Training in progress, step 3350, 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:ef14182bf1d07b3faa2a7a86412e84a9d84c96a499788dc7b2b24ca4bb861777
|
| 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:dd3e2103dc30722aa87c7cd55f1a9a76dc7a2230ddccf9937e25c8618914e16c
|
| 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:d32c8d70b85a48bfc4ba18e08a87e8470bd145d432774b0fc981eec59da390fb
|
| 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": 25.
|
| 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,
|
|
@@ -6020,6 +6020,24 @@
|
|
| 6020 |
"mean_token_accuracy": 0.6307004660367965,
|
| 6021 |
"num_tokens": 12180342.0,
|
| 6022 |
"step": 3340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6023 |
}
|
| 6024 |
],
|
| 6025 |
"logging_steps": 5,
|
|
@@ -6039,7 +6057,7 @@
|
|
| 6039 |
"attributes": {}
|
| 6040 |
}
|
| 6041 |
},
|
| 6042 |
-
"total_flos": 6.
|
| 6043 |
"train_batch_size": 4,
|
| 6044 |
"trial_name": null,
|
| 6045 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 25.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3350,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6020 |
"mean_token_accuracy": 0.6307004660367965,
|
| 6021 |
"num_tokens": 12180342.0,
|
| 6022 |
"step": 3340
|
| 6023 |
+
},
|
| 6024 |
+
{
|
| 6025 |
+
"epoch": 25.73076923076923,
|
| 6026 |
+
"grad_norm": 0.0,
|
| 6027 |
+
"learning_rate": 3.328e-05,
|
| 6028 |
+
"loss": 1.7708,
|
| 6029 |
+
"mean_token_accuracy": 0.6448087066411972,
|
| 6030 |
+
"num_tokens": 12198282.0,
|
| 6031 |
+
"step": 3345
|
| 6032 |
+
},
|
| 6033 |
+
{
|
| 6034 |
+
"epoch": 25.76923076923077,
|
| 6035 |
+
"grad_norm": 0.0,
|
| 6036 |
+
"learning_rate": 3.3255000000000006e-05,
|
| 6037 |
+
"loss": 1.7765,
|
| 6038 |
+
"mean_token_accuracy": 0.6405314236879349,
|
| 6039 |
+
"num_tokens": 12215896.0,
|
| 6040 |
+
"step": 3350
|
| 6041 |
}
|
| 6042 |
],
|
| 6043 |
"logging_steps": 5,
|
|
|
|
| 6057 |
"attributes": {}
|
| 6058 |
}
|
| 6059 |
},
|
| 6060 |
+
"total_flos": 6.189166662274253e+17,
|
| 6061 |
"train_batch_size": 4,
|
| 6062 |
"trial_name": null,
|
| 6063 |
"trial_params": null
|