Training in progress, step 99, 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 161533192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8a2ca6ef247f0719f65a0453e7acf234646a9ae1d03af394ae0b747851fa1b5
|
3 |
size 161533192
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 82460660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5be38a4ed0ab3c8afd2629e65b83ebac0aa631709b036a31b2dc071b2ec0751e
|
3 |
size 82460660
|
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 sha256:44d0e6232fa35968ab6e9a766dedfd5be3af299a338f513b1e164207a9471726
|
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 sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
|
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": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -305,6 +305,35 @@
|
|
305 |
"eval_samples_per_second": 14.884,
|
306 |
"eval_steps_per_second": 1.871,
|
307 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
308 |
}
|
309 |
],
|
310 |
"logging_steps": 3,
|
@@ -324,7 +353,7 @@
|
|
324 |
"attributes": {}
|
325 |
}
|
326 |
},
|
327 |
-
"total_flos": 1.
|
328 |
"train_batch_size": 8,
|
329 |
"trial_name": null,
|
330 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.18073938840712003,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 99,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
305 |
"eval_samples_per_second": 14.884,
|
306 |
"eval_steps_per_second": 1.871,
|
307 |
"step": 90
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.1697854860794158,
|
311 |
+
"grad_norm": 0.7800453305244446,
|
312 |
+
"learning_rate": 1.4852136862001764e-06,
|
313 |
+
"loss": 1.3199,
|
314 |
+
"step": 93
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.17526243724326793,
|
318 |
+
"grad_norm": 0.9326381087303162,
|
319 |
+
"learning_rate": 4.865965629214819e-07,
|
320 |
+
"loss": 1.4299,
|
321 |
+
"step": 96
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.18073938840712003,
|
325 |
+
"grad_norm": 0.8738844990730286,
|
326 |
+
"learning_rate": 3.04586490452119e-08,
|
327 |
+
"loss": 1.5228,
|
328 |
+
"step": 99
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.18073938840712003,
|
332 |
+
"eval_loss": 1.459765076637268,
|
333 |
+
"eval_runtime": 62.037,
|
334 |
+
"eval_samples_per_second": 14.878,
|
335 |
+
"eval_steps_per_second": 1.87,
|
336 |
+
"step": 99
|
337 |
}
|
338 |
],
|
339 |
"logging_steps": 3,
|
|
|
353 |
"attributes": {}
|
354 |
}
|
355 |
},
|
356 |
+
"total_flos": 1.3875918062537933e+17,
|
357 |
"train_batch_size": 8,
|
358 |
"trial_name": null,
|
359 |
"trial_params": null
|