Commit ·
40a3b7b
1
Parent(s): 937d27f
(11) class crawler 65e
Browse files- optimizer.pt +3 -0
- pytorch_model.bin +1 -1
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +991 -0
- training_args.bin +2 -2
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6fa49861293b096f4ec4a7287f7759ac99a2062f0f275e63f7280fc15e0f9f6
|
| 3 |
+
size 535750213
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267880109
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:491feb260883d9c03042e7f92de7b291e3680759cf403faee560c936244e4b35
|
| 3 |
size 267880109
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3899805085e9d2ac6cbf41d1e231c8019961099f94de919796ff76ec1a2a6d27
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f164eca888cfa14782f70fc9a282dd4e6c1593faf867ae17dfa46d264aa2942
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:772dd81534f16ccad499eda8bef2dc60508234c8daa4ecae9a5aa2c25f5ac971
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,991 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 65.0,
|
| 5 |
+
"global_step": 6760,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.99,
|
| 12 |
+
"learning_rate": 4.9238165680473374e-05,
|
| 13 |
+
"loss": 1.4565,
|
| 14 |
+
"step": 103
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 1.0,
|
| 18 |
+
"eval_f1": 0.5061315988298739,
|
| 19 |
+
"eval_loss": 1.226438045501709,
|
| 20 |
+
"eval_runtime": 2.9031,
|
| 21 |
+
"eval_samples_per_second": 190.487,
|
| 22 |
+
"eval_steps_per_second": 12.056,
|
| 23 |
+
"step": 104
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.98,
|
| 27 |
+
"learning_rate": 4.8483727810650895e-05,
|
| 28 |
+
"loss": 1.08,
|
| 29 |
+
"step": 206
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 2.0,
|
| 33 |
+
"eval_f1": 0.5585235698125446,
|
| 34 |
+
"eval_loss": 1.1974396705627441,
|
| 35 |
+
"eval_runtime": 2.9416,
|
| 36 |
+
"eval_samples_per_second": 187.991,
|
| 37 |
+
"eval_steps_per_second": 11.898,
|
| 38 |
+
"step": 208
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 2.97,
|
| 42 |
+
"learning_rate": 4.772189349112427e-05,
|
| 43 |
+
"loss": 0.8073,
|
| 44 |
+
"step": 309
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.0,
|
| 48 |
+
"eval_f1": 0.5539323613883379,
|
| 49 |
+
"eval_loss": 1.276489496231079,
|
| 50 |
+
"eval_runtime": 2.969,
|
| 51 |
+
"eval_samples_per_second": 186.259,
|
| 52 |
+
"eval_steps_per_second": 11.789,
|
| 53 |
+
"step": 312
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 3.96,
|
| 57 |
+
"learning_rate": 4.696005917159764e-05,
|
| 58 |
+
"loss": 0.5577,
|
| 59 |
+
"step": 412
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.0,
|
| 63 |
+
"eval_f1": 0.5553847052045314,
|
| 64 |
+
"eval_loss": 1.427822232246399,
|
| 65 |
+
"eval_runtime": 2.9361,
|
| 66 |
+
"eval_samples_per_second": 188.346,
|
| 67 |
+
"eval_steps_per_second": 11.921,
|
| 68 |
+
"step": 416
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 4.95,
|
| 72 |
+
"learning_rate": 4.619822485207101e-05,
|
| 73 |
+
"loss": 0.3941,
|
| 74 |
+
"step": 515
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 5.0,
|
| 78 |
+
"eval_f1": 0.5570342860609194,
|
| 79 |
+
"eval_loss": 1.6517128944396973,
|
| 80 |
+
"eval_runtime": 2.9022,
|
| 81 |
+
"eval_samples_per_second": 190.542,
|
| 82 |
+
"eval_steps_per_second": 12.06,
|
| 83 |
+
"step": 520
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 5.94,
|
| 87 |
+
"learning_rate": 4.543639053254438e-05,
|
| 88 |
+
"loss": 0.2878,
|
| 89 |
+
"step": 618
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 6.0,
|
| 93 |
+
"eval_f1": 0.5619826716090497,
|
| 94 |
+
"eval_loss": 1.8180437088012695,
|
| 95 |
+
"eval_runtime": 2.855,
|
| 96 |
+
"eval_samples_per_second": 193.697,
|
| 97 |
+
"eval_steps_per_second": 12.259,
|
| 98 |
+
"step": 624
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 6.93,
|
| 102 |
+
"learning_rate": 4.468195266272189e-05,
|
| 103 |
+
"loss": 0.2337,
|
| 104 |
+
"step": 721
