Training in progress, step 3950, 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 sha256:11e8ceb4c69f40905d60c57b58de9a97dd3412eb410fca13b96fa9f59ebd6a5a
|
| 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:d12f0138b0ca59e0fc4f65f740d072b3952156390a65ddfd4df12ffd8603245b
|
| 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 sha256:47c49682091437c55722c583bc9cb8245bf277e4359647357826497045411070
|
| 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": 30.
|
| 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,
|
|
@@ -7100,6 +7100,24 @@
|
|
| 7100 |
"mean_token_accuracy": 0.6724200338125229,
|
| 7101 |
"num_tokens": 14369664.0,
|
| 7102 |
"step": 3940
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7103 |
}
|
| 7104 |
],
|
| 7105 |
"logging_steps": 5,
|
|
@@ -7119,7 +7137,7 @@
|
|
| 7119 |
"attributes": {}
|
| 7120 |
}
|
| 7121 |
},
|
| 7122 |
-
"total_flos": 7.
|
| 7123 |
"train_batch_size": 4,
|
| 7124 |
"trial_name": null,
|
| 7125 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 30.384615384615383,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3950,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 7100 |
"mean_token_accuracy": 0.6724200338125229,
|
| 7101 |
"num_tokens": 14369664.0,
|
| 7102 |
"step": 3940
|
| 7103 |
+
},
|
| 7104 |
+
{
|
| 7105 |
+
"epoch": 30.346153846153847,
|
| 7106 |
+
"grad_norm": 0.0,
|
| 7107 |
+
"learning_rate": 3.028e-05,
|
| 7108 |
+
"loss": 1.7748,
|
| 7109 |
+
"mean_token_accuracy": 0.6431576639413834,
|
| 7110 |
+
"num_tokens": 14388275.0,
|
| 7111 |
+
"step": 3945
|
| 7112 |
+
},
|
| 7113 |
+
{
|
| 7114 |
+
"epoch": 30.384615384615383,
|
| 7115 |
+
"grad_norm": 0.0,
|
| 7116 |
+
"learning_rate": 3.0255e-05,
|
| 7117 |
+
"loss": 1.7376,
|
| 7118 |
+
"mean_token_accuracy": 0.6552271574735642,
|
| 7119 |
+
"num_tokens": 14406379.0,
|
| 7120 |
+
"step": 3950
|
| 7121 |
}
|
| 7122 |
],
|
| 7123 |
"logging_steps": 5,
|
|
|
|
| 7137 |
"attributes": {}
|
| 7138 |
}
|
| 7139 |
},
|
| 7140 |
+
"total_flos": 7.301320901989171e+17,
|
| 7141 |
"train_batch_size": 4,
|
| 7142 |
"trial_name": null,
|
| 7143 |
"trial_params": null
|