Training in progress, step 1800, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce2398087b9c95ecb2d27ad93dc71d1c42c6137766dbebc720788b257ddd6029
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ffa9eb486af2a5fe8e24a36c5c9b2a0a220ff288e930f1efa25af84bea4a05b
|
3 |
size 18902665
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75ff2b6345961e3defe7acb1f921dae5616ba7afff13dd0bf10bb569ed4bc334
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -245,13 +245,27 @@
|
|
245 |
"eval_samples_per_second": 30.562,
|
246 |
"eval_steps_per_second": 3.824,
|
247 |
"step": 1700
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
248 |
}
|
249 |
],
|
250 |
"logging_steps": 100,
|
251 |
"max_steps": 4116,
|
252 |
"num_train_epochs": 3,
|
253 |
"save_steps": 100,
|
254 |
-
"total_flos":
|
255 |
"trial_name": null,
|
256 |
"trial_params": null
|
257 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.2405381202697754,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1800",
|
4 |
+
"epoch": 1.3114754098360657,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1800,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
245 |
"eval_samples_per_second": 30.562,
|
246 |
"eval_steps_per_second": 3.824,
|
247 |
"step": 1700
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 1.31,
|
251 |
+
"learning_rate": 0.0002,
|
252 |
+
"loss": 2.2141,
|
253 |
+
"step": 1800
|
254 |
+
},
|
255 |
+
{
|
256 |
+
"epoch": 1.31,
|
257 |
+
"eval_loss": 2.2405381202697754,
|
258 |
+
"eval_runtime": 205.0141,
|
259 |
+
"eval_samples_per_second": 30.603,
|
260 |
+
"eval_steps_per_second": 3.829,
|
261 |
+
"step": 1800
|
262 |
}
|
263 |
],
|
264 |
"logging_steps": 100,
|
265 |
"max_steps": 4116,
|
266 |
"num_train_epochs": 3,
|
267 |
"save_steps": 100,
|
268 |
+
"total_flos": 5.260717969532928e+16,
|
269 |
"trial_name": null,
|
270 |
"trial_params": null
|
271 |
}
|