Training in progress, step 1000, 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 161533160
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:027c28cbacad0920c7a8ec1a4dbaf396f0658e37d9c57aa24903513cf568bf29
|
| 3 |
size 161533160
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 323292202
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a811f08d635f9fd429d0ac8672eee899607dd871ece10f326b8ec3e7266d9db2
|
| 3 |
size 323292202
|
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 sha256:824d4a418ca52dbceab02ca3bdda11d00d54b246084fd87a75671a28233a0cb2
|
| 3 |
size 1064
|
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": 0.
|
| 6 |
"eval_steps": 100,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -150,6 +150,20 @@
|
|
| 150 |
"learning_rate": 4.961368653421634e-05,
|
| 151 |
"loss": 0.7661,
|
| 152 |
"step": 900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 153 |
}
|
| 154 |
],
|
| 155 |
"logging_steps": 50,
|
|
@@ -169,7 +183,7 @@
|
|
| 169 |
"attributes": {}
|
| 170 |
}
|
| 171 |
},
|
| 172 |
-
"total_flos":
|
| 173 |
"train_batch_size": 1,
|
| 174 |
"trial_name": null,
|
| 175 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.16556291390728478,
|
| 6 |
"eval_steps": 100,
|
| 7 |
+
"global_step": 1000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 150 |
"learning_rate": 4.961368653421634e-05,
|
| 151 |
"loss": 0.7661,
|
| 152 |
"step": 900
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.15728476821192053,
|
| 156 |
+
"grad_norm": 2.3362715244293213,
|
| 157 |
+
"learning_rate": 5.237306843267108e-05,
|
| 158 |
+
"loss": 0.736,
|
| 159 |
+
"step": 950
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.16556291390728478,
|
| 163 |
+
"grad_norm": 1.8228410482406616,
|
| 164 |
+
"learning_rate": 5.513245033112583e-05,
|
| 165 |
+
"loss": 0.7213,
|
| 166 |
+
"step": 1000
|
| 167 |
}
|
| 168 |
],
|
| 169 |
"logging_steps": 50,
|
|
|
|
| 183 |
"attributes": {}
|
| 184 |
}
|
| 185 |
},
|
| 186 |
+
"total_flos": 7833052747137024.0,
|
| 187 |
"train_batch_size": 1,
|
| 188 |
"trial_name": null,
|
| 189 |
"trial_params": null
|