89b4c42223129b3af3f176b65378dc2344e9ded67564b4c895b08a011b21
|
| 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 sha256:31baf0e868bf5631586cb9f222a8b58bfc60456232ba95710e8fcd730839a5b0
|
| 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": 51.
|
| 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,
|
|
@@ -12086,6 +12086,24 @@
|
|
| 12086 |
"mean_token_accuracy": 0.644529914855957,
|
| 12087 |
"num_tokens": 24471067.0,
|
| 12088 |
"step": 6710
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12089 |
}
|
| 12090 |
],
|
| 12091 |
"logging_steps": 5,
|
|
@@ -12105,7 +12123,7 @@
|
|
| 12105 |
"attributes": {}
|
| 12106 |
}
|
| 12107 |
},
|
| 12108 |
-
"total_flos": 1.
|
| 12109 |
"train_batch_size": 4,
|
| 12110 |
"trial_name": null,
|
| 12111 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.69230769230769,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6720,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12086 |
"mean_token_accuracy": 0.644529914855957,
|
| 12087 |
"num_tokens": 24471067.0,
|
| 12088 |
"step": 6710
|
| 12089 |
+
},
|
| 12090 |
+
{
|
| 12091 |
+
"epoch": 51.65384615384615,
|
| 12092 |
+
"grad_norm": 0.0,
|
| 12093 |
+
"learning_rate": 1.643e-05,
|
| 12094 |
+
"loss": 1.6671,
|
| 12095 |
+
"mean_token_accuracy": 0.6617798268795013,
|
| 12096 |
+
"num_tokens": 24489441.0,
|
| 12097 |
+
"step": 6715
|
| 12098 |
+
},
|
| 12099 |
+
{
|
| 12100 |
+
"epoch": 51.69230769230769,
|
| 12101 |
+
"grad_norm": 0.0,
|
| 12102 |
+
"learning_rate": 1.6405e-05,
|
| 12103 |
+
"loss": 1.7789,
|
| 12104 |
+
"mean_token_accuracy": 0.6475713908672333,
|
| 12105 |
+
"num_tokens": 24507517.0,
|
| 12106 |
+
"step": 6720
|
| 12107 |
}
|
| 12108 |
],
|
| 12109 |
"logging_steps": 5,
|
|
|
|
| 12123 |
"attributes": {}
|
| 12124 |
}
|
| 12125 |
},
|
| 12126 |
+
"total_flos": 1.2424695247459123e+18,
|
| 12127 |
"train_batch_size": 4,
|
| 12128 |
"trial_name": null,
|
| 12129 |
"trial_params": null
|