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 7.0,
|
| 108 |
+
"eval_f1": 0.5674708526030706,
|
| 109 |
+
"eval_loss": 1.9061989784240723,
|
| 110 |
+
"eval_runtime": 2.8641,
|
| 111 |
+
"eval_samples_per_second": 193.077,
|
| 112 |
+
"eval_steps_per_second": 12.22,
|
| 113 |
+
"step": 728
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 7.92,
|
| 117 |
+
"learning_rate": 4.392011834319526e-05,
|
| 118 |
+
"loss": 0.1743,
|
| 119 |
+
"step": 824
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 8.0,
|
| 123 |
+
"eval_f1": 0.5571774381839604,
|
| 124 |
+
"eval_loss": 2.166078805923462,
|
| 125 |
+
"eval_runtime": 2.8885,
|
| 126 |
+
"eval_samples_per_second": 191.449,
|
| 127 |
+
"eval_steps_per_second": 12.117,
|
| 128 |
+
"step": 832
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 8.91,
|
| 132 |
+
"learning_rate": 4.315828402366864e-05,
|
| 133 |
+
"loss": 0.1324,
|
| 134 |
+
"step": 927
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 9.0,
|
| 138 |
+
"eval_f1": 0.5586999359656486,
|
| 139 |
+
"eval_loss": 2.1434192657470703,
|
| 140 |
+
"eval_runtime": 2.8793,
|
| 141 |
+
"eval_samples_per_second": 192.062,
|
| 142 |
+
"eval_steps_per_second": 12.156,
|
| 143 |
+
"step": 936
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 9.9,
|
| 147 |
+
"learning_rate": 4.239644970414201e-05,
|
| 148 |
+
"loss": 0.1051,
|
| 149 |
+
"step": 1030
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 10.0,
|
| 153 |
+
"eval_f1": 0.571861247626083,
|
| 154 |
+
"eval_loss": 2.2514231204986572,
|
| 155 |
+
"eval_runtime": 2.8876,
|
| 156 |
+
"eval_samples_per_second": 191.511,
|
| 157 |
+
"eval_steps_per_second": 12.121,
|
| 158 |
+
"step": 1040
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 10.89,
|
| 162 |
+
"learning_rate": 4.163461538461539e-05,
|
| 163 |
+
"loss": 0.1016,
|
| 164 |
+
"step": 1133
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 11.0,
|
| 168 |
+
"eval_f1": 0.5608736700927537,
|
| 169 |
+
"eval_loss": 2.452277898788452,
|
| 170 |
+
"eval_runtime": 2.9662,
|
| 171 |
+
"eval_samples_per_second": 186.434,
|
| 172 |
+
"eval_steps_per_second": 11.8,
|
| 173 |
+
"step": 1144
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 11.88,
|
| 177 |
+
"learning_rate": 4.0872781065088764e-05,
|
| 178 |
+
"loss": 0.0814,
|
| 179 |
+
"step": 1236
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 12.0,
|
| 183 |
+
"eval_f1": 0.5643677851728315,
|
| 184 |
+
"eval_loss": 2.5340888500213623,
|
| 185 |
+
"eval_runtime": 2.8457,
|
| 186 |
+
"eval_samples_per_second": 194.329,
|
| 187 |
+
"eval_steps_per_second": 12.299,
|
| 188 |
+
"step": 1248
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 12.88,
|
| 192 |
+
"learning_rate": 4.0110946745562136e-05,
|
| 193 |
+
"loss": 0.0673,
|
| 194 |
+
"step": 1339
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 13.0,
|
| 198 |
+
"eval_f1": 0.5738915229311208,
|
| 199 |
+
"eval_loss": 2.6217703819274902,
|
| 200 |
+
"eval_runtime": 2.9035,
|
| 201 |
+
"eval_samples_per_second": 190.46,
|
| 202 |
+
"eval_steps_per_second": 12.054,
|
| 203 |
+
"step": 1352
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 13.87,
|
| 207 |
+
"learning_rate": 3.934911242603551e-05,
|
| 208 |
+
"loss": 0.0684,
|
| 209 |
+
"step": 1442
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 14.0,
|
| 213 |
+
"eval_f1": 0.5366433281464598,
|
| 214 |
+
"eval_loss": 2.9552414417266846,
|
| 215 |
+
"eval_runtime": 2.9063,
|
| 216 |
+
"eval_samples_per_second": 190.277,
|
| 217 |
+
"eval_steps_per_second": 12.043,
|
| 218 |
+
"step": 1456
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 14.86,
|
| 222 |
+
"learning_rate": 3.858727810650888e-05,
|
| 223 |
+
"loss": 0.0466,
|
| 224 |
+
"step": 1545
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 15.0,
|
| 228 |
+
"eval_f1": 0.5787084254032917,
|
| 229 |
+
"eval_loss": 2.7240512371063232,
|
| 230 |
+
"eval_runtime": 2.8887,
|
| 231 |
+
"eval_samples_per_second": 191.438,
|
| 232 |
+
