BayesTensor
commited on
Training in progress, epoch 12, 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 737722356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e725f21bf5e9e86c88f80c57e3bb2704cf1eb07e29d0c579587b5032b0691e76
|
3 |
size 737722356
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1475564538
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af46f8dedd17a334921f28292e8c85822fc33f297652c8536b53d32b54f2073c
|
3 |
size 1475564538
|
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 sha256:8a622f6a101cea5ef2f690e821b18ab364a3198cabaabf2a361e8317a9501bb4
|
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:d7a0e59c63e2086f8607dd910ba9145cdf868d634af5bc4d4ce1666a51f2c790
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.2747629944426283,
|
3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -246,6 +246,22 @@
|
|
246 |
"eval_samples_per_second": 7.053,
|
247 |
"eval_steps_per_second": 3.526,
|
248 |
"step": 2013
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
249 |
}
|
250 |
],
|
251 |
"logging_steps": 100,
|
@@ -265,7 +281,7 @@
|
|
265 |
"attributes": {}
|
266 |
}
|
267 |
},
|
268 |
-
"total_flos":
|
269 |
"train_batch_size": 2,
|
270 |
"trial_name": null,
|
271 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.2747629944426283,
|
3 |
"best_model_checkpoint": "debertalarge-medical-classifier/checkpoint-366",
|
4 |
+
"epoch": 12.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2196,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
246 |
"eval_samples_per_second": 7.053,
|
247 |
"eval_steps_per_second": 3.526,
|
248 |
"step": 2013
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 11.475409836065573,
|
252 |
+
"grad_norm": 2.8780972957611084,
|
253 |
+
"learning_rate": 2.7049180327868856e-05,
|
254 |
+
"loss": 1.0844,
|
255 |
+
"step": 2100
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 12.0,
|
259 |
+
"eval_f1": 0.2747629944426283,
|
260 |
+
"eval_loss": 1.11479651927948,
|
261 |
+
"eval_runtime": 13.056,
|
262 |
+
"eval_samples_per_second": 7.047,
|
263 |
+
"eval_steps_per_second": 3.523,
|
264 |
+
"step": 2196
|
265 |
}
|
266 |
],
|
267 |
"logging_steps": 100,
|
|
|
281 |
"attributes": {}
|
282 |
}
|
283 |
},
|
284 |
+
"total_flos": 5852322922680000.0,
|
285 |
"train_batch_size": 2,
|
286 |
"trial_name": null,
|
287 |
"trial_params": null
|