Upload 6 files
Browse files
checkpoint-116994/my_custom_model.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b89d605c5e94325b01af0b03336ae434f8871638df687b94c03b36e578eb537
|
| 3 |
+
size 502285990
|
checkpoint-116994/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dadcf92f66401229b0fc3840c1f23a6ac82170364711ed8e2c8589b73b60153
|
| 3 |
+
size 1004571002
|
checkpoint-116994/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47d953e44ced351a19079428860d71a230e5396163b3698ac93402f8343bb63e
|
| 3 |
+
size 14244
|
checkpoint-116994/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8360e10dc7b9180c15d3d1c8f7d7f766e80a7dc9f5bac7df9a3f22e31ea497b
|
| 3 |
+
size 1064
|
checkpoint-116994/trainer_state.json
ADDED
|
@@ -0,0 +1,1055 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 36.98830224470439,
|
| 5 |
+
"eval_steps": 1581,
|
| 6 |
+
"global_step": 116994,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5,
|
| 13 |
+
"learning_rate": 4.995001580777743e-05,
|
| 14 |
+
"loss": 3.0674,
|
| 15 |
+
"step": 1581
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.5,
|
| 19 |
+
"eval_loss": 3.00907301902771,
|
| 20 |
+
"eval_runtime": 732.5252,
|
| 21 |
+
"eval_samples_per_second": 44.214,
|
| 22 |
+
"eval_steps_per_second": 1.383,
|
| 23 |
+
"step": 1581
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"learning_rate": 4.990003161555485e-05,
|
| 28 |
+
"loss": 2.8959,
|
| 29 |
+
"step": 3162
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 1.0,
|
| 33 |
+
"eval_loss": 2.149791717529297,
|
| 34 |
+
"eval_runtime": 732.3378,
|
| 35 |
+
"eval_samples_per_second": 44.225,
|
| 36 |
+
"eval_steps_per_second": 1.383,
|
| 37 |
+
"step": 3162
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 1.5,
|
| 41 |
+
"learning_rate": 4.985004742333228e-05,
|
| 42 |
+
"loss": 1.5763,
|
| 43 |
+
"step": 4743
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 1.5,
|
| 47 |
+
"eval_loss": 1.1582367420196533,
|
| 48 |
+
"eval_runtime": 732.2588,
|
| 49 |
+
"eval_samples_per_second": 44.23,
|
| 50 |
+
"eval_steps_per_second": 1.383,
|
| 51 |
+
"step": 4743
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 2.0,
|
| 55 |
+
"learning_rate": 4.9800063231109704e-05,
|
| 56 |
+
"loss": 1.072,
|
| 57 |
+
"step": 6324
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.0,
|
| 61 |
+
"eval_loss": 0.8775840401649475,
|
| 62 |
+
"eval_runtime": 733.2045,
|
| 63 |
+
"eval_samples_per_second": 44.173,
|
| 64 |
+
"eval_steps_per_second": 1.382,
|
| 65 |
+
"step": 6324
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.5,
|
| 69 |
+
"learning_rate": 4.975007903888714e-05,
|
| 70 |
+
"loss": 0.8663,
|
| 71 |
+
"step": 7905
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 2.5,
|
| 75 |
+
"eval_loss": 0.7342700958251953,
|
| 76 |
+
"eval_runtime": 729.9421,
|
| 77 |
+
"eval_samples_per_second": 44.371,
|
| 78 |
+
"eval_steps_per_second": 1.388,
|
| 79 |
+
"step": 7905
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 3.0,
|
| 83 |
+
"learning_rate": 4.970009484666456e-05,
|
| 84 |
+
"loss": 0.7491,
|
| 85 |
+
"step": 9486
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 3.0,
|
| 89 |
+
"eval_loss": 0.652782678604126,
|
| 90 |
+
"eval_runtime": 730.2341,
|
| 91 |
+
"eval_samples_per_second": 44.353,
|
| 92 |
+
"eval_steps_per_second": 1.387,
|
| 93 |
+
"step": 9486
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.5,
|
| 97 |
+
"learning_rate": 4.965011065444199e-05,
|
| 98 |
+
"loss": 0.6797,
|
| 99 |
+
"step": 11067
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.5,
|
| 103 |
+
"eval_loss": 0.5981677174568176,
|
| 104 |
+
"eval_runtime": 731.2047,
|
| 105 |
+
"eval_samples_per_second": 44.294,
|
| 106 |
+
"eval_steps_per_second": 1.385,
|
| 107 |
+
"step": 11067
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 4.0,
|
| 111 |
+
"learning_rate": 4.960012646221941e-05,
|
| 112 |
+
"loss": 0.6299,
|
| 113 |
+
"step": 12648
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 4.0,
|
| 117 |
+
"eval_loss": 0.558130145072937,
|
| 118 |
+
"eval_runtime": 731.0787,
|
| 119 |
+
"eval_samples_per_second": 44.302,
|
