Training in progress, step 8230, 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 sha256:057c2a73af0781455bb073e65e5c61b51e9fc4505ea5b4faaf7cb8161ccfac3e
|
| 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:a443a4614ba96a0247064cb711390960325482e3083f1c784fe6e38b2c9618ea
|
| 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 sha256:59a1f6b2241b8e94221dea1cf6383dc0927f93819148a078e7fa7bf298cd5b11
|
| 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,
|
|
@@ -14804,6 +14804,24 @@
|
|
| 14804 |
"mean_token_accuracy": 0.6512804627418518,
|
| 14805 |
"num_tokens": 29978320.0,
|
| 14806 |
"step": 8220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14807 |
}
|
| 14808 |
],
|
| 14809 |
"logging_steps": 5,
|
|
@@ -14823,7 +14841,7 @@
|
|
| 14823 |
"attributes": {}
|
| 14824 |
}
|
| 14825 |
},
|
| 14826 |
-
"total_flos": 1.
|
| 14827 |
"train_batch_size": 4,
|
| 14828 |
"trial_name": null,
|
| 14829 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 63.30769230769231,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14804 |
"mean_token_accuracy": 0.6512804627418518,
|
| 14805 |
"num_tokens": 29978320.0,
|
| 14806 |
"step": 8220
|
| 14807 |
+
},
|
| 14808 |
+
{
|
| 14809 |
+
"epoch": 63.26923076923077,
|
| 14810 |
+
"grad_norm": 0.0,
|
| 14811 |
+
"learning_rate": 8.880000000000001e-06,
|
| 14812 |
+
"loss": 1.7525,
|
| 14813 |
+
"mean_token_accuracy": 0.6476843535900116,
|
| 14814 |
+
"num_tokens": 29996596.0,
|
| 14815 |
+
"step": 8225
|
| 14816 |
+
},
|
| 14817 |
+
{
|
| 14818 |
+
"epoch": 63.30769230769231,
|
| 14819 |
+
"grad_norm": 0.0,
|
| 14820 |
+
"learning_rate": 8.855e-06,
|
| 14821 |
+
"loss": 1.6552,
|
| 14822 |
+
"mean_token_accuracy": 0.6682954013347626,
|
| 14823 |
+
"num_tokens": 30015615.0,
|
| 14824 |
+
"step": 8230
|
| 14825 |
}
|
| 14826 |
],
|
| 14827 |
"logging_steps": 5,
|
|
|
|
| 14841 |
"attributes": {}
|
| 14842 |
}
|
| 14843 |
},
|
| 14844 |
+
"total_flos": 1.5219236801529446e+18,
|
| 14845 |
"train_batch_size": 4,
|
| 14846 |
"trial_name": null,
|
| 14847 |
"trial_params": null
|