Training in progress, step 104, 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 639691872
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d15e4509d78b338702add67e1a0342d20cea1e62d70828144cdd82d7e225f61c
|
3 |
size 639691872
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 325339796
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a134a8407784819add1857aa0a3a9ee8c24a75e636b885a04bed46b9e8d507c
|
3 |
size 325339796
|
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 sha256:11f555bc649def2d5f222c82b81fe7588d9710c829bc5246c9b7c7e93cf60c40
|
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:c89b61481eb2980a04190d12a0165f95c9fc0a4db20ad8cc3d895835eac42f68
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -281,6 +281,42 @@
|
|
281 |
"eval_samples_per_second": 13.198,
|
282 |
"eval_steps_per_second": 1.651,
|
283 |
"step": 91
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
284 |
}
|
285 |
],
|
286 |
"logging_steps": 3,
|
@@ -300,7 +336,7 @@
|
|
300 |
"attributes": {}
|
301 |
}
|
302 |
},
|
303 |
-
"total_flos": 1.
|
304 |
"train_batch_size": 8,
|
305 |
"trial_name": null,
|
306 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.028800886181113265,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 104,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
281 |
"eval_samples_per_second": 13.198,
|
282 |
"eval_steps_per_second": 1.651,
|
283 |
"step": 91
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.025754638604264746,
|
287 |
+
"grad_norm": 1.784736156463623,
|
288 |
+
"learning_rate": 3.562003362839914e-05,
|
289 |
+
"loss": 1.3904,
|
290 |
+
"step": 93
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.026585433397950706,
|
294 |
+
"grad_norm": 1.4629104137420654,
|
295 |
+
"learning_rate": 3.243125879593286e-05,
|
296 |
+
"loss": 1.4639,
|
297 |
+
"step": 96
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.027416228191636666,
|
301 |
+
"grad_norm": 1.478938102722168,
|
302 |
+
"learning_rate": 2.932207475167398e-05,
|
303 |
+
"loss": 1.4463,
|
304 |
+
"step": 99
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 0.028247022985322626,
|
308 |
+
"grad_norm": 1.7279759645462036,
|
309 |
+
"learning_rate": 2.630656687635007e-05,
|
310 |
+
"loss": 1.3153,
|
311 |
+
"step": 102
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 0.028800886181113265,
|
315 |
+
"eval_loss": 0.3473006784915924,
|
316 |
+
"eval_runtime": 460.803,
|
317 |
+
"eval_samples_per_second": 13.199,
|
318 |
+
"eval_steps_per_second": 1.651,
|
319 |
+
"step": 104
|
320 |
}
|
321 |
],
|
322 |
"logging_steps": 3,
|
|
|
336 |
"attributes": {}
|
337 |
}
|
338 |
},
|
339 |
+
"total_flos": 1.689729633311785e+17,
|
340 |
"train_batch_size": 8,
|
341 |
"trial_name": null,
|
342 |
"trial_params": null
|