avsolatorio
commited on
Commit
•
dbeb19d
1
Parent(s):
d9a4e3b
Training in progress, step 14000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 567860028
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8872fada1a981cf6b5a3b4e8ccf8c61843bbeb383d907f5afdf234ab3625087d
|
3 |
size 567860028
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1135783354
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d3d3afd06995d892904de019bc49182323dd2135abf4e4a204ebe2485e31f61
|
3 |
size 1135783354
|
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:b3067b28aa64de4757065dd8a01a67d3704c9818184e3b87673b274005079225
|
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 sha256:33ec0c6c7881febe86af83de0fd1c05de3d6b8cdacbf1d5a88958d9ee8777f33
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.03680593520402908,
|
3 |
"best_model_checkpoint": "doc-topic-model_eval-04_train-02/checkpoint-11000",
|
4 |
-
"epoch": 6.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -345,6 +345,32 @@
|
|
345 |
"eval_samples_per_second": 559.778,
|
346 |
"eval_steps_per_second": 2.208,
|
347 |
"step": 13000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
348 |
}
|
349 |
],
|
350 |
"logging_steps": 500,
|
@@ -373,7 +399,7 @@
|
|
373 |
"attributes": {}
|
374 |
}
|
375 |
},
|
376 |
-
"total_flos":
|
377 |
"train_batch_size": 4,
|
378 |
"trial_name": null,
|
379 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.03680593520402908,
|
3 |
"best_model_checkpoint": "doc-topic-model_eval-04_train-02/checkpoint-11000",
|
4 |
+
"epoch": 6.903353057199211,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 14000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
345 |
"eval_samples_per_second": 559.778,
|
346 |
"eval_steps_per_second": 2.208,
|
347 |
"step": 13000
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 6.65680473372781,
|
351 |
+
"grad_norm": 0.3087170124053955,
|
352 |
+
"learning_rate": 1.8668836291913217e-05,
|
353 |
+
"loss": 0.0266,
|
354 |
+
"step": 13500
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 6.903353057199211,
|
358 |
+
"grad_norm": 0.2865307033061981,
|
359 |
+
"learning_rate": 1.8619526627218937e-05,
|
360 |
+
"loss": 0.0272,
|
361 |
+
"step": 14000
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 6.903353057199211,
|
365 |
+
"eval_accuracy": 0.9874545039818313,
|
366 |
+
"eval_f1": 0.6193526200404075,
|
367 |
+
"eval_loss": 0.03758929669857025,
|
368 |
+
"eval_precision": 0.706066843085367,
|
369 |
+
"eval_recall": 0.5516079632465544,
|
370 |
+
"eval_runtime": 14.5181,
|
371 |
+
"eval_samples_per_second": 558.821,
|
372 |
+
"eval_steps_per_second": 2.204,
|
373 |
+
"step": 14000
|
374 |
}
|
375 |
],
|
376 |
"logging_steps": 500,
|
|
|
399 |
"attributes": {}
|
400 |
}
|
401 |
},
|
402 |
+
"total_flos": 316297938560220.0,
|
403 |
"train_batch_size": 4,
|
404 |
"trial_name": null,
|
405 |
"trial_params": null
|