Training in progress, step 1120, 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 sha256:51c76f0a0ebc966663c84f0c6279c6441d6845fb94e8d7a67f8ac03c80bd61c3
|
| 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:e07dccc21ef6bd08e4dc974c9af2ae4f5d6e1e9b525609ab567df2a354fbe7df
|
| 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 sha256:371d281181d023181d7e0e069aaf7be30e930f14ab5bbdc4edc17c4053a1a278
|
| 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": 8.
|
| 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,
|
|
@@ -2006,6 +2006,24 @@
|
|
| 2006 |
"mean_token_accuracy": 0.6439882755279541,
|
| 2007 |
"num_tokens": 4047081.0,
|
| 2008 |
"step": 1110
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2009 |
}
|
| 2010 |
],
|
| 2011 |
"logging_steps": 5,
|
|
@@ -2025,7 +2043,7 @@
|
|
| 2025 |
"attributes": {}
|
| 2026 |
}
|
| 2027 |
},
|
| 2028 |
-
"total_flos": 2.
|
| 2029 |
"train_batch_size": 4,
|
| 2030 |
"trial_name": null,
|
| 2031 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.615384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1120,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2006 |
"mean_token_accuracy": 0.6439882755279541,
|
| 2007 |
"num_tokens": 4047081.0,
|
| 2008 |
"step": 1110
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 8.576923076923077,
|
| 2012 |
+
"grad_norm": 0.0,
|
| 2013 |
+
"learning_rate": 4.443e-05,
|
| 2014 |
+
"loss": 1.8174,
|
| 2015 |
+
"mean_token_accuracy": 0.6325599551200867,
|
| 2016 |
+
"num_tokens": 4065118.0,
|
| 2017 |
+
"step": 1115
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 8.615384615384615,
|
| 2021 |
+
"grad_norm": 0.0,
|
| 2022 |
+
"learning_rate": 4.4405e-05,
|
| 2023 |
+
"loss": 1.7934,
|
| 2024 |
+
"mean_token_accuracy": 0.6423143684864044,
|
| 2025 |
+
"num_tokens": 4083327.0,
|
| 2026 |
+
"step": 1120
|
| 2027 |
}
|
| 2028 |
],
|
| 2029 |
"logging_steps": 5,
|
|
|
|
| 2043 |
"attributes": {}
|
| 2044 |
}
|
| 2045 |
},
|
| 2046 |
+
"total_flos": 2.0708722514608128e+17,
|
| 2047 |
"train_batch_size": 4,
|
| 2048 |
"trial_name": null,
|
| 2049 |
"trial_params": null
|