| 120 |
+
"eval_steps_per_second": 1.386,
|
| 121 |
+
"step": 12648
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.5,
|
| 125 |
+
"learning_rate": 4.955014226999684e-05,
|
| 126 |
+
"loss": 0.592,
|
| 127 |
+
"step": 14229
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 4.5,
|
| 131 |
+
"eval_loss": 0.5258910655975342,
|
| 132 |
+
"eval_runtime": 731.2669,
|
| 133 |
+
"eval_samples_per_second": 44.29,
|
| 134 |
+
"eval_steps_per_second": 1.385,
|
| 135 |
+
"step": 14229
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 5.0,
|
| 139 |
+
"learning_rate": 4.950015807777427e-05,
|
| 140 |
+
"loss": 0.5608,
|
| 141 |
+
"step": 15810
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 5.0,
|
| 145 |
+
"eval_loss": 0.500377357006073,
|
| 146 |
+
"eval_runtime": 730.6976,
|
| 147 |
+
"eval_samples_per_second": 44.325,
|
| 148 |
+
"eval_steps_per_second": 1.386,
|
| 149 |
+
"step": 15810
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 5.5,
|
| 153 |
+
"learning_rate": 4.945017388555169e-05,
|
| 154 |
+
"loss": 0.5358,
|
| 155 |
+
"step": 17391
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 5.5,
|
| 159 |
+
"eval_loss": 0.4785815179347992,
|
| 160 |
+
"eval_runtime": 730.9055,
|
| 161 |
+
"eval_samples_per_second": 44.312,
|
| 162 |
+
"eval_steps_per_second": 1.386,
|
| 163 |
+
"step": 17391
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 6.0,
|
| 167 |
+
"learning_rate": 4.940018969332912e-05,
|
| 168 |
+
"loss": 0.5145,
|
| 169 |
+
"step": 18972
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 6.0,
|
| 173 |
+
"eval_loss": 0.4611227214336395,
|
| 174 |
+
"eval_runtime": 731.1857,
|
| 175 |
+
"eval_samples_per_second": 44.295,
|
| 176 |
+
"eval_steps_per_second": 1.385,
|
| 177 |
+
"step": 18972
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 6.5,
|
| 181 |
+
"learning_rate": 4.935020550110654e-05,
|
| 182 |
+
"loss": 0.496,
|
| 183 |
+
"step": 20553
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.5,
|
| 187 |
+
"eval_loss": 0.44416335225105286,
|
| 188 |
+
"eval_runtime": 731.3727,
|
| 189 |
+
"eval_samples_per_second": 44.284,
|
| 190 |
+
"eval_steps_per_second": 1.385,
|
| 191 |
+
"step": 20553
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 7.0,
|
| 195 |
+
"learning_rate": 4.930022130888398e-05,
|
| 196 |
+
"loss": 0.4802,
|
| 197 |
+
"step": 22134
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 7.0,
|
| 201 |
+
"eval_loss": 0.4299512505531311,
|
| 202 |
+
"eval_runtime": 731.2898,
|
| 203 |
+
"eval_samples_per_second": 44.289,
|
| 204 |
+
"eval_steps_per_second": 1.385,
|
| 205 |
+
"step": 22134
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 7.5,
|
| 209 |
+
"learning_rate": 4.92502371166614e-05,
|
| 210 |
+
"loss": 0.4651,
|
| 211 |
+
"step": 23715
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 7.5,
|
| 215 |
+
"eval_loss": 0.4183834195137024,
|
| 216 |
+
"eval_runtime": 731.1247,
|
| 217 |
+
"eval_samples_per_second": 44.299,
|
| 218 |
+
"eval_steps_per_second": 1.386,
|
| 219 |
+
"step": 23715
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 8.0,
|
| 223 |
+
"learning_rate": 4.920025292443883e-05,
|
| 224 |
+
"loss": 0.453,
|
| 225 |
+
"step": 25296
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 8.0,
|
| 229 |
+
"eval_loss": 0.40729984641075134,
|
| 230 |
+
"eval_runtime": 730.8948,
|
| 231 |
+
"eval_samples_per_second": 44.313,
|
| 232 |
+
"eval_steps_per_second": 1.386,
|
| 233 |
+
"step": 25296
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.5,
|
| 237 |
+
"learning_rate": 4.915026873221625e-05,
|
| 238 |
+
"loss": 0.4415,
|
| 239 |
+
"step": 26877
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 8.5,
|
| 243 |
+
"eval_loss": 0.39817574620246887,
|
| 244 |
+
"eval_runtime": 731.174,
|
| 245 |
+
"eval_samples_per_second": 44.296,
|
| 246 |
+
"eval_steps_per_second": 1.385,
|
| 247 |
+
"step": 26877
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 9.0,
|
| 251 |
+
"learning_rate": 4.910028453999368e-05,
|
| 252 |
+
"loss": 0.4306,
|
| 253 |
+
"step": 28458
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 9.0,
|
| 257 |
+
