Training in progress, step 8960, 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 sha256:52a86a2c4b93fa6c561622931141d8d722bc16bb83cec9d269343bc2e7193e07
|
| 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 sha256:56344b08d086a272f7fffe8cdcdb57e62878da75e500999bffe6366f7298620a
|
| 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:e00cc3af2dd3bd8ee63b1b573ed901b55cb677214ccbf2a1a1fcb6494e20b724
|
| 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": 68.
|
| 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,
|
|
@@ -16118,6 +16118,24 @@
|
|
| 16118 |
"mean_token_accuracy": 0.6429592072963715,
|
| 16119 |
"num_tokens": 32638580.0,
|
| 16120 |
"step": 8950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16121 |
}
|
| 16122 |
],
|
| 16123 |
"logging_steps": 5,
|
|
@@ -16137,7 +16155,7 @@
|
|
| 16137 |
"attributes": {}
|
| 16138 |
}
|
| 16139 |
},
|
| 16140 |
-
"total_flos": 1.
|
| 16141 |
"train_batch_size": 4,
|
| 16142 |
"trial_name": null,
|
| 16143 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8960,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16118 |
"mean_token_accuracy": 0.6429592072963715,
|
| 16119 |
"num_tokens": 32638580.0,
|
| 16120 |
"step": 8950
|
| 16121 |
+
},
|
| 16122 |
+
{
|
| 16123 |
+
"epoch": 68.88461538461539,
|
| 16124 |
+
"grad_norm": 0.0,
|
| 16125 |
+
"learning_rate": 5.23e-06,
|
| 16126 |
+
"loss": 1.7375,
|
| 16127 |
+
"mean_token_accuracy": 0.6491723597049713,
|
| 16128 |
+
"num_tokens": 32657574.0,
|
| 16129 |
+
"step": 8955
|
| 16130 |
+
},
|
| 16131 |
+
{
|
| 16132 |
+
"epoch": 68.92307692307692,
|
| 16133 |
+
"grad_norm": 0.0,
|
| 16134 |
+
"learning_rate": 5.205e-06,
|
| 16135 |
+
"loss": 1.6892,
|
| 16136 |
+
"mean_token_accuracy": 0.6607306629419327,
|
| 16137 |
+
"num_tokens": 32676715.0,
|
| 16138 |
+
"step": 8960
|
| 16139 |
}
|
| 16140 |
],
|
| 16141 |
"logging_steps": 5,
|
|
|
|
| 16155 |
"attributes": {}
|
| 16156 |
}
|
| 16157 |
},
|
| 16158 |
+
"total_flos": 1.6570115487616205e+18,
|
| 16159 |
"train_batch_size": 4,
|
| 16160 |
"trial_name": null,
|
| 16161 |
"trial_params": null
|