"eval_steps_per_second": 12.116,
|
| 233 |
+
"step": 1560
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 15.85,
|
| 237 |
+
"learning_rate": 3.782544378698225e-05,
|
| 238 |
+
"loss": 0.0577,
|
| 239 |
+
"step": 1648
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 16.0,
|
| 243 |
+
"eval_f1": 0.5666557248979172,
|
| 244 |
+
"eval_loss": 2.821897506713867,
|
| 245 |
+
"eval_runtime": 2.8994,
|
| 246 |
+
"eval_samples_per_second": 190.727,
|
| 247 |
+
"eval_steps_per_second": 12.071,
|
| 248 |
+
"step": 1664
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 16.84,
|
| 252 |
+
"learning_rate": 3.706360946745562e-05,
|
| 253 |
+
"loss": 0.042,
|
| 254 |
+
"step": 1751
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 17.0,
|
| 258 |
+
"eval_f1": 0.56033452806457,
|
| 259 |
+
"eval_loss": 2.9155900478363037,
|
| 260 |
+
"eval_runtime": 2.9258,
|
| 261 |
+
"eval_samples_per_second": 189.01,
|
| 262 |
+
"eval_steps_per_second": 11.963,
|
| 263 |
+
"step": 1768
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 17.83,
|
| 267 |
+
"learning_rate": 3.6301775147928995e-05,
|
| 268 |
+
"loss": 0.0404,
|
| 269 |
+
"step": 1854
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 18.0,
|
| 273 |
+
"eval_f1": 0.5621979513908701,
|
| 274 |
+
"eval_loss": 2.893630266189575,
|
| 275 |
+
"eval_runtime": 2.9319,
|
| 276 |
+
"eval_samples_per_second": 188.613,
|
| 277 |
+
"eval_steps_per_second": 11.938,
|
| 278 |
+
"step": 1872
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 18.82,
|
| 282 |
+
"learning_rate": 3.553994082840237e-05,
|
| 283 |
+
"loss": 0.0426,
|
| 284 |
+
"step": 1957
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 19.0,
|
| 288 |
+
"eval_f1": 0.5766503161850353,
|
| 289 |
+
"eval_loss": 3.00762939453125,
|
| 290 |
+
"eval_runtime": 2.9064,
|
| 291 |
+
"eval_samples_per_second": 190.271,
|
| 292 |
+
"eval_steps_per_second": 12.042,
|
| 293 |
+
"step": 1976
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 19.81,
|
| 297 |
+
"learning_rate": 3.477810650887574e-05,
|
| 298 |
+
"loss": 0.0361,
|
| 299 |
+
"step": 2060
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 20.0,
|
| 303 |
+
"eval_f1": 0.5565194377868121,
|
| 304 |
+
"eval_loss": 3.043562173843384,
|
| 305 |
+
"eval_runtime": 2.9099,
|
| 306 |
+
"eval_samples_per_second": 190.043,
|
| 307 |
+
"eval_steps_per_second": 12.028,
|
| 308 |
+
"step": 2080
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 20.8,
|
| 312 |
+
"learning_rate": 3.401627218934911e-05,
|
| 313 |
+
"loss": 0.039,
|
| 314 |
+
"step": 2163
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 21.0,
|
| 318 |
+
"eval_f1": 0.5661283975776907,
|
| 319 |
+
"eval_loss": 3.034050226211548,
|
| 320 |
+
"eval_runtime": 2.8472,
|
| 321 |
+
"eval_samples_per_second": 194.228,
|
| 322 |
+
"eval_steps_per_second": 12.293,
|
| 323 |
+
"step": 2184
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 21.79,
|
| 327 |
+
"learning_rate": 3.325443786982248e-05,
|
| 328 |
+
"loss": 0.0311,
|
| 329 |
+
"step": 2266
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 22.0,
|
| 333 |
+
"eval_f1": 0.5698598461896062,
|
| 334 |
+
"eval_loss": 3.1546428203582764,
|
| 335 |
+
"eval_runtime": 2.8965,
|
| 336 |
+
"eval_samples_per_second": 190.921,
|
| 337 |
+
"eval_steps_per_second": 12.084,
|
| 338 |
+
"step": 2288
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 22.78,
|
| 342 |
+
"learning_rate": 3.2492603550295855e-05,
|
| 343 |
+
"loss": 0.0296,
|
| 344 |
+
"step": 2369
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 23.0,
|
| 348 |
+
"eval_f1": 0.5584145320343268,
|
| 349 |
+
"eval_loss": 3.3160221576690674,
|
| 350 |
+
"eval_runtime": 2.9004,
|
| 351 |
+
"eval_samples_per_second": 190.664,
|
| 352 |
+
"eval_steps_per_second": 12.067,
|
| 353 |
+
"step": 2392
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 23.77,
|
| 357 |
+
"learning_rate": 3.1730769230769234e-05,
|
| 358 |
+
"loss": 0.03,
|
| 359 |
+
"step": 2472
