Training in progress, epoch 9, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2682482800
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e5385f06b538652646cbfc5a3c4525834c11507811c34df5129d1be043b66a0
|
| 3 |
size 2682482800
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5365108834
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56534d7c9ad9c6552d031e100a935ff682554d5639111b5205152078ee8863bd
|
| 3 |
size 5365108834
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e32c207ec0bcf846fcaf43ef5edf6b4221a950f70a18cd68fd181dbb601795c
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f5b79a171d8efc048051d23a19cdcdf9d97e554172eb7fbf8ebe8493e689716
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric":
|
| 3 |
-
"best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -127,6 +127,21 @@
|
|
| 127 |
"eval_samples_per_second": 46.565,
|
| 128 |
"eval_steps_per_second": 5.821,
|
| 129 |
"step": 2056
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 130 |
}
|
| 131 |
],
|
| 132 |
"logging_steps": 500,
|
|
@@ -155,7 +170,7 @@
|
|
| 155 |
"attributes": {}
|
| 156 |
}
|
| 157 |
},
|
| 158 |
-
"total_flos":
|
| 159 |
"train_batch_size": 8,
|
| 160 |
"trial_name": null,
|
| 161 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 0.9869545102119446,
|
| 3 |
+
"best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-2313",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2313,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 127 |
"eval_samples_per_second": 46.565,
|
| 128 |
"eval_steps_per_second": 5.821,
|
| 129 |
"step": 2056
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 9.0,
|
| 133 |
+
"grad_norm": 0.5170336961746216,
|
| 134 |
+
"learning_rate": 8.494140625e-05,
|
| 135 |
+
"loss": 0.832,
|
| 136 |
+
"step": 2313
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 9.0,
|
| 140 |
+
"eval_loss": 0.9869545102119446,
|
| 141 |
+
"eval_runtime": 9.2784,
|
| 142 |
+
"eval_samples_per_second": 46.56,
|
| 143 |
+
"eval_steps_per_second": 5.82,
|
| 144 |
+
"step": 2313
|
| 145 |
}
|
| 146 |
],
|
| 147 |
"logging_steps": 500,
|
|
|
|
| 170 |
"attributes": {}
|
| 171 |
}
|
| 172 |
},
|
| 173 |
+
"total_flos": 3.323957954394194e+17,
|
| 174 |
"train_batch_size": 8,
|
| 175 |
"trial_name": null,
|
| 176 |
"trial_params": null
|