Training in progress, step 105, 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 1001465824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:266cd94871718a986e4ce23c183790fc4b0de8cc9aa2104fde09808eb0885d75
|
3 |
size 1001465824
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 509176980
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e33311b799b7918ecff9dc9f8b578379d48f6bda91cf68adc1a95d45266093b
|
3 |
size 509176980
|
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 sha256:83b302bd10368c09cb19ba400e1fa8ceca162eab977031b0bc94e411bbd47746
|
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 sha256:9042f02fbfca7c1dbbfe6d148e2a1de0ab7c9345d455fd2ba76f5d757c8ebcc0
|
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": 1.
|
5 |
"eval_steps": 15,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -273,6 +273,49 @@
|
|
273 |
"eval_samples_per_second": 4.437,
|
274 |
"eval_steps_per_second": 0.595,
|
275 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
276 |
}
|
277 |
],
|
278 |
"logging_steps": 3,
|
@@ -292,7 +335,7 @@
|
|
292 |
"attributes": {}
|
293 |
}
|
294 |
},
|
295 |
-
"total_flos":
|
296 |
"train_batch_size": 8,
|
297 |
"trial_name": null,
|
298 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.8225108225108224,
|
5 |
"eval_steps": 15,
|
6 |
+
"global_step": 105,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
273 |
"eval_samples_per_second": 4.437,
|
274 |
"eval_steps_per_second": 0.595,
|
275 |
"step": 90
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.6147186147186146,
|
279 |
+
"grad_norm": 0.9706316590309143,
|
280 |
+
"learning_rate": 4.855468326228638e-05,
|
281 |
+
"loss": 2.0843,
|
282 |
+
"step": 93
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.6666666666666665,
|
286 |
+
"grad_norm": 1.0962471961975098,
|
287 |
+
"learning_rate": 4.566888047586507e-05,
|
288 |
+
"loss": 2.0797,
|
289 |
+
"step": 96
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 1.7186147186147185,
|
293 |
+
"grad_norm": 0.9773306846618652,
|
294 |
+
"learning_rate": 4.27975536108268e-05,
|
295 |
+
"loss": 2.1115,
|
296 |
+
"step": 99
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.7705627705627704,
|
300 |
+
"grad_norm": 0.9265680909156799,
|
301 |
+
"learning_rate": 3.9950299516607766e-05,
|
302 |
+
"loss": 2.1697,
|
303 |
+
"step": 102
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.8225108225108224,
|
307 |
+
"grad_norm": 1.1050467491149902,
|
308 |
+
"learning_rate": 3.713663458410779e-05,
|
309 |
+
"loss": 2.157,
|
310 |
+
"step": 105
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 1.8225108225108224,
|
314 |
+
"eval_loss": 0.6672056317329407,
|
315 |
+
"eval_runtime": 21.8494,
|
316 |
+
"eval_samples_per_second": 4.439,
|
317 |
+
"eval_steps_per_second": 0.595,
|
318 |
+
"step": 105
|
319 |
}
|
320 |
],
|
321 |
"logging_steps": 3,
|
|
|
335 |
"attributes": {}
|
336 |
}
|
337 |
},
|
338 |
+
"total_flos": 5.403225279902515e+17,
|
339 |
"train_batch_size": 8,
|
340 |
"trial_name": null,
|
341 |
"trial_params": null
|