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 24.0,
|
| 363 |
+
"eval_f1": 0.5765799312977243,
|
| 364 |
+
"eval_loss": 3.2025678157806396,
|
| 365 |
+
"eval_runtime": 2.837,
|
| 366 |
+
"eval_samples_per_second": 194.921,
|
| 367 |
+
"eval_steps_per_second": 12.337,
|
| 368 |
+
"step": 2496
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 24.76,
|
| 372 |
+
"learning_rate": 3.0968934911242606e-05,
|
| 373 |
+
"loss": 0.0333,
|
| 374 |
+
"step": 2575
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 25.0,
|
| 378 |
+
"eval_f1": 0.5689553713820321,
|
| 379 |
+
"eval_loss": 3.211634397506714,
|
| 380 |
+
"eval_runtime": 2.9044,
|
| 381 |
+
"eval_samples_per_second": 190.402,
|
| 382 |
+
"eval_steps_per_second": 12.051,
|
| 383 |
+
"step": 2600
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 25.75,
|
| 387 |
+
"learning_rate": 3.0207100591715974e-05,
|
| 388 |
+
"loss": 0.0321,
|
| 389 |
+
"step": 2678
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 26.0,
|
| 393 |
+
"eval_f1": 0.5756108062994573,
|
| 394 |
+
"eval_loss": 3.2678425312042236,
|
| 395 |
+
"eval_runtime": 2.8888,
|
| 396 |
+
"eval_samples_per_second": 191.428,
|
| 397 |
+
"eval_steps_per_second": 12.116,
|
| 398 |
+
"step": 2704
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 26.74,
|
| 402 |
+
"learning_rate": 2.944526627218935e-05,
|
| 403 |
+
"loss": 0.0263,
|
| 404 |
+
"step": 2781
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 27.0,
|
| 408 |
+
"eval_f1": 0.5758065273285641,
|
| 409 |
+
"eval_loss": 3.2969822883605957,
|
| 410 |
+
"eval_runtime": 2.9527,
|
| 411 |
+
"eval_samples_per_second": 187.286,
|
| 412 |
+
"eval_steps_per_second": 11.854,
|
| 413 |
+
"step": 2808
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 27.73,
|
| 417 |
+
"learning_rate": 2.8683431952662725e-05,
|
| 418 |
+
"loss": 0.0281,
|
| 419 |
+
"step": 2884
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 28.0,
|
| 423 |
+
"eval_f1": 0.5781354966097151,
|
| 424 |
+
"eval_loss": 3.3730037212371826,
|
| 425 |
+
"eval_runtime": 2.8614,
|
| 426 |
+
"eval_samples_per_second": 193.264,
|
| 427 |
+
"eval_steps_per_second": 12.232,
|
| 428 |
+
"step": 2912
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 28.72,
|
| 432 |
+
"learning_rate": 2.7921597633136097e-05,
|
| 433 |
+
"loss": 0.0282,
|
| 434 |
+
"step": 2987
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 29.0,
|
| 438 |
+
"eval_f1": 0.5741866124789994,
|
| 439 |
+
"eval_loss": 3.364117383956909,
|
| 440 |
+
"eval_runtime": 2.8696,
|
| 441 |
+
"eval_samples_per_second": 192.707,
|
| 442 |
+
"eval_steps_per_second": 12.197,
|
| 443 |
+
"step": 3016
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 29.71,
|
| 447 |
+
"learning_rate": 2.7159763313609472e-05,
|
| 448 |
+
"loss": 0.0296,
|
| 449 |
+
"step": 3090
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 30.0,
|
| 453 |
+
"eval_f1": 0.5771762774162508,
|
| 454 |
+
"eval_loss": 3.3623032569885254,
|
| 455 |
+
"eval_runtime": 2.9567,
|
| 456 |
+
"eval_samples_per_second": 187.031,
|
| 457 |
+
"eval_steps_per_second": 11.837,
|
| 458 |
+
"step": 3120
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 30.7,
|
| 462 |
+
"learning_rate": 2.6397928994082844e-05,
|
| 463 |
+
"loss": 0.0308,
|
| 464 |
+
"step": 3193
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 31.0,
|
| 468 |
+
"eval_f1": 0.578537002980747,
|
| 469 |
+
"eval_loss": 3.4039528369903564,
|
| 470 |
+
"eval_runtime": 2.8263,
|
| 471 |
+
"eval_samples_per_second": 195.66,
|
| 472 |
+
"eval_steps_per_second": 12.384,
|
| 473 |
+
"step": 3224
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 31.69,
|
| 477 |
+
"learning_rate": 2.5636094674556216e-05,
|
| 478 |
+
"loss": 0.0308,
|
| 479 |
+
"step": 3296
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 32.0,
|
| 483 |
+
"eval_f1": 0.575919412837488,
|
| 484 |
+
"eval_loss": 3.392319679260254,
|
| 485 |
+
"eval_runtime": 2.9375,
|
| 486 |
+
"eval_samples_per_second": 188.254,
|
