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 203456160
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f53c04877827f365bbb4b3293465de2b06121c34cfb053670282e1364c050ab
|
3 |
size 203456160
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 407121750
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66684c7ea21a5f9e9275e6da185c54daaff64cb3c6eb431221bbd9e84fa2c70e
|
3 |
size 407121750
|
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 sha256:3b85bf58fb3d4810098a20a7bc55cb856b96ab7f966d6f0d0f6222b6a34a8ebe
|
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:cf6a9a1e39c0655c6941309388d2a028b5b8dbbca031ca2500bdfcdc9f2c01aa
|
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": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -306,6 +306,13 @@
|
|
306 |
"eval_samples_per_second": 6.266,
|
307 |
"eval_steps_per_second": 3.139,
|
308 |
"step": 88
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
309 |
}
|
310 |
],
|
311 |
"logging_steps": 3,
|
@@ -320,12 +327,12 @@
|
|
320 |
"should_evaluate": false,
|
321 |
"should_log": false,
|
322 |
"should_save": true,
|
323 |
-
"should_training_stop":
|
324 |
},
|
325 |
"attributes": {}
|
326 |
}
|
327 |
},
|
328 |
-
"total_flos": 2.
|
329 |
"train_batch_size": 2,
|
330 |
"trial_name": null,
|
331 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5695076132094127,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 90,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
306 |
"eval_samples_per_second": 6.266,
|
307 |
"eval_steps_per_second": 3.139,
|
308 |
"step": 88
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 0.5695076132094127,
|
312 |
+
"grad_norm": 0.8084313869476318,
|
313 |
+
"learning_rate": 0.0,
|
314 |
+
"loss": 0.6271,
|
315 |
+
"step": 90
|
316 |
}
|
317 |
],
|
318 |
"logging_steps": 3,
|
|
|
327 |
"should_evaluate": false,
|
328 |
"should_log": false,
|
329 |
"should_save": true,
|
330 |
+
"should_training_stop": true
|
331 |
},
|
332 |
"attributes": {}
|
333 |
}
|
334 |
},
|
335 |
+
"total_flos": 2.388734427267072e+17,
|
336 |
"train_batch_size": 2,
|
337 |
"trial_name": null,
|
338 |
"trial_params": null
|