Training in progress, step 5010, 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 sha256:4ea01fcd712b5447f95fee7857bb6a682708b4aeba42dbe7012b6627e059a9cb
|
| 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 sha256:01294bdfd37f812054f9825d93f12b1c182004bf0ba912f811cb525fa143314c
|
| 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:d41d5446e9d676d9f2a9da3bf6cf153ba9b0f61cab7fc6a0c296fc4e842a14bb
|
| 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": 38.
|
| 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,
|
|
@@ -9008,6 +9008,24 @@
|
|
| 9008 |
"mean_token_accuracy": 0.642228040099144,
|
| 9009 |
"num_tokens": 18235182.0,
|
| 9010 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9011 |
}
|
| 9012 |
],
|
| 9013 |
"logging_steps": 5,
|
|
@@ -9027,7 +9045,7 @@
|
|
| 9027 |
"attributes": {}
|
| 9028 |
}
|
| 9029 |
},
|
| 9030 |
-
"total_flos": 9.
|
| 9031 |
"train_batch_size": 4,
|
| 9032 |
"trial_name": null,
|
| 9033 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5010,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9008 |
"mean_token_accuracy": 0.642228040099144,
|
| 9009 |
"num_tokens": 18235182.0,
|
| 9010 |
"step": 5000
|
| 9011 |
+
},
|
| 9012 |
+
{
|
| 9013 |
+
"epoch": 38.5,
|
| 9014 |
+
"grad_norm": 0.0,
|
| 9015 |
+
"learning_rate": 2.498e-05,
|
| 9016 |
+
"loss": 1.7976,
|
| 9017 |
+
"mean_token_accuracy": 0.6354389518499375,
|
| 9018 |
+
"num_tokens": 18252871.0,
|
| 9019 |
+
"step": 5005
|
| 9020 |
+
},
|
| 9021 |
+
{
|
| 9022 |
+
"epoch": 38.53846153846154,
|
| 9023 |
+
"grad_norm": 0.0,
|
| 9024 |
+
"learning_rate": 2.4955e-05,
|
| 9025 |
+
"loss": 1.7793,
|
| 9026 |
+
"mean_token_accuracy": 0.6435254126787185,
|
| 9027 |
+
"num_tokens": 18270734.0,
|
| 9028 |
+
"step": 5010
|
| 9029 |
}
|
| 9030 |
],
|
| 9031 |
"logging_steps": 5,
|
|
|
|
| 9045 |
"attributes": {}
|
| 9046 |
}
|
| 9047 |
},
|
| 9048 |
+
"total_flos": 9.25880896512e+17,
|
| 9049 |
"train_batch_size": 4,
|
| 9050 |
"trial_name": null,
|
| 9051 |
"trial_params": null
|