| 487 |
+
"eval_steps_per_second": 11.915,
|
| 488 |
+
"step": 3328
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 32.68,
|
| 492 |
+
"learning_rate": 2.4874260355029588e-05,
|
| 493 |
+
"loss": 0.0262,
|
| 494 |
+
"step": 3399
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 33.0,
|
| 498 |
+
"eval_f1": 0.5563772891428104,
|
| 499 |
+
"eval_loss": 3.4757542610168457,
|
| 500 |
+
"eval_runtime": 2.865,
|
| 501 |
+
"eval_samples_per_second": 193.019,
|
| 502 |
+
"eval_steps_per_second": 12.216,
|
| 503 |
+
"step": 3432
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 33.67,
|
| 507 |
+
"learning_rate": 2.411242603550296e-05,
|
| 508 |
+
"loss": 0.0319,
|
| 509 |
+
"step": 3502
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 34.0,
|
| 513 |
+
"eval_f1": 0.5738865992034025,
|
| 514 |
+
"eval_loss": 3.425334930419922,
|
| 515 |
+
"eval_runtime": 2.9109,
|
| 516 |
+
"eval_samples_per_second": 189.974,
|
| 517 |
+
"eval_steps_per_second": 12.024,
|
| 518 |
+
"step": 3536
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 34.66,
|
| 522 |
+
"learning_rate": 2.3350591715976332e-05,
|
| 523 |
+
"loss": 0.0277,
|
| 524 |
+
"step": 3605
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 35.0,
|
| 528 |
+
"eval_f1": 0.5785980513801816,
|
| 529 |
+
"eval_loss": 3.4686436653137207,
|
| 530 |
+
"eval_runtime": 2.93,
|
| 531 |
+
"eval_samples_per_second": 188.738,
|
| 532 |
+
"eval_steps_per_second": 11.945,
|
| 533 |
+
"step": 3640
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 35.65,
|
| 537 |
+
"learning_rate": 2.2588757396449707e-05,
|
| 538 |
+
"loss": 0.0289,
|
| 539 |
+
"step": 3708
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 36.0,
|
| 543 |
+
"eval_f1": 0.5836924697871717,
|
| 544 |
+
"eval_loss": 3.462078094482422,
|
| 545 |
+
"eval_runtime": 2.8428,
|
| 546 |
+
"eval_samples_per_second": 194.527,
|
| 547 |
+
"eval_steps_per_second": 12.312,
|
| 548 |
+
"step": 3744
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 36.64,
|
| 552 |
+
"learning_rate": 2.182692307692308e-05,
|
| 553 |
+
"loss": 0.0247,
|
| 554 |
+
"step": 3811
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 37.0,
|
| 558 |
+
"eval_f1": 0.5734707197245945,
|
| 559 |
+
"eval_loss": 3.481998920440674,
|
| 560 |
+
"eval_runtime": 3.0017,
|
| 561 |
+
"eval_samples_per_second": 184.228,
|
| 562 |
+
"eval_steps_per_second": 11.66,
|
| 563 |
+
"step": 3848
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 37.63,
|
| 567 |
+
"learning_rate": 2.106508875739645e-05,
|
| 568 |
+
"loss": 0.0303,
|
| 569 |
+
"step": 3914
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 38.0,
|
| 573 |
+
"eval_f1": 0.5770262969511715,
|
| 574 |
+
"eval_loss": 3.466510772705078,
|
| 575 |
+
"eval_runtime": 2.8587,
|
| 576 |
+
"eval_samples_per_second": 193.442,
|
| 577 |
+
"eval_steps_per_second": 12.243,
|
| 578 |
+
"step": 3952
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 38.62,
|
| 582 |
+
"learning_rate": 2.0303254437869823e-05,
|
| 583 |
+
"loss": 0.0239,
|
| 584 |
+
"step": 4017
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 39.0,
|
| 588 |
+
"eval_f1": 0.5666519467364683,
|
| 589 |
+
"eval_loss": 3.5593807697296143,
|
| 590 |
+
"eval_runtime": 2.8222,
|
| 591 |
+
"eval_samples_per_second": 195.946,
|
| 592 |
+
"eval_steps_per_second": 12.402,
|
| 593 |
+
"step": 4056
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 39.62,
|
| 597 |
+
"learning_rate": 1.9541420118343195e-05,
|
| 598 |
+
"loss": 0.0262,
|
| 599 |
+
"step": 4120
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 40.0,
|
| 603 |
+
"eval_f1": 0.5808476343157906,
|
| 604 |
+
"eval_loss": 3.5302422046661377,
|
| 605 |
+
"eval_runtime": 2.8598,
|
| 606 |
+
"eval_samples_per_second": 193.368,
|
| 607 |
+
"eval_steps_per_second": 12.238,
|
| 608 |
+
"step": 4160
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 40.61,
|
| 612 |
+
"learning_rate": 1.8779585798816567e-05,
|
| 613 |
+
"loss": 0.0282,
|
| 614 |
