Training in progress, step 2000, 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:d17bad9c011295dd4b19a7e7572de3cbf2645aaad544ed5ffe6f55dcc8878a26
|
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 sha256:8fe379fbfeb0c096e15e4a7204b2c4ddc9fddbd1a60d5e4110f894893e7e567f
|
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 sha256:83e1d9e3c6fddcf57fc2aabd22296e90ae548cdb72410388a1385f5736629c4e
|
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 sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
|
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,
|
@@ -273,13 +273,27 @@
|
|
273 |
"eval_samples_per_second": 30.548,
|
274 |
"eval_steps_per_second": 3.822,
|
275 |
"step": 1900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
276 |
}
|
277 |
],
|
278 |
"logging_steps": 100,
|
279 |
"max_steps": 4116,
|
280 |
"num_train_epochs": 3,
|
281 |
"save_steps": 100,
|
282 |
-
"total_flos": 5.
|
283 |
"trial_name": null,
|
284 |
"trial_params": null
|
285 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.211982011795044,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-2000",
|
4 |
+
"epoch": 1.4571948998178508,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
273 |
"eval_samples_per_second": 30.548,
|
274 |
"eval_steps_per_second": 3.822,
|
275 |
"step": 1900
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.46,
|
279 |
+
"learning_rate": 0.0002,
|
280 |
+
"loss": 2.1926,
|
281 |
+
"step": 2000
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.46,
|
285 |
+
"eval_loss": 2.211982011795044,
|
286 |
+
"eval_runtime": 205.3797,
|
287 |
+
"eval_samples_per_second": 30.548,
|
288 |
+
"eval_steps_per_second": 3.822,
|
289 |
+
"step": 2000
|
290 |
}
|
291 |
],
|
292 |
"logging_steps": 100,
|
293 |
"max_steps": 4116,
|
294 |
"num_train_epochs": 3,
|
295 |
"save_steps": 100,
|
296 |
+
"total_flos": 5.844081922689024e+16,
|
297 |
"trial_name": null,
|
298 |
"trial_params": null
|
299 |
}
|