"eval_loss": 0.3896329998970032,
|
| 258 |
+
"eval_runtime": 730.8703,
|
| 259 |
+
"eval_samples_per_second": 44.314,
|
| 260 |
+
"eval_steps_per_second": 1.386,
|
| 261 |
+
"step": 28458
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 9.5,
|
| 265 |
+
"learning_rate": 4.905030034777111e-05,
|
| 266 |
+
"loss": 0.4209,
|
| 267 |
+
"step": 30039
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 9.5,
|
| 271 |
+
"eval_loss": 0.3798244297504425,
|
| 272 |
+
"eval_runtime": 731.1006,
|
| 273 |
+
"eval_samples_per_second": 44.3,
|
| 274 |
+
"eval_steps_per_second": 1.386,
|
| 275 |
+
"step": 30039
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 10.0,
|
| 279 |
+
"learning_rate": 4.900031615554853e-05,
|
| 280 |
+
"loss": 0.4129,
|
| 281 |
+
"step": 31620
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 10.0,
|
| 285 |
+
"eval_loss": 0.3725457489490509,
|
| 286 |
+
"eval_runtime": 731.3194,
|
| 287 |
+
"eval_samples_per_second": 44.287,
|
| 288 |
+
"eval_steps_per_second": 1.385,
|
| 289 |
+
"step": 31620
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 10.5,
|
| 293 |
+
"learning_rate": 4.895033196332596e-05,
|
| 294 |
+
"loss": 0.4043,
|
| 295 |
+
"step": 33201
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 10.5,
|
| 299 |
+
"eval_loss": 0.3666287660598755,
|
| 300 |
+
"eval_runtime": 730.8225,
|
| 301 |
+
"eval_samples_per_second": 44.317,
|
| 302 |
+
"eval_steps_per_second": 1.386,
|
| 303 |
+
"step": 33201
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 11.0,
|
| 307 |
+
"learning_rate": 4.890034777110338e-05,
|
| 308 |
+
"loss": 0.3972,
|
| 309 |
+
"step": 34782
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 11.0,
|
| 313 |
+
"eval_loss": 0.35826411843299866,
|
| 314 |
+
"eval_runtime": 731.1962,
|
| 315 |
+
"eval_samples_per_second": 44.295,
|
| 316 |
+
"eval_steps_per_second": 1.385,
|
| 317 |
+
"step": 34782
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 11.5,
|
| 321 |
+
"learning_rate": 4.885036357888081e-05,
|
| 322 |
+
"loss": 0.39,
|
| 323 |
+
"step": 36363
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 11.5,
|
| 327 |
+
"eval_loss": 0.3527071177959442,
|
| 328 |
+
"eval_runtime": 730.1333,
|
| 329 |
+
"eval_samples_per_second": 44.359,
|
| 330 |
+
"eval_steps_per_second": 1.387,
|
| 331 |
+
"step": 36363
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 12.0,
|
| 335 |
+
"learning_rate": 4.880037938665824e-05,
|
| 336 |
+
"loss": 0.3835,
|
| 337 |
+
"step": 37944
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 12.0,
|
| 341 |
+
"eval_loss": 0.3478526175022125,
|
| 342 |
+
"eval_runtime": 731.1852,
|
| 343 |
+
"eval_samples_per_second": 44.295,
|
| 344 |
+
"eval_steps_per_second": 1.385,
|
| 345 |
+
"step": 37944
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 12.5,
|
| 349 |
+
"learning_rate": 4.875039519443567e-05,
|
| 350 |
+
"loss": 0.3771,
|
| 351 |
+
"step": 39525
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 12.5,
|
| 355 |
+
"eval_loss": 0.341802179813385,
|
| 356 |
+
"eval_runtime": 730.7567,
|
| 357 |
+
"eval_samples_per_second": 44.321,
|
| 358 |
+
"eval_steps_per_second": 1.386,
|
| 359 |
+
"step": 39525
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 13.0,
|
| 363 |
+
"learning_rate": 4.870041100221309e-05,
|
| 364 |
+
"loss": 0.3717,
|
| 365 |
+
"step": 41106
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 13.0,
|
| 369 |
+
"eval_loss": 0.33608582615852356,
|
| 370 |
+
"eval_runtime": 731.8327,
|
| 371 |
+
"eval_samples_per_second": 44.256,
|
| 372 |
+
"eval_steps_per_second": 1.384,
|
| 373 |
+
"step": 41106
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 13.5,
|
| 377 |
+
"learning_rate": 4.865042680999052e-05,
|
| 378 |
+
"loss": 0.3658,
|
| 379 |
+
"step": 42687
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 13.5,
|
| 383 |
+
"eval_loss": 0.3327673375606537,
|
| 384 |
+
"eval_runtime": 730.5115,
|
| 385 |
+
"eval_samples_per_second": 44.336,
|
| 386 |
+
"eval_steps_per_second": 1.387,
|
| 387 |
+
"step": 42687
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 14.0,
|
| 391 |
+
"learning_rate": 4.860044261776795e-05,