+
"step": 4223
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 41.0,
|
| 618 |
+
"eval_f1": 0.5835890408164021,
|
| 619 |
+
"eval_loss": 3.4572339057922363,
|
| 620 |
+
"eval_runtime": 2.8566,
|
| 621 |
+
"eval_samples_per_second": 193.584,
|
| 622 |
+
"eval_steps_per_second": 12.252,
|
| 623 |
+
"step": 4264
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 41.6,
|
| 627 |
+
"learning_rate": 1.8025147928994084e-05,
|
| 628 |
+
"loss": 0.0469,
|
| 629 |
+
"step": 4326
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 42.0,
|
| 633 |
+
"eval_f1": 0.5685331156394952,
|
| 634 |
+
"eval_loss": 3.609334707260132,
|
| 635 |
+
"eval_runtime": 2.8251,
|
| 636 |
+
"eval_samples_per_second": 195.747,
|
| 637 |
+
"eval_steps_per_second": 12.389,
|
| 638 |
+
"step": 4368
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 42.59,
|
| 642 |
+
"learning_rate": 1.7263313609467456e-05,
|
| 643 |
+
"loss": 0.0302,
|
| 644 |
+
"step": 4429
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 43.0,
|
| 648 |
+
"eval_f1": 0.5684067370608473,
|
| 649 |
+
"eval_loss": 3.6115400791168213,
|
| 650 |
+
"eval_runtime": 2.9194,
|
| 651 |
+
"eval_samples_per_second": 189.42,
|
| 652 |
+
"eval_steps_per_second": 11.989,
|
| 653 |
+
"step": 4472
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 43.58,
|
| 657 |
+
"learning_rate": 1.650147928994083e-05,
|
| 658 |
+
"loss": 0.0289,
|
| 659 |
+
"step": 4532
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 44.0,
|
| 663 |
+
"eval_f1": 0.5757900647671246,
|
| 664 |
+
"eval_loss": 3.629568099975586,
|
| 665 |
+
"eval_runtime": 2.9036,
|
| 666 |
+
"eval_samples_per_second": 190.453,
|
| 667 |
+
"eval_steps_per_second": 12.054,
|
| 668 |
+
"step": 4576
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 44.57,
|
| 672 |
+
"learning_rate": 1.5739644970414204e-05,
|
| 673 |
+
"loss": 0.0254,
|
| 674 |
+
"step": 4635
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 45.0,
|
| 678 |
+
"eval_f1": 0.5689505752768721,
|
| 679 |
+
"eval_loss": 3.7250843048095703,
|
| 680 |
+
"eval_runtime": 2.9726,
|
| 681 |
+
"eval_samples_per_second": 186.035,
|
| 682 |
+
"eval_steps_per_second": 11.774,
|
| 683 |
+
"step": 4680
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 45.56,
|
| 687 |
+
"learning_rate": 1.4977810650887576e-05,
|
| 688 |
+
"loss": 0.0283,
|
| 689 |
+
"step": 4738
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 46.0,
|
| 693 |
+
"eval_f1": 0.5592198654774546,
|
| 694 |
+
"eval_loss": 3.726353645324707,
|
| 695 |
+
"eval_runtime": 2.9328,
|
| 696 |
+
"eval_samples_per_second": 188.559,
|
| 697 |
+
"eval_steps_per_second": 11.934,
|
| 698 |
+
"step": 4784
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 46.55,
|
| 702 |
+
"learning_rate": 1.4215976331360948e-05,
|
| 703 |
+
"loss": 0.0246,
|
| 704 |
+
"step": 4841
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 47.0,
|
| 708 |
+
"eval_f1": 0.5650157110711802,
|
| 709 |
+
"eval_loss": 3.7832093238830566,
|
| 710 |
+
"eval_runtime": 2.9067,
|
| 711 |
+
"eval_samples_per_second": 190.249,
|
| 712 |
+
"eval_steps_per_second": 12.041,
|
| 713 |
+
"step": 4888
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 47.54,
|
| 717 |
+
"learning_rate": 1.345414201183432e-05,
|
| 718 |
+
"loss": 0.0311,
|
| 719 |
+
"step": 4944
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 48.0,
|
| 723 |
+
"eval_f1": 0.5681512072556809,
|
| 724 |
+
"eval_loss": 3.6964025497436523,
|
| 725 |
+
"eval_runtime": 2.9008,
|
| 726 |
+
"eval_samples_per_second": 190.634,
|
| 727 |
+
"eval_steps_per_second": 12.065,
|
| 728 |
+
"step": 4992
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 48.53,
|
| 732 |
+
"learning_rate": 1.2692307692307691e-05,
|
| 733 |
+
"loss": 0.0268,
|
| 734 |
+
"step": 5047
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 49.0,
|
| 738 |
+
"eval_f1": 0.5674808111122996,
|
| 739 |
+
"eval_loss": 3.7195167541503906,
|
| 740 |
+
"eval_runtime": 2.8604,
|
| 741 |
+
