Training in progress, step 560, 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 sha256:0d416b96ddb86b39acea285afa1c535ead42e497a733cb29207280e6c2f83fa7
|
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:d337ec9fb2f1caa18ce4f33b9a96b7fcffd2a399f435bf0b35f9ff16c4c1ad17
|
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 sha256:1df3a3cae241082d68c3a6cb326bf131e93d4d808298cd38ff7f1baeee5d48f8
|
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:bef42e564008e32e1ede623c5c541c27431e92ce859dc16d7a639dbd642b25ba
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 2.6893604854194564e-07,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-540",
|
4 |
-
"epoch": 3.
|
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,
|
@@ -266,6 +266,14 @@
|
|
266 |
"eval_samples_per_second": 28.484,
|
267 |
"eval_steps_per_second": 0.912,
|
268 |
"step": 540
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
269 |
}
|
270 |
],
|
271 |
"logging_steps": 100,
|
@@ -280,7 +288,7 @@
|
|
280 |
"early_stopping_threshold": 0.0
|
281 |
},
|
282 |
"attributes": {
|
283 |
-
"early_stopping_patience_counter":
|
284 |
}
|
285 |
},
|
286 |
"TrainerControl": {
|
@@ -294,7 +302,7 @@
|
|
294 |
"attributes": {}
|
295 |
}
|
296 |
},
|
297 |
-
"total_flos": 2.
|
298 |
"train_batch_size": 8,
|
299 |
"trial_name": null,
|
300 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 2.6893604854194564e-07,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-540",
|
4 |
+
"epoch": 3.771043771043771,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 560,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
266 |
"eval_samples_per_second": 28.484,
|
267 |
"eval_steps_per_second": 0.912,
|
268 |
"step": 540
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 3.771043771043771,
|
272 |
+
"eval_loss": 2.6898223381977004e-07,
|
273 |
+
"eval_runtime": 4.4647,
|
274 |
+
"eval_samples_per_second": 27.998,
|
275 |
+
"eval_steps_per_second": 0.896,
|
276 |
+
"step": 560
|
277 |
}
|
278 |
],
|
279 |
"logging_steps": 100,
|
|
|
288 |
"early_stopping_threshold": 0.0
|
289 |
},
|
290 |
"attributes": {
|
291 |
+
"early_stopping_patience_counter": 1
|
292 |
}
|
293 |
},
|
294 |
"TrainerControl": {
|
|
|
302 |
"attributes": {}
|
303 |
}
|
304 |
},
|
305 |
+
"total_flos": 2.3648525642366976e+17,
|
306 |
"train_batch_size": 8,
|
307 |
"trial_name": null,
|
308 |
"trial_params": null
|