|
| 392 |
+
"loss": 0.3611,
|
| 393 |
+
"step": 44268
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 14.0,
|
| 397 |
+
"eval_loss": 0.3284221887588501,
|
| 398 |
+
"eval_runtime": 730.7314,
|
| 399 |
+
"eval_samples_per_second": 44.323,
|
| 400 |
+
"eval_steps_per_second": 1.386,
|
| 401 |
+
"step": 44268
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 14.5,
|
| 405 |
+
"learning_rate": 4.855045842554537e-05,
|
| 406 |
+
"loss": 0.3561,
|
| 407 |
+
"step": 45849
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 14.5,
|
| 411 |
+
"eval_loss": 0.3230164051055908,
|
| 412 |
+
"eval_runtime": 731.0925,
|
| 413 |
+
"eval_samples_per_second": 44.301,
|
| 414 |
+
"eval_steps_per_second": 1.386,
|
| 415 |
+
"step": 45849
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 15.0,
|
| 419 |
+
"learning_rate": 4.85004742333228e-05,
|
| 420 |
+
"loss": 0.3512,
|
| 421 |
+
"step": 47430
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 15.0,
|
| 425 |
+
"eval_loss": 0.31766462326049805,
|
| 426 |
+
"eval_runtime": 730.5299,
|
| 427 |
+
"eval_samples_per_second": 44.335,
|
| 428 |
+
"eval_steps_per_second": 1.387,
|
| 429 |
+
"step": 47430
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 15.5,
|
| 433 |
+
"learning_rate": 4.845049004110022e-05,
|
| 434 |
+
"loss": 0.3464,
|
| 435 |
+
"step": 49011
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 15.5,
|
| 439 |
+
"eval_loss": 0.31685832142829895,
|
| 440 |
+
"eval_runtime": 730.0764,
|
| 441 |
+
"eval_samples_per_second": 44.362,
|
| 442 |
+
"eval_steps_per_second": 1.388,
|
| 443 |
+
"step": 49011
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 15.99,
|
| 447 |
+
"learning_rate": 4.840050584887765e-05,
|
| 448 |
+
"loss": 0.3426,
|
| 449 |
+
"step": 50592
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 15.99,
|
| 453 |
+
"eval_loss": 0.31031087040901184,
|
| 454 |
+
"eval_runtime": 729.7311,
|
| 455 |
+
"eval_samples_per_second": 44.383,
|
| 456 |
+
"eval_steps_per_second": 1.388,
|
| 457 |
+
"step": 50592
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 16.49,
|
| 461 |
+
"learning_rate": 4.835052165665508e-05,
|
| 462 |
+
"loss": 0.3385,
|
| 463 |
+
"step": 52173
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 16.49,
|
| 467 |
+
"eval_loss": 0.30902454257011414,
|
| 468 |
+
"eval_runtime": 730.6826,
|
| 469 |
+
"eval_samples_per_second": 44.326,
|
| 470 |
+
"eval_steps_per_second": 1.386,
|
| 471 |
+
"step": 52173
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 16.99,
|
| 475 |
+
"learning_rate": 4.8300537464432506e-05,
|
| 476 |
+
"loss": 0.3347,
|
| 477 |
+
"step": 53754
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 16.99,
|
| 481 |
+
"eval_loss": 0.30510178208351135,
|
| 482 |
+
"eval_runtime": 731.2599,
|
| 483 |
+
"eval_samples_per_second": 44.291,
|
| 484 |
+
"eval_steps_per_second": 1.385,
|
| 485 |
+
"step": 53754
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 17.49,
|
| 489 |
+
"learning_rate": 4.825055327220993e-05,
|
| 490 |
+
"loss": 0.3309,
|
| 491 |
+
"step": 55335
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 17.49,
|
| 495 |
+
"eval_loss": 0.301559180021286,
|
| 496 |
+
"eval_runtime": 730.9908,
|
| 497 |
+
"eval_samples_per_second": 44.307,
|
| 498 |
+
"eval_steps_per_second": 1.386,
|
| 499 |
+
"step": 55335
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 17.99,
|
| 503 |
+
"learning_rate": 4.8200569079987357e-05,
|
| 504 |
+
"loss": 0.3278,
|
| 505 |
+
"step": 56916
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 17.99,
|
| 509 |
+
"eval_loss": 0.29871445894241333,
|
| 510 |
+
"eval_runtime": 730.5796,
|
| 511 |
+
"eval_samples_per_second": 44.332,
|
| 512 |
+
"eval_steps_per_second": 1.387,
|
| 513 |
+
"step": 56916
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 18.49,
|
| 517 |
+
"learning_rate": 4.8150584887764785e-05,
|
| 518 |
+
"loss": 0.3241,
|
| 519 |
+
"step": 58497
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 18.49,
|
| 523 |
+
"eval_loss": 0.29653671383857727,
|
| 524 |
+
"eval_runtime": 730.4163,
|
| 525 |
+
"eval_samples_per_second": 44.342,