"eval_samples_per_second": 193.33,
|
| 742 |
+
"eval_steps_per_second": 12.236,
|
| 743 |
+
"step": 5096
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 49.52,
|
| 747 |
+
"learning_rate": 1.1930473372781067e-05,
|
| 748 |
+
"loss": 0.0293,
|
| 749 |
+
"step": 5150
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 50.0,
|
| 753 |
+
"eval_f1": 0.5614419693521525,
|
| 754 |
+
"eval_loss": 3.752530097961426,
|
| 755 |
+
"eval_runtime": 2.8761,
|
| 756 |
+
"eval_samples_per_second": 192.275,
|
| 757 |
+
"eval_steps_per_second": 12.169,
|
| 758 |
+
"step": 5200
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 50.51,
|
| 762 |
+
"learning_rate": 1.1168639053254439e-05,
|
| 763 |
+
"loss": 0.0282,
|
| 764 |
+
"step": 5253
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 51.0,
|
| 768 |
+
"eval_f1": 0.5655838635083059,
|
| 769 |
+
"eval_loss": 3.7514984607696533,
|
| 770 |
+
"eval_runtime": 2.8609,
|
| 771 |
+
"eval_samples_per_second": 193.296,
|
| 772 |
+
"eval_steps_per_second": 12.234,
|
| 773 |
+
"step": 5304
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 51.5,
|
| 777 |
+
"learning_rate": 1.040680473372781e-05,
|
| 778 |
+
"loss": 0.0248,
|
| 779 |
+
"step": 5356
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 52.0,
|
| 783 |
+
"eval_f1": 0.5590951084274065,
|
| 784 |
+
"eval_loss": 3.7639315128326416,
|
| 785 |
+
"eval_runtime": 2.8211,
|
| 786 |
+
"eval_samples_per_second": 196.025,
|
| 787 |
+
"eval_steps_per_second": 12.407,
|
| 788 |
+
"step": 5408
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 52.49,
|
| 792 |
+
"learning_rate": 9.644970414201183e-06,
|
| 793 |
+
"loss": 0.0257,
|
| 794 |
+
"step": 5459
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 53.0,
|
| 798 |
+
"eval_f1": 0.5480134247467852,
|
| 799 |
+
"eval_loss": 3.824922800064087,
|
| 800 |
+
"eval_runtime": 2.8475,
|
| 801 |
+
"eval_samples_per_second": 194.205,
|
| 802 |
+
"eval_steps_per_second": 12.291,
|
| 803 |
+
"step": 5512
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 53.48,
|
| 807 |
+
"learning_rate": 8.883136094674558e-06,
|
| 808 |
+
"loss": 0.0235,
|
| 809 |
+
"step": 5562
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 54.0,
|
| 813 |
+
"eval_f1": 0.5565796472147394,
|
| 814 |
+
"eval_loss": 3.7871253490448,
|
| 815 |
+
"eval_runtime": 2.9817,
|
| 816 |
+
"eval_samples_per_second": 185.462,
|
| 817 |
+
"eval_steps_per_second": 11.738,
|
| 818 |
+
"step": 5616
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 54.47,
|
| 822 |
+
"learning_rate": 8.12130177514793e-06,
|
| 823 |
+
"loss": 0.0299,
|
| 824 |
+
"step": 5665
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 55.0,
|
| 828 |
+
"eval_f1": 0.5574154263000176,
|
| 829 |
+
"eval_loss": 3.788760185241699,
|
| 830 |
+
"eval_runtime": 2.8852,
|
| 831 |
+
"eval_samples_per_second": 191.665,
|
| 832 |
+
"eval_steps_per_second": 12.131,
|
| 833 |
+
"step": 5720
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 55.46,
|
| 837 |
+
"learning_rate": 7.359467455621302e-06,
|
| 838 |
+
"loss": 0.0277,
|
| 839 |
+
"step": 5768
|
| 840 |
+
},
|
| 841 |
+
{
|
| 842 |
+
"epoch": 56.0,
|
| 843 |
+
"eval_f1": 0.563024311843682,
|
| 844 |
+
"eval_loss": 3.7907044887542725,
|
| 845 |
+
"eval_runtime": 2.8658,
|
| 846 |
+
"eval_samples_per_second": 192.962,
|
| 847 |
+
"eval_steps_per_second": 12.213,
|
| 848 |
+
"step": 5824
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 56.45,
|
| 852 |
+
"learning_rate": 6.597633136094675e-06,
|
| 853 |
+
"loss": 0.0256,
|
| 854 |
+
"step": 5871
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 57.0,
|
| 858 |
+
"eval_f1": 0.56153234588093,
|
| 859 |
+
"eval_loss": 3.799422264099121,
|
| 860 |
+
"eval_runtime": 2.8666,
|
| 861 |
+
"eval_samples_per_second": 192.912,
|
| 862 |
+
"eval_steps_per_second": 12.21,
|
| 863 |
+
"step": 5928
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 57.44,
|
| 867 |
+
"learning_rate": 5.8357988165680474e-06,
|
| 868 |
+
