ramdhanfirdaus
commited on
Commit
•
79920a4
1
Parent(s):
d9b6dd2
Training in progress, step 2300, 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 50338848
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd9bfe3a61b9d671b668afd9854e6e0f31dd1bfaf2c496e8b646c13b4b667b83
|
3 |
size 50338848
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100693001
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:83d8eadc3f5112242fcda8091f4fe5bdcc4a798387065d67067a1d1908ed110a
|
3 |
size 100693001
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91ce772f9b2a32aa1626e6ccbc135efad31ff1869adac26764a35a5c73bb1216
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -315,13 +315,27 @@
|
|
315 |
"eval_samples_per_second": 43.579,
|
316 |
"eval_steps_per_second": 5.453,
|
317 |
"step": 2200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 100,
|
321 |
"max_steps": 4116,
|
322 |
"num_train_epochs": 3,
|
323 |
"save_steps": 100,
|
324 |
-
"total_flos": 1.
|
325 |
"trial_name": null,
|
326 |
"trial_params": null
|
327 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.4158506393432617,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2300",
|
4 |
+
"epoch": 1.6757741347905282,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
315 |
"eval_samples_per_second": 43.579,
|
316 |
"eval_steps_per_second": 5.453,
|
317 |
"step": 2200
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.68,
|
321 |
+
"learning_rate": 0.0002,
|
322 |
+
"loss": 1.4103,
|
323 |
+
"step": 2300
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.68,
|
327 |
+
"eval_loss": 1.4158506393432617,
|
328 |
+
"eval_runtime": 143.8198,
|
329 |
+
"eval_samples_per_second": 43.624,
|
330 |
+
"eval_steps_per_second": 5.458,
|
331 |
+
"step": 2300
|
332 |
}
|
333 |
],
|
334 |
"logging_steps": 100,
|
335 |
"max_steps": 4116,
|
336 |
"num_train_epochs": 3,
|
337 |
"save_steps": 100,
|
338 |
+
"total_flos": 1.3711720075820237e+17,
|
339 |
"trial_name": null,
|
340 |
"trial_params": null
|
341 |
}
|