|
| 526 |
+
"eval_steps_per_second": 1.387,
|
| 527 |
+
"step": 58497
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 18.99,
|
| 531 |
+
"learning_rate": 4.810060069554221e-05,
|
| 532 |
+
"loss": 0.3213,
|
| 533 |
+
"step": 60078
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 18.99,
|
| 537 |
+
"eval_loss": 0.29158106446266174,
|
| 538 |
+
"eval_runtime": 731.4216,
|
| 539 |
+
"eval_samples_per_second": 44.281,
|
| 540 |
+
"eval_steps_per_second": 1.385,
|
| 541 |
+
"step": 60078
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 19.49,
|
| 545 |
+
"learning_rate": 4.8050616503319636e-05,
|
| 546 |
+
"loss": 0.3171,
|
| 547 |
+
"step": 61659
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 19.49,
|
| 551 |
+
"eval_loss": 0.2904985845088959,
|
| 552 |
+
"eval_runtime": 731.2299,
|
| 553 |
+
"eval_samples_per_second": 44.292,
|
| 554 |
+
"eval_steps_per_second": 1.385,
|
| 555 |
+
"step": 61659
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 19.99,
|
| 559 |
+
"learning_rate": 4.800063231109706e-05,
|
| 560 |
+
"loss": 0.3144,
|
| 561 |
+
"step": 63240
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 19.99,
|
| 565 |
+
"eval_loss": 0.28789228200912476,
|
| 566 |
+
"eval_runtime": 731.0148,
|
| 567 |
+
"eval_samples_per_second": 44.306,
|
| 568 |
+
"eval_steps_per_second": 1.386,
|
| 569 |
+
"step": 63240
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 20.49,
|
| 573 |
+
"learning_rate": 4.795064811887449e-05,
|
| 574 |
+
"loss": 0.3118,
|
| 575 |
+
"step": 64821
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 20.49,
|
| 579 |
+
"eval_loss": 0.2837814390659332,
|
| 580 |
+
"eval_runtime": 731.7352,
|
| 581 |
+
"eval_samples_per_second": 44.262,
|
| 582 |
+
"eval_steps_per_second": 1.384,
|
| 583 |
+
"step": 64821
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 20.99,
|
| 587 |
+
"learning_rate": 4.7900663926651916e-05,
|
| 588 |
+
"loss": 0.3095,
|
| 589 |
+
"step": 66402
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 20.99,
|
| 593 |
+
"eval_loss": 0.2827259302139282,
|
| 594 |
+
"eval_runtime": 731.0522,
|
| 595 |
+
"eval_samples_per_second": 44.303,
|
| 596 |
+
"eval_steps_per_second": 1.386,
|
| 597 |
+
"step": 66402
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 21.49,
|
| 601 |
+
"learning_rate": 4.7850679734429344e-05,
|
| 602 |
+
"loss": 0.306,
|
| 603 |
+
"step": 67983
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 21.49,
|
| 607 |
+
"eval_loss": 0.2803361415863037,
|
| 608 |
+
"eval_runtime": 730.6173,
|
| 609 |
+
"eval_samples_per_second": 44.33,
|
| 610 |
+
"eval_steps_per_second": 1.386,
|
| 611 |
+
"step": 67983
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 21.99,
|
| 615 |
+
"learning_rate": 4.7800695542206766e-05,
|
| 616 |
+
"loss": 0.3041,
|
| 617 |
+
"step": 69564
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 21.99,
|
| 621 |
+
"eval_loss": 0.27723076939582825,
|
| 622 |
+
"eval_runtime": 730.7403,
|
| 623 |
+
"eval_samples_per_second": 44.322,
|
| 624 |
+
"eval_steps_per_second": 1.386,
|
| 625 |
+
"step": 69564
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 22.49,
|
| 629 |
+
"learning_rate": 4.7750711349984195e-05,
|
| 630 |
+
"loss": 0.3008,
|
| 631 |
+
"step": 71145
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 22.49,
|
| 635 |
+
"eval_loss": 0.27573683857917786,
|
| 636 |
+
"eval_runtime": 731.0262,
|
| 637 |
+
"eval_samples_per_second": 44.305,
|
| 638 |
+
"eval_steps_per_second": 1.386,
|
| 639 |
+
"step": 71145
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 22.99,
|
| 643 |
+
"learning_rate": 4.7700727157761624e-05,
|
| 644 |
+
"loss": 0.2988,
|
| 645 |
+
"step": 72726
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 22.99,
|
| 649 |
+
"eval_loss": 0.27441859245300293,
|
| 650 |
+
"eval_runtime": 730.8932,
|
| 651 |
+
"eval_samples_per_second": 44.313,
|
| 652 |
+
"eval_steps_per_second": 1.386,
|
| 653 |
+
"step": 72726
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 23.49,
|
| 657 |
+
"learning_rate": 4.7650742965539046e-05,
|
| 658 |
+
"loss": 0.2962,
|
| 659 |
+
"step": 74307
