Training in progress, step 2200, 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 sha256:350c1967286dd64a95fd5e74d50f830f2121f7fa957a9cf1f0510ea18888be16
|
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:e6e51297d8eb04bfa815f4810ff640d24dd696dece50f3931e74723c2d7845b8
|
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 sha256:05cf802ece851e37f7a2e8e09140678d93619f6c1e72127ae6bb12317798901b
|
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:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
|
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,
|
@@ -301,13 +301,27 @@
|
|
301 |
"eval_samples_per_second": 30.444,
|
302 |
"eval_steps_per_second": 3.809,
|
303 |
"step": 2100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
304 |
}
|
305 |
],
|
306 |
"logging_steps": 100,
|
307 |
"max_steps": 4116,
|
308 |
"num_train_epochs": 3,
|
309 |
"save_steps": 100,
|
310 |
-
"total_flos": 6.
|
311 |
"trial_name": null,
|
312 |
"trial_params": null
|
313 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.1567013263702393,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2200",
|
4 |
+
"epoch": 1.6029143897996359,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
301 |
"eval_samples_per_second": 30.444,
|
302 |
"eval_steps_per_second": 3.809,
|
303 |
"step": 2100
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.6,
|
307 |
+
"learning_rate": 0.0002,
|
308 |
+
"loss": 2.1373,
|
309 |
+
"step": 2200
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.6,
|
313 |
+
"eval_loss": 2.1567013263702393,
|
314 |
+
"eval_runtime": 206.3812,
|
315 |
+
"eval_samples_per_second": 30.4,
|
316 |
+
"eval_steps_per_second": 3.804,
|
317 |
+
"step": 2200
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 100,
|
321 |
"max_steps": 4116,
|
322 |
"num_train_epochs": 3,
|
323 |
"save_steps": 100,
|
324 |
+
"total_flos": 6.469323520149504e+16,
|
325 |
"trial_name": null,
|
326 |
"trial_params": null
|
327 |
}
|