Training in progress, step 660, 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 109009752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5f4554e7aff6599904d0319a20ee86142cd7d1747a6de55c2ecc7a2ef0f88e9
|
3 |
size 109009752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56088788
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db78a63e6ac946bde21e73e26a05c81e9c8b3b13e74e2fb7450f6da464fb0e13
|
3 |
size 56088788
|
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 sha256:1b8bd222230b9ba24daa62957d67e25eed67a1b67be6dbe8febbba1f1264beae
|
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:ce585e1dbd1dc0083d726023c4787702cd6c517b31ebbe8e35d5384feabc9615
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 2.578611599801661e-07,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-640",
|
4 |
-
"epoch": 4.
|
5 |
"eval_steps": 20,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -313,6 +313,14 @@
|
|
313 |
"eval_samples_per_second": 28.64,
|
314 |
"eval_steps_per_second": 0.916,
|
315 |
"step": 640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
316 |
}
|
317 |
],
|
318 |
"logging_steps": 100,
|
@@ -327,7 +335,7 @@
|
|
327 |
"early_stopping_threshold": 0.0
|
328 |
},
|
329 |
"attributes": {
|
330 |
-
"early_stopping_patience_counter":
|
331 |
}
|
332 |
},
|
333 |
"TrainerControl": {
|
@@ -341,7 +349,7 @@
|
|
341 |
"attributes": {}
|
342 |
}
|
343 |
},
|
344 |
-
"total_flos": 2.
|
345 |
"train_batch_size": 8,
|
346 |
"trial_name": null,
|
347 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 2.578611599801661e-07,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-640",
|
4 |
+
"epoch": 4.444444444444445,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 660,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
313 |
"eval_samples_per_second": 28.64,
|
314 |
"eval_steps_per_second": 0.916,
|
315 |
"step": 640
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 4.444444444444445,
|
319 |
+
"eval_loss": 2.583842331205233e-07,
|
320 |
+
"eval_runtime": 4.3769,
|
321 |
+
"eval_samples_per_second": 28.559,
|
322 |
+
"eval_steps_per_second": 0.914,
|
323 |
+
"step": 660
|
324 |
}
|
325 |
],
|
326 |
"logging_steps": 100,
|
|
|
335 |
"early_stopping_threshold": 0.0
|
336 |
},
|
337 |
"attributes": {
|
338 |
+
"early_stopping_patience_counter": 1
|
339 |
}
|
340 |
},
|
341 |
"TrainerControl": {
|
|
|
349 |
"attributes": {}
|
350 |
}
|
351 |
},
|
352 |
+
"total_flos": 2.7870250829611008e+17,
|
353 |
"train_batch_size": 8,
|
354 |
"trial_name": null,
|
355 |
"trial_params": null
|