"loss": 0.0226,
|
| 869 |
+
"step": 5974
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 58.0,
|
| 873 |
+
"eval_f1": 0.5555061070073688,
|
| 874 |
+
"eval_loss": 3.811858892440796,
|
| 875 |
+
"eval_runtime": 2.8683,
|
| 876 |
+
"eval_samples_per_second": 192.797,
|
| 877 |
+
"eval_steps_per_second": 12.202,
|
| 878 |
+
"step": 6032
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 58.43,
|
| 882 |
+
"learning_rate": 5.07396449704142e-06,
|
| 883 |
+
"loss": 0.0284,
|
| 884 |
+
"step": 6077
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 59.0,
|
| 888 |
+
"eval_f1": 0.5597671150511061,
|
| 889 |
+
"eval_loss": 3.8192451000213623,
|
| 890 |
+
"eval_runtime": 2.8512,
|
| 891 |
+
"eval_samples_per_second": 193.951,
|
| 892 |
+
"eval_steps_per_second": 12.275,
|
| 893 |
+
"step": 6136
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 59.42,
|
| 897 |
+
"learning_rate": 4.312130177514793e-06,
|
| 898 |
+
"loss": 0.0233,
|
| 899 |
+
"step": 6180
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 60.0,
|
| 903 |
+
"eval_f1": 0.5584681716027172,
|
| 904 |
+
"eval_loss": 3.823091983795166,
|
| 905 |
+
"eval_runtime": 2.9385,
|
| 906 |
+
"eval_samples_per_second": 188.191,
|
| 907 |
+
"eval_steps_per_second": 11.911,
|
| 908 |
+
"step": 6240
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 60.41,
|
| 912 |
+
"learning_rate": 3.550295857988166e-06,
|
| 913 |
+
"loss": 0.0266,
|
| 914 |
+
"step": 6283
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 61.0,
|
| 918 |
+
"eval_f1": 0.5625000576804086,
|
| 919 |
+
"eval_loss": 3.8085415363311768,
|
| 920 |
+
"eval_runtime": 2.9015,
|
| 921 |
+
"eval_samples_per_second": 190.588,
|
| 922 |
+
"eval_steps_per_second": 12.063,
|
| 923 |
+
"step": 6344
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 61.4,
|
| 927 |
+
"learning_rate": 2.7958579881656803e-06,
|
| 928 |
+
"loss": 0.0267,
|
| 929 |
+
"step": 6386
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 62.0,
|
| 933 |
+
"eval_f1": 0.5622167257088028,
|
| 934 |
+
"eval_loss": 3.80642032623291,
|
| 935 |
+
"eval_runtime": 2.8514,
|
| 936 |
+
"eval_samples_per_second": 193.94,
|
| 937 |
+
"eval_steps_per_second": 12.275,
|
| 938 |
+
"step": 6448
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 62.39,
|
| 942 |
+
"learning_rate": 2.034023668639053e-06,
|
| 943 |
+
"loss": 0.0281,
|
| 944 |
+
"step": 6489
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 63.0,
|
| 948 |
+
"eval_f1": 0.564106811375439,
|
| 949 |
+
"eval_loss": 3.8057875633239746,
|
| 950 |
+
"eval_runtime": 2.8945,
|
| 951 |
+
"eval_samples_per_second": 191.055,
|
| 952 |
+
"eval_steps_per_second": 12.092,
|
| 953 |
+
"step": 6552
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 63.38,
|
| 957 |
+
"learning_rate": 1.2721893491124261e-06,
|
| 958 |
+
"loss": 0.025,
|
| 959 |
+
"step": 6592
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 64.0,
|
| 963 |
+
"eval_f1": 0.5644375312998279,
|
| 964 |
+
"eval_loss": 3.807055950164795,
|
| 965 |
+
"eval_runtime": 2.8941,
|
| 966 |
+
"eval_samples_per_second": 191.08,
|
| 967 |
+
"eval_steps_per_second": 12.094,
|
| 968 |
+
"step": 6656
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 64.38,
|
| 972 |
+
"learning_rate": 5.103550295857988e-07,
|
| 973 |
+
"loss": 0.0226,
|
| 974 |
+
"step": 6695
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 65.0,
|
| 978 |
+
"eval_f1": 0.5644375312998279,
|
| 979 |
+
"eval_loss": 3.807528018951416,
|
| 980 |
+
"eval_runtime": 2.8626,
|
| 981 |
+
"eval_samples_per_second": 193.181,
|
| 982 |
+
"eval_steps_per_second": 12.227,
|
| 983 |
+
"step": 6760
|
| 984 |
+
}
|
| 985 |
+
],
|
| 986 |
+
"max_steps": 6760,
|
| 987 |
+
"num_train_epochs": 65,
|
| 988 |
+
"total_flos": 1.4286659901696e+16,
|
| 989 |
+
"trial_name": null,
|
| 990 |
+
"trial_params": null
|
| 991 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69dba15562adc963c0e958faa40949482ed3f4a4e7db086eedc1130e4eecc7b6
|
| 3 |
+
size 3707
|