Training in progress, step 90, 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 1001465824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c83497329fb42af49da70fbc3c60c36b43dc83dd65c358fca5f048d008c168f
|
3 |
size 1001465824
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 509176980
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4ba0b62f0ca73cf26460d7ea15aec677a396882d9b4f8029e11d7b4c2cb2668
|
3 |
size 509176980
|
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 sha256:05022b5c93ac0c87641f83d2aeb7aee1afa0bbf65f75509e0da8ffce4e027801
|
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 sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
|
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,
|
@@ -276,6 +276,35 @@
|
|
276 |
"eval_samples_per_second": 7.748,
|
277 |
"eval_steps_per_second": 1.957,
|
278 |
"step": 81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
279 |
}
|
280 |
],
|
281 |
"logging_steps": 3,
|
@@ -295,7 +324,7 @@
|
|
295 |
"attributes": {}
|
296 |
}
|
297 |
},
|
298 |
-
"total_flos": 1.
|
299 |
"train_batch_size": 4,
|
300 |
"trial_name": null,
|
301 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7964601769911505,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 90,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
276 |
"eval_samples_per_second": 7.748,
|
277 |
"eval_steps_per_second": 1.957,
|
278 |
"step": 81
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 0.7433628318584071,
|
282 |
+
"grad_norm": 6.199401832418516e-05,
|
283 |
+
"learning_rate": 7.597595192178702e-06,
|
284 |
+
"loss": 0.0,
|
285 |
+
"step": 84
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.7699115044247787,
|
289 |
+
"grad_norm": 5.3589974413625896e-05,
|
290 |
+
"learning_rate": 5.060297685041659e-06,
|
291 |
+
"loss": 0.0,
|
292 |
+
"step": 87
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 0.7964601769911505,
|
296 |
+
"grad_norm": 0.003909613471478224,
|
297 |
+
"learning_rate": 3.0153689607045845e-06,
|
298 |
+
"loss": 0.0,
|
299 |
+
"step": 90
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 0.7964601769911505,
|
303 |
+
"eval_loss": 2.0171441406091617e-07,
|
304 |
+
"eval_runtime": 12.2288,
|
305 |
+
"eval_samples_per_second": 7.769,
|
306 |
+
"eval_steps_per_second": 1.963,
|
307 |
+
"step": 90
|
308 |
}
|
309 |
],
|
310 |
"logging_steps": 3,
|
|
|
324 |
"attributes": {}
|
325 |
}
|
326 |
},
|
327 |
+
"total_flos": 1.3073439686393856e+17,
|
328 |
"train_batch_size": 4,
|
329 |
"trial_name": null,
|
330 |
"trial_params": null
|