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 23.49,
|
| 663 |
+
"eval_loss": 0.271846204996109,
|
| 664 |
+
"eval_runtime": 730.9499,
|
| 665 |
+
"eval_samples_per_second": 44.309,
|
| 666 |
+
"eval_steps_per_second": 1.386,
|
| 667 |
+
"step": 74307
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 23.99,
|
| 671 |
+
"learning_rate": 4.7600758773316475e-05,
|
| 672 |
+
"loss": 0.2942,
|
| 673 |
+
"step": 75888
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 23.99,
|
| 677 |
+
"eval_loss": 0.26958543062210083,
|
| 678 |
+
"eval_runtime": 730.8234,
|
| 679 |
+
"eval_samples_per_second": 44.317,
|
| 680 |
+
"eval_steps_per_second": 1.386,
|
| 681 |
+
"step": 75888
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 24.49,
|
| 685 |
+
"learning_rate": 4.75507745810939e-05,
|
| 686 |
+
"loss": 0.2917,
|
| 687 |
+
"step": 77469
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 24.49,
|
| 691 |
+
"eval_loss": 0.26596799492836,
|
| 692 |
+
"eval_runtime": 730.7217,
|
| 693 |
+
"eval_samples_per_second": 44.323,
|
| 694 |
+
"eval_steps_per_second": 1.386,
|
| 695 |
+
"step": 77469
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 24.99,
|
| 699 |
+
"learning_rate": 4.7500790388871325e-05,
|
| 700 |
+
"loss": 0.2896,
|
| 701 |
+
"step": 79050
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 24.99,
|
| 705 |
+
"eval_loss": 0.26481589674949646,
|
| 706 |
+
"eval_runtime": 731.0551,
|
| 707 |
+
"eval_samples_per_second": 44.303,
|
| 708 |
+
"eval_steps_per_second": 1.386,
|
| 709 |
+
"step": 79050
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 25.49,
|
| 713 |
+
"learning_rate": 4.7450806196648754e-05,
|
| 714 |
+
"loss": 0.2873,
|
| 715 |
+
"step": 80631
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 25.49,
|
| 719 |
+
"eval_loss": 0.26311883330345154,
|
| 720 |
+
"eval_runtime": 730.6956,
|
| 721 |
+
"eval_samples_per_second": 44.325,
|
| 722 |
+
"eval_steps_per_second": 1.386,
|
| 723 |
+
"step": 80631
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 25.99,
|
| 727 |
+
"learning_rate": 4.740082200442618e-05,
|
| 728 |
+
"loss": 0.2853,
|
| 729 |
+
"step": 82212
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 25.99,
|
| 733 |
+
"eval_loss": 0.26103758811950684,
|
| 734 |
+
"eval_runtime": 731.3509,
|
| 735 |
+
"eval_samples_per_second": 44.285,
|
| 736 |
+
"eval_steps_per_second": 1.385,
|
| 737 |
+
"step": 82212
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 26.49,
|
| 741 |
+
"learning_rate": 4.7350837812203605e-05,
|
| 742 |
+
"loss": 0.2834,
|
| 743 |
+
"step": 83793
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 26.49,
|
| 747 |
+
"eval_loss": 0.25927209854125977,
|
| 748 |
+
"eval_runtime": 731.6353,
|
| 749 |
+
"eval_samples_per_second": 44.268,
|
| 750 |
+
"eval_steps_per_second": 1.385,
|
| 751 |
+
"step": 83793
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 26.99,
|
| 755 |
+
"learning_rate": 4.7300853619981034e-05,
|
| 756 |
+
"loss": 0.282,
|
| 757 |
+
"step": 85374
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 26.99,
|
| 761 |
+
"eval_loss": 0.2577729821205139,
|
| 762 |
+
"eval_runtime": 730.4389,
|
| 763 |
+
"eval_samples_per_second": 44.34,
|
| 764 |
+
"eval_steps_per_second": 1.387,
|
| 765 |
+
"step": 85374
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 27.49,
|
| 769 |
+
"learning_rate": 4.725086942775846e-05,
|
| 770 |
+
"loss": 0.2788,
|
| 771 |
+
"step": 86955
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 27.49,
|
| 775 |
+
"eval_loss": 0.25541242957115173,
|
| 776 |
+
"eval_runtime": 730.4208,
|
| 777 |
+
"eval_samples_per_second": 44.342,
|
| 778 |
+
"eval_steps_per_second": 1.387,
|
| 779 |
+
"step": 86955
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 27.99,
|
| 783 |
+
"learning_rate": 4.7200885235535884e-05,
|
| 784 |
+
"loss": 0.2781,
|
| 785 |
+
"step": 88536
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 27.99,
|
| 789 |
+
"eval_loss": 0.2544184625148773,
|
| 790 |
+
"eval_runtime": 730.365,
|
| 791 |
+
"eval_samples_per_second": 44.345,
|
| 792 |
+
"eval_steps_per_second": 1.387,
|
| 793 |
+
"step": 88536
