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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daaa4a6b7826812b8e9965822fbc381115a2fbd7c4b953e302ff03f102a8045c
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96f5fd3635cd53667fc2683a72c7b0a5c82d0855e00b104bc5ff97599142bca1
|
3 |
size 18902665
|
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 sha256:14dabd6ac5b413b42d35c286b0d19e23ed4fec71087c81558b454fea8c926535
|
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": 2.
|
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": 30.5,
|
316 |
"eval_steps_per_second": 3.816,
|
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": 6.
|
325 |
"trial_name": null,
|
326 |
"trial_params": null
|
327 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.1711061000823975,
|
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": 30.5,
|
316 |
"eval_steps_per_second": 3.816,
|
317 |
"step": 2200
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.68,
|
321 |
+
"learning_rate": 0.0002,
|
322 |
+
"loss": 2.1481,
|
323 |
+
"step": 2300
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.68,
|
327 |
+
"eval_loss": 2.1711061000823975,
|
328 |
+
"eval_runtime": 205.9233,
|
329 |
+
"eval_samples_per_second": 30.468,
|
330 |
+
"eval_steps_per_second": 3.812,
|
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": 6.719177798387712e+16,
|
339 |
"trial_name": null,
|
340 |
"trial_params": null
|
341 |
}
|