Training in progress, step 8950, 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 sha256:63fc425705459dc014b8743d38ae6536ca65fa500f11c1fe0ffe05cdff9e8187
|
| 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 sha256:6bd51b3b84cb20775a709fb0d51e7f82b9ee8181d7d3312b2b9018e416a262ae
|
| 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 sha256:737deddd653d2010b4fc69707dbec45c1edd7c0ee5f6eb1e48fa49882fadf6e5
|
| 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": 68.
|
| 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,
|
|
@@ -16100,6 +16100,24 @@
|
|
| 16100 |
"mean_token_accuracy": 0.6541435539722442,
|
| 16101 |
"num_tokens": 32602652.0,
|
| 16102 |
"step": 8940
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16103 |
}
|
| 16104 |
],
|
| 16105 |
"logging_steps": 5,
|
|
@@ -16119,7 +16137,7 @@
|
|
| 16119 |
"attributes": {}
|
| 16120 |
}
|
| 16121 |
},
|
| 16122 |
-
"total_flos": 1.
|
| 16123 |
"train_batch_size": 4,
|
| 16124 |
"trial_name": null,
|
| 16125 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8950,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16100 |
"mean_token_accuracy": 0.6541435539722442,
|
| 16101 |
"num_tokens": 32602652.0,
|
| 16102 |
"step": 8940
|
| 16103 |
+
},
|
| 16104 |
+
{
|
| 16105 |
+
"epoch": 68.8076923076923,
|
| 16106 |
+
"grad_norm": 0.0,
|
| 16107 |
+
"learning_rate": 5.28e-06,
|
| 16108 |
+
"loss": 1.8005,
|
| 16109 |
+
"mean_token_accuracy": 0.6381476581096649,
|
| 16110 |
+
"num_tokens": 32620436.0,
|
| 16111 |
+
"step": 8945
|
| 16112 |
+
},
|
| 16113 |
+
{
|
| 16114 |
+
"epoch": 68.84615384615384,
|
| 16115 |
+
"grad_norm": 0.0,
|
| 16116 |
+
"learning_rate": 5.2550000000000005e-06,
|
| 16117 |
+
"loss": 1.7707,
|
| 16118 |
+
"mean_token_accuracy": 0.6429592072963715,
|
| 16119 |
+
"num_tokens": 32638580.0,
|
| 16120 |
+
"step": 8950
|
| 16121 |
}
|
| 16122 |
],
|
| 16123 |
"logging_steps": 5,
|
|
|
|
| 16137 |
"attributes": {}
|
| 16138 |
}
|
| 16139 |
},
|
| 16140 |
+
"total_flos": 1.655041099556782e+18,
|
| 16141 |
"train_batch_size": 4,
|
| 16142 |
"trial_name": null,
|
| 16143 |
"trial_params": null
|