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 191968
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c860ea5a6e8e22df234610e427732ece01430ff261f7528de4ec38092fe82cc
|
3 |
size 191968
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 253144
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:350bfcd84c37639d857006c6d77476c76e729234f8e6eaf3830e73a3135b6fec
|
3 |
size 253144
|
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:dfe472efafb6374e91efc60fbb9e59628946f50e8efb56a3c6f635d192b12727
|
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": 233.357,
|
306 |
"eval_steps_per_second": 29.177,
|
307 |
"step": 90
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
308 |
}
|
309 |
],
|
310 |
"logging_steps": 3,
|
@@ -324,7 +353,7 @@
|
|
324 |
"attributes": {}
|
325 |
}
|
326 |
},
|
327 |
-
"total_flos":
|
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": 0.02162870719318368,
|
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": 233.357,
|
306 |
"eval_steps_per_second": 29.177,
|
307 |
"step": 90
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.02031787645420285,
|
311 |
+
"grad_norm": 0.146971195936203,
|
312 |
+
"learning_rate": 1.4852136862001764e-06,
|
313 |
+
"loss": 10.2779,
|
314 |
+
"step": 93
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.020973291823693264,
|
318 |
+
"grad_norm": 0.2508053779602051,
|
319 |
+
"learning_rate": 4.865965629214819e-07,
|
320 |
+
"loss": 10.2598,
|
321 |
+
"step": 96
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.02162870719318368,
|
325 |
+
"grad_norm": 0.16878999769687653,
|
326 |
+
"learning_rate": 3.04586490452119e-08,
|
327 |
+
"loss": 10.2826,
|
328 |
+
"step": 99
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.02162870719318368,
|
332 |
+
"eval_loss": 10.264737129211426,
|
333 |
+
"eval_runtime": 33.0022,
|
334 |
+
"eval_samples_per_second": 233.62,
|
335 |
+
"eval_steps_per_second": 29.21,
|
336 |
+
"step": 99
|
337 |
}
|
338 |
],
|
339 |
"logging_steps": 3,
|
|
|
353 |
"attributes": {}
|
354 |
}
|
355 |
},
|
356 |
+
"total_flos": 22087030800384.0,
|
357 |
"train_batch_size": 8,
|
358 |
"trial_name": null,
|
359 |
"trial_params": null
|