Training in progress, step 9340, 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 sha256:264565fa51bed685efe49f5f5637101ed20757f15405b1daa532e7e38b4f316b
|
| 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:eb08db812ddfc022c74f7836e951100a82ea90092eb40a6d60491919b3a76058
|
| 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:f98ef67d8d8c6e8bacd493255370cc9673cddc364695103fedbc2b96a5a072e5
|
| 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": 71.
|
| 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,
|
|
@@ -16802,6 +16802,24 @@
|
|
| 16802 |
"mean_token_accuracy": 0.6419746041297912,
|
| 16803 |
"num_tokens": 34028492.0,
|
| 16804 |
"step": 9330
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16805 |
}
|
| 16806 |
],
|
| 16807 |
"logging_steps": 5,
|
|
@@ -16821,7 +16839,7 @@
|
|
| 16821 |
"attributes": {}
|
| 16822 |
}
|
| 16823 |
},
|
| 16824 |
-
"total_flos": 1.
|
| 16825 |
"train_batch_size": 4,
|
| 16826 |
"trial_name": null,
|
| 16827 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 71.84615384615384,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9340,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16802 |
"mean_token_accuracy": 0.6419746041297912,
|
| 16803 |
"num_tokens": 34028492.0,
|
| 16804 |
"step": 9330
|
| 16805 |
+
},
|
| 16806 |
+
{
|
| 16807 |
+
"epoch": 71.8076923076923,
|
| 16808 |
+
"grad_norm": 0.0,
|
| 16809 |
+
"learning_rate": 3.3300000000000003e-06,
|
| 16810 |
+
"loss": 1.8112,
|
| 16811 |
+
"mean_token_accuracy": 0.6337680786848068,
|
| 16812 |
+
"num_tokens": 34045754.0,
|
| 16813 |
+
"step": 9335
|
| 16814 |
+
},
|
| 16815 |
+
{
|
| 16816 |
+
"epoch": 71.84615384615384,
|
| 16817 |
+
"grad_norm": 0.0,
|
| 16818 |
+
"learning_rate": 3.3050000000000005e-06,
|
| 16819 |
+
"loss": 1.7796,
|
| 16820 |
+
"mean_token_accuracy": 0.6412538975477219,
|
| 16821 |
+
"num_tokens": 34063747.0,
|
| 16822 |
+
"step": 9340
|
| 16823 |
}
|
| 16824 |
],
|
| 16825 |
"logging_steps": 5,
|
|
|
|
| 16839 |
"attributes": {}
|
| 16840 |
}
|
| 16841 |
},
|
| 16842 |
+
"total_flos": 1.7273291165820518e+18,
|
| 16843 |
"train_batch_size": 4,
|
| 16844 |
"trial_name": null,
|
| 16845 |
"trial_params": null
|