Training in progress, step 1600, 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:c26994a8ad06a0daccdf5b25357f28e8297fdefe14673db1e689fb5c36d2d0c1
|
| 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 sha256:35a7abba63dcfef191f13f474a266dab26dc8e113221e8b80bbc5c2a57a5e671
|
| 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 sha256:3f14a9ae67d23e442f4fbee57d4b98572dba9ac2830f4548744a1393408b6a64
|
| 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": 12.
|
| 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,
|
|
@@ -2870,6 +2870,24 @@
|
|
| 2870 |
"mean_token_accuracy": 0.6427943378686904,
|
| 2871 |
"num_tokens": 5795346.0,
|
| 2872 |
"step": 1590
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2873 |
}
|
| 2874 |
],
|
| 2875 |
"logging_steps": 5,
|
|
@@ -2889,7 +2907,7 @@
|
|
| 2889 |
"attributes": {}
|
| 2890 |
}
|
| 2891 |
},
|
| 2892 |
-
"total_flos": 2.
|
| 2893 |
"train_batch_size": 4,
|
| 2894 |
"trial_name": null,
|
| 2895 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 12.307692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1600,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2870 |
"mean_token_accuracy": 0.6427943378686904,
|
| 2871 |
"num_tokens": 5795346.0,
|
| 2872 |
"step": 1590
|
| 2873 |
+
},
|
| 2874 |
+
{
|
| 2875 |
+
"epoch": 12.26923076923077,
|
| 2876 |
+
"grad_norm": 0.0,
|
| 2877 |
+
"learning_rate": 4.203e-05,
|
| 2878 |
+
"loss": 1.7938,
|
| 2879 |
+
"mean_token_accuracy": 0.6385728657245636,
|
| 2880 |
+
"num_tokens": 5812776.0,
|
| 2881 |
+
"step": 1595
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 12.307692307692308,
|
| 2885 |
+
"grad_norm": 0.0,
|
| 2886 |
+
"learning_rate": 4.2005e-05,
|
| 2887 |
+
"loss": 1.7442,
|
| 2888 |
+
"mean_token_accuracy": 0.6511879444122315,
|
| 2889 |
+
"num_tokens": 5831416.0,
|
| 2890 |
+
"step": 1600
|
| 2891 |
}
|
| 2892 |
],
|
| 2893 |
"logging_steps": 5,
|
|
|
|
| 2907 |
"attributes": {}
|
| 2908 |
}
|
| 2909 |
},
|
| 2910 |
+
"total_flos": 2.9523966056792064e+17,
|
| 2911 |
"train_batch_size": 4,
|
| 2912 |
"trial_name": null,
|
| 2913 |
"trial_params": null
|