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 28.49,
|
| 797 |
+
"learning_rate": 4.715090104331331e-05,
|
| 798 |
+
"loss": 0.2755,
|
| 799 |
+
"step": 90117
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 28.49,
|
| 803 |
+
"eval_loss": 0.25301480293273926,
|
| 804 |
+
"eval_runtime": 730.3814,
|
| 805 |
+
"eval_samples_per_second": 44.344,
|
| 806 |
+
"eval_steps_per_second": 1.387,
|
| 807 |
+
"step": 90117
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 28.99,
|
| 811 |
+
"learning_rate": 4.7100916851090735e-05,
|
| 812 |
+
"loss": 0.2742,
|
| 813 |
+
"step": 91698
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 28.99,
|
| 817 |
+
"eval_loss": 0.24893982708454132,
|
| 818 |
+
"eval_runtime": 730.5139,
|
| 819 |
+
"eval_samples_per_second": 44.336,
|
| 820 |
+
"eval_steps_per_second": 1.387,
|
| 821 |
+
"step": 91698
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 29.49,
|
| 825 |
+
"learning_rate": 4.7050932658868164e-05,
|
| 826 |
+
"loss": 0.2723,
|
| 827 |
+
"step": 93279
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 29.49,
|
| 831 |
+
"eval_loss": 0.24909181892871857,
|
| 832 |
+
"eval_runtime": 729.9952,
|
| 833 |
+
"eval_samples_per_second": 44.367,
|
| 834 |
+
"eval_steps_per_second": 1.388,
|
| 835 |
+
"step": 93279
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 29.99,
|
| 839 |
+
"learning_rate": 4.700094846664559e-05,
|
| 840 |
+
"loss": 0.2709,
|
| 841 |
+
"step": 94860
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 29.99,
|
| 845 |
+
"eval_loss": 0.248749241232872,
|
| 846 |
+
"eval_runtime": 730.3489,
|
| 847 |
+
"eval_samples_per_second": 44.346,
|
| 848 |
+
"eval_steps_per_second": 1.387,
|
| 849 |
+
"step": 94860
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 30.49,
|
| 853 |
+
"learning_rate": 4.695096427442302e-05,
|
| 854 |
+
"loss": 0.2689,
|
| 855 |
+
"step": 96441
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 30.49,
|
| 859 |
+
"eval_loss": 0.24696363508701324,
|
| 860 |
+
"eval_runtime": 730.2536,
|
| 861 |
+
"eval_samples_per_second": 44.352,
|
| 862 |
+
"eval_steps_per_second": 1.387,
|
| 863 |
+
"step": 96441
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 30.99,
|
| 867 |
+
"learning_rate": 4.6900980082200443e-05,
|
| 868 |
+
"loss": 0.2671,
|
| 869 |
+
"step": 98022
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 30.99,
|
| 873 |
+
"eval_loss": 0.2443317025899887,
|
| 874 |
+
"eval_runtime": 730.6664,
|
| 875 |
+
"eval_samples_per_second": 44.327,
|
| 876 |
+
"eval_steps_per_second": 1.386,
|
| 877 |
+
"step": 98022
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 31.49,
|
| 881 |
+
"learning_rate": 4.685099588997787e-05,
|
| 882 |
+
"loss": 0.2659,
|
| 883 |
+
"step": 99603
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 31.49,
|
| 887 |
+
"eval_loss": 0.24296976625919342,
|
| 888 |
+
"eval_runtime": 730.1073,
|
| 889 |
+
"eval_samples_per_second": 44.361,
|
| 890 |
+
"eval_steps_per_second": 1.387,
|
| 891 |
+
"step": 99603
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 31.99,
|
| 895 |
+
"learning_rate": 4.68010116977553e-05,
|
| 896 |
+
"loss": 0.2641,
|
| 897 |
+
"step": 101184
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 31.99,
|
| 901 |
+
"eval_loss": 0.2419230043888092,
|
| 902 |
+
"eval_runtime": 730.5564,
|
| 903 |
+
"eval_samples_per_second": 44.333,
|
| 904 |
+
"eval_steps_per_second": 1.387,
|
| 905 |
+
"step": 101184
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 32.49,
|
| 909 |
+
"learning_rate": 4.675102750553272e-05,
|
| 910 |
+
"loss": 0.2624,
|
| 911 |
+
"step": 102765
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 32.49,
|
| 915 |
+
"eval_loss": 0.24093250930309296,
|
| 916 |
+
"eval_runtime": 729.8364,
|
| 917 |
+
"eval_samples_per_second": 44.377,
|
| 918 |
+
"eval_steps_per_second": 1.388,
|
| 919 |
+
"step": 102765
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 32.99,
|
| 923 |
+
"learning_rate": 4.670104331331015e-05,
|
| 924 |
+
"loss": 0.2616,
|
| 925 |
+
"step": 104346
|
| 926 |
+
},
|
| 927 |
+
{
|
| 928 |
+
"epoch": 32.99,
|
| 929 |
+
