Training in progress, step 90, 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 78480072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:33a5d0fe066ffa93cff2ce666eac60a71cc401ba96a6b8dcbc1678ac2c78714b
|
3 |
size 78480072
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40131268
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:422ea9fef3dca06cb7e139f9dd806e7bc0a80c88e3881a1598bc6b0b686c0fa3
|
3 |
size 40131268
|
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:a8544242e3f788be29e662c88830e08ff5706a9604518162edf02980d267fa66
|
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 sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
|
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": 0.
|
5 |
"eval_steps": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -276,6 +276,35 @@
|
|
276 |
"eval_samples_per_second": 26.257,
|
277 |
"eval_steps_per_second": 3.315,
|
278 |
"step": 81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
279 |
}
|
280 |
],
|
281 |
"logging_steps": 3,
|
@@ -295,7 +324,7 @@
|
|
295 |
"attributes": {}
|
296 |
}
|
297 |
},
|
298 |
-
"total_flos": 3.
|
299 |
"train_batch_size": 8,
|
300 |
"trial_name": null,
|
301 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.3037974683544304,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 90,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
276 |
"eval_samples_per_second": 26.257,
|
277 |
"eval_steps_per_second": 3.315,
|
278 |
"step": 81
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.28354430379746837,
|
282 |
+
"grad_norm": 0.4782557189464569,
|
283 |
+
"learning_rate": 3.798797596089351e-06,
|
284 |
+
"loss": 0.9225,
|
285 |
+
"step": 84
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.2936708860759494,
|
289 |
+
"grad_norm": 0.4685029685497284,
|
290 |
+
"learning_rate": 2.5301488425208296e-06,
|
291 |
+
"loss": 0.8903,
|
292 |
+
"step": 87
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.3037974683544304,
|
296 |
+
"grad_norm": 0.48110467195510864,
|
297 |
+
"learning_rate": 1.5076844803522922e-06,
|
298 |
+
"loss": 0.9264,
|
299 |
+
"step": 90
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.3037974683544304,
|
303 |
+
"eval_loss": 0.9077513217926025,
|
304 |
+
"eval_runtime": 19.0064,
|
305 |
+
"eval_samples_per_second": 26.254,
|
306 |
+
"eval_steps_per_second": 3.315,
|
307 |
+
"step": 90
|
308 |
}
|
309 |
],
|
310 |
"logging_steps": 3,
|
|
|
324 |
"attributes": {}
|
325 |
}
|
326 |
},
|
327 |
+
"total_flos": 3.885912614240256e+16,
|
328 |
"train_batch_size": 8,
|
329 |
"trial_name": null,
|
330 |
"trial_params": null
|