Training in progress, step 4520, 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 sha256:356a072f85438eb0e5d6a4e4c2511bfa2fe5a30e6cdc1e47dd55187a2876a092
|
| 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 sha256:5d7c01b1c95458b220b0d8435968a7e71e543b88a90afc36fac0675d4b394288
|
| 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 sha256:0424b0cf8b51444c5dcde84d4423a394d4827ad8a0fd24ffd1e0b8424978d3d7
|
| 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": 34.
|
| 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,
|
|
@@ -8126,6 +8126,24 @@
|
|
| 8126 |
"mean_token_accuracy": 0.6399717807769776,
|
| 8127 |
"num_tokens": 16447829.0,
|
| 8128 |
"step": 4510
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8129 |
}
|
| 8130 |
],
|
| 8131 |
"logging_steps": 5,
|
|
@@ -8145,7 +8163,7 @@
|
|
| 8145 |
"attributes": {}
|
| 8146 |
}
|
| 8147 |
},
|
| 8148 |
-
"total_flos": 8.
|
| 8149 |
"train_batch_size": 4,
|
| 8150 |
"trial_name": null,
|
| 8151 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 34.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4520,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8126 |
"mean_token_accuracy": 0.6399717807769776,
|
| 8127 |
"num_tokens": 16447829.0,
|
| 8128 |
"step": 4510
|
| 8129 |
+
},
|
| 8130 |
+
{
|
| 8131 |
+
"epoch": 34.73076923076923,
|
| 8132 |
+
"grad_norm": 0.0,
|
| 8133 |
+
"learning_rate": 2.743e-05,
|
| 8134 |
+
"loss": 1.6926,
|
| 8135 |
+
"mean_token_accuracy": 0.6622339367866517,
|
| 8136 |
+
"num_tokens": 16466534.0,
|
| 8137 |
+
"step": 4515
|
| 8138 |
+
},
|
| 8139 |
+
{
|
| 8140 |
+
"epoch": 34.76923076923077,
|
| 8141 |
+
"grad_norm": 0.0,
|
| 8142 |
+
"learning_rate": 2.7405000000000003e-05,
|
| 8143 |
+
"loss": 1.7331,
|
| 8144 |
+
"mean_token_accuracy": 0.6530486464500427,
|
| 8145 |
+
"num_tokens": 16484278.0,
|
| 8146 |
+
"step": 4520
|
| 8147 |
}
|
| 8148 |
],
|
| 8149 |
"logging_steps": 5,
|
|
|
|
| 8163 |
"attributes": {}
|
| 8164 |
}
|
| 8165 |
},
|
| 8166 |
+
"total_flos": 8.354225115493171e+17,
|
| 8167 |
"train_batch_size": 4,
|
| 8168 |
"trial_name": null,
|
| 8169 |
"trial_params": null
|