"eval_loss": 0.24029986560344696,
|
| 930 |
+
"eval_runtime": 729.4415,
|
| 931 |
+
"eval_samples_per_second": 44.401,
|
| 932 |
+
"eval_steps_per_second": 1.389,
|
| 933 |
+
"step": 104346
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 33.49,
|
| 937 |
+
"learning_rate": 4.6651059121087574e-05,
|
| 938 |
+
"loss": 0.2603,
|
| 939 |
+
"step": 105927
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 33.49,
|
| 943 |
+
"eval_loss": 0.23759804666042328,
|
| 944 |
+
"eval_runtime": 729.4526,
|
| 945 |
+
"eval_samples_per_second": 44.4,
|
| 946 |
+
"eval_steps_per_second": 1.389,
|
| 947 |
+
"step": 105927
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 33.99,
|
| 951 |
+
"learning_rate": 4.6601074928865e-05,
|
| 952 |
+
"loss": 0.2582,
|
| 953 |
+
"step": 107508
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 33.99,
|
| 957 |
+
"eval_loss": 0.23841261863708496,
|
| 958 |
+
"eval_runtime": 730.3906,
|
| 959 |
+
"eval_samples_per_second": 44.343,
|
| 960 |
+
"eval_steps_per_second": 1.387,
|
| 961 |
+
"step": 107508
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 34.49,
|
| 965 |
+
"learning_rate": 4.6551090736642425e-05,
|
| 966 |
+
"loss": 0.2568,
|
| 967 |
+
"step": 109089
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 34.49,
|
| 971 |
+
"eval_loss": 0.23516328632831573,
|
| 972 |
+
"eval_runtime": 730.065,
|
| 973 |
+
"eval_samples_per_second": 44.363,
|
| 974 |
+
"eval_steps_per_second": 1.388,
|
| 975 |
+
"step": 109089
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 34.99,
|
| 979 |
+
"learning_rate": 4.650110654441986e-05,
|
| 980 |
+
"loss": 0.2554,
|
| 981 |
+
"step": 110670
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 34.99,
|
| 985 |
+
"eval_loss": 0.2346547394990921,
|
| 986 |
+
"eval_runtime": 729.7863,
|
| 987 |
+
"eval_samples_per_second": 44.38,
|
| 988 |
+
"eval_steps_per_second": 1.388,
|
| 989 |
+
"step": 110670
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 35.49,
|
| 993 |
+
"learning_rate": 4.645112235219728e-05,
|
| 994 |
+
"loss": 0.2538,
|
| 995 |
+
"step": 112251
|
| 996 |
+
},
|
| 997 |
+
{
|
| 998 |
+
"epoch": 35.49,
|
| 999 |
+
"eval_loss": 0.23422306776046753,
|
| 1000 |
+
"eval_runtime": 729.5559,
|
| 1001 |
+
"eval_samples_per_second": 44.394,
|
| 1002 |
+
"eval_steps_per_second": 1.389,
|
| 1003 |
+
"step": 112251
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 35.99,
|
| 1007 |
+
"learning_rate": 4.640113815997471e-05,
|
| 1008 |
+
"loss": 0.253,
|
| 1009 |
+
"step": 113832
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 35.99,
|
| 1013 |
+
"eval_loss": 0.2336236983537674,
|
| 1014 |
+
"eval_runtime": 729.8583,
|
| 1015 |
+
"eval_samples_per_second": 44.376,
|
| 1016 |
+
"eval_steps_per_second": 1.388,
|
| 1017 |
+
"step": 113832
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 36.49,
|
| 1021 |
+
"learning_rate": 4.635115396775214e-05,
|
| 1022 |
+
"loss": 0.2517,
|
| 1023 |
+
"step": 115413
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 36.49,
|
| 1027 |
+
"eval_loss": 0.23158451914787292,
|
| 1028 |
+
"eval_runtime": 730.2735,
|
| 1029 |
+
"eval_samples_per_second": 44.351,
|
| 1030 |
+
"eval_steps_per_second": 1.387,
|
| 1031 |
+
"step": 115413
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 36.99,
|
| 1035 |
+
"learning_rate": 4.630116977552956e-05,
|
| 1036 |
+
"loss": 0.25,
|
| 1037 |
+
"step": 116994
|
| 1038 |
+
},
|
| 1039 |
+
{
|
| 1040 |
+
"epoch": 36.99,
|
| 1041 |
+
"eval_loss": 0.2291453778743744,
|
| 1042 |
+
"eval_runtime": 730.6072,
|
| 1043 |
+
"eval_samples_per_second": 44.33,
|
| 1044 |
+
"eval_steps_per_second": 1.387,
|
| 1045 |
+
"step": 116994
|
| 1046 |
+
}
|
| 1047 |
+
],
|
| 1048 |
+
"logging_steps": 1581,
|
| 1049 |
+
"max_steps": 1581500,
|
| 1050 |
+
"num_train_epochs": 500,
|
| 1051 |
+
"save_steps": 1581,
|
| 1052 |
+
"total_flos": 7.944349100547981e+18,
|
| 1053 |
+
"trial_name": null,
|
| 1054 |
+
"trial_params": null
|
| 1055 |
+
}
|
checkpoint-116994/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2621a21fd43f188955ba955f7f93eab840a7c1ee63d8e4944a528c04059638ce
|
| 3 |
+
size 4600
|