Training in progress, step 19, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3908ffb6cd7f2bc7032059d7effa6ee0df356568bab265f0918f0cee9a4f8c67
|
| 3 |
size 14696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 39398
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:833c0b97b3bd39c2c2b9e8d81d93f3e66deb0a53184ee95e60944afdee682b7f
|
| 3 |
size 39398
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14244
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e97d40b2fa3ebcebcef043ec5052510bb9b61525df8fd3a495991e57f6fe27ab
|
| 3 |
size 14244
|
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 sha256:83e3bd115fb7914e3157d1cddd28d2440908da5dddf3ed8b9232586a56c11e23
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 5,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -144,6 +144,34 @@
|
|
| 144 |
"eval_samples_per_second": 528.753,
|
| 145 |
"eval_steps_per_second": 264.377,
|
| 146 |
"step": 15
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 147 |
}
|
| 148 |
],
|
| 149 |
"logging_steps": 1,
|
|
@@ -158,12 +186,12 @@
|
|
| 158 |
"should_evaluate": false,
|
| 159 |
"should_log": false,
|
| 160 |
"should_save": true,
|
| 161 |
-
"should_training_stop":
|
| 162 |
},
|
| 163 |
"attributes": {}
|
| 164 |
}
|
| 165 |
},
|
| 166 |
-
"total_flos":
|
| 167 |
"train_batch_size": 2,
|
| 168 |
"trial_name": null,
|
| 169 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0132450331125828,
|
| 5 |
"eval_steps": 5,
|
| 6 |
+
"global_step": 19,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 144 |
"eval_samples_per_second": 528.753,
|
| 145 |
"eval_steps_per_second": 264.377,
|
| 146 |
"step": 15
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.847682119205298,
|
| 150 |
+
"grad_norm": 0.1068856492638588,
|
| 151 |
+
"learning_rate": 2.500000000000001e-05,
|
| 152 |
+
"loss": 11.9305,
|
| 153 |
+
"step": 16
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.9006622516556292,
|
| 157 |
+
"grad_norm": 0.10238690674304962,
|
| 158 |
+
"learning_rate": 1.1697777844051105e-05,
|
| 159 |
+
"loss": 11.9345,
|
| 160 |
+
"step": 17
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.9536423841059603,
|
| 164 |
+
"grad_norm": 0.09888564050197601,
|
| 165 |
+
"learning_rate": 3.0153689607045845e-06,
|
| 166 |
+
"loss": 11.9339,
|
| 167 |
+
"step": 18
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.0132450331125828,
|
| 171 |
+
"grad_norm": 0.12345912307500839,
|
| 172 |
+
"learning_rate": 0.0,
|
| 173 |
+
"loss": 14.6969,
|
| 174 |
+
"step": 19
|
| 175 |
}
|
| 176 |
],
|
| 177 |
"logging_steps": 1,
|
|
|
|
| 186 |
"should_evaluate": false,
|
| 187 |
"should_log": false,
|
| 188 |
"should_save": true,
|
| 189 |
+
"should_training_stop": true
|
| 190 |
},
|
| 191 |
"attributes": {}
|
| 192 |
}
|
| 193 |
},
|
| 194 |
+
"total_flos": 8980267008.0,
|
| 195 |
"train_batch_size": 2,
|
| 196 |
"trial_name": null,
|
| 197 |
"trial_params": null
|