Training in progress, step 12000, 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 613004648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3b588761b50be65d8796badee7ef8b1410198e0580687e0e9b4fb211a20c99b
|
| 3 |
size 613004648
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1226096954
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a271571edbbdb0723201c1dcd4e66117d96525b325fc1fd6acf49af21cc25818
|
| 3 |
size 1226096954
|
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 sha256:7f92435eb6dc7f41ea95fa3d980a0666d4a13b153aeb2cd8cebe90dc94dc1f10
|
| 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 1000
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8db93a2f6abb2c48f8c464d140e6d8e94f07e6e65ef70a39fa77270a82587ab1
|
| 3 |
size 1000
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 5.
|
| 5 |
"eval_steps": 250,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -8411,6 +8411,770 @@
|
|
| 8411 |
"eval_spearman_manhattan": 0.7590724893258253,
|
| 8412 |
"eval_steps_per_second": 37.21,
|
| 8413 |
"step": 11000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8414 |
}
|
| 8415 |
],
|
| 8416 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.623242736644799,
|
| 5 |
"eval_steps": 250,
|
| 6 |
+
"global_step": 12000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 8411 |
"eval_spearman_manhattan": 0.7590724893258253,
|
| 8412 |
"eval_steps_per_second": 37.21,
|
| 8413 |
"step": 11000
|
| 8414 |
+
},
|
| 8415 |
+
{
|
| 8416 |
+
"epoch": 5.159325210871603,
|
| 8417 |
+
"grad_norm": 2.7338879108428955,
|
| 8418 |
+
"learning_rate": 9.35508434864105e-06,
|
| 8419 |
+
"loss": 0.1157,
|
| 8420 |
+
"step": 11010
|
| 8421 |
+
},
|
| 8422 |
+
{
|
| 8423 |
+
"epoch": 5.164011246485473,
|
| 8424 |
+
"grad_norm": 2.1284737586975098,
|
| 8425 |
+
"learning_rate": 9.354498594189316e-06,
|
| 8426 |
+
"loss": 0.1073,
|
| 8427 |
+
"step": 11020
|
| 8428 |
+
},
|
| 8429 |
+
{
|
| 8430 |
+
"epoch": 5.168697282099344,
|
| 8431 |
+
"grad_norm": 1.506453037261963,
|
| 8432 |
+
"learning_rate": 9.353912839737583e-06,
|
| 8433 |
+
"loss": 0.1119,
|
| 8434 |
+
"step": 11030
|
| 8435 |
+
},
|
| 8436 |
+
{
|
| 8437 |
+
"epoch": 5.173383317713214,
|
| 8438 |
+
"grad_norm": 2.2100448608398438,
|
| 8439 |
+
"learning_rate": 9.35332708528585e-06,
|
| 8440 |
+
"loss": 0.1091,
|
| 8441 |
+
"step": 11040
|
| 8442 |
+
},
|
| 8443 |
+
{
|
| 8444 |
+
"epoch": 5.178069353327086,
|
| 8445 |
+
"grad_norm": 2.5225071907043457,
|
| 8446 |
+
"learning_rate": 9.352741330834115e-06,
|
| 8447 |
+
"loss": 0.1089,
|
| 8448 |
+
"step": 11050
|
| 8449 |
+
},
|
| 8450 |
+
{
|
| 8451 |
+
"epoch": 5.182755388940956,
|
| 8452 |
+
"grad_norm": 2.282289981842041,
|
| 8453 |
+
"learning_rate": 9.352155576382382e-06,
|
| 8454 |
+
"loss": 0.1165,
|
| 8455 |
+
"step": 11060
|
| 8456 |
+
},
|
| 8457 |
+
{
|
| 8458 |
+
"epoch": 5.187441424554827,
|
| 8459 |
+
"grad_norm": 2.467607259750366,
|
| 8460 |
+
"learning_rate": 9.351569821930647e-06,
|
| 8461 |
+
"loss": 0.1104,
|
| 8462 |
+
"step": 11070
|
| 8463 |
+
},
|
| 8464 |
+
{
|
| 8465 |
+
"epoch": 5.192127460168697,
|
| 8466 |
+
"grad_norm": 2.524582624435425,
|
| 8467 |
+
"learning_rate": 9.350984067478914e-06,
|
| 8468 |
+
"loss": 0.1316,
|
| 8469 |
+
"step": 11080
|
| 8470 |
+
},
|
| 8471 |
+
{
|
| 8472 |
+
"epoch": 5.196813495782568,
|
| 8473 |
+
"grad_norm": 2.6294236183166504,
|
| 8474 |
+
"learning_rate": 9.350398313027181e-06,
|
| 8475 |
+
"loss": 0.1068,
|
| 8476 |
+
"step": 11090
|
| 8477 |
+
},
|
| 8478 |
+
{
|
| 8479 |
+
"epoch": 5.201499531396439,
|
| 8480 |
+
"grad_norm": 2.033003091812134,
|
| 8481 |
+
"learning_rate": 9.349812558575446e-06,
|
| 8482 |
+
"loss": 0.1025,
|
| 8483 |
+
"step": 11100
|
| 8484 |
+
},
|
| 8485 |
+
{
|
| 8486 |
+
"epoch": 5.206185567010309,
|
| 8487 |
+
"grad_norm": 1.909003734588623,
|
| 8488 |
+
"learning_rate": 9.349226804123713e-06,
|
| 8489 |
+
"loss": 0.0948,
|
| 8490 |
+
"step": 11110
|
| 8491 |
+
},
|
| 8492 |
+
{
|
| 8493 |
+
"epoch": 5.21087160262418,
|
| 8494 |
+
"grad_norm": 2.284494400024414,
|
| 8495 |
+
"learning_rate": 9.348641049671978e-06,
|
| 8496 |
+
"loss": 0.1456,
|
| 8497 |
+
"step": 11120
|
| 8498 |
+
},
|
| 8499 |
+
{
|
| 8500 |
+
"epoch": 5.21555763823805,
|
| 8501 |
+
"grad_norm": 2.152364492416382,
|
| 8502 |
+
"learning_rate": 9.348055295220243e-06,
|
| 8503 |
+
"loss": 0.1067,
|
| 8504 |
+
"step": 11130
|
| 8505 |
+
},
|
| 8506 |
+
{
|
| 8507 |
+
"epoch": 5.220243673851921,
|
| 8508 |
+
"grad_norm": 1.9327460527420044,
|
| 8509 |
+
"learning_rate": 9.34746954076851e-06,
|
| 8510 |
+
"loss": 0.1041,
|
| 8511 |
+
"step": 11140
|
| 8512 |
+
},
|
| 8513 |
+
{
|
| 8514 |
+
"epoch": 5.224929709465792,
|
| 8515 |
+
"grad_norm": 1.4854366779327393,
|
| 8516 |
+
"learning_rate": 9.346883786316777e-06,
|
| 8517 |
+
"loss": 0.1014,
|
| 8518 |
+
"step": 11150
|
| 8519 |
+
},
|
| 8520 |
+
{
|
| 8521 |
+
"epoch": 5.229615745079663,
|
| 8522 |
+
"grad_norm": 2.438124418258667,
|
| 8523 |
+
"learning_rate": 9.346298031865043e-06,
|
| 8524 |
+
"loss": 0.1009,
|
| 8525 |
+
"step": 11160
|
| 8526 |
+
},
|
| 8527 |
+
{
|
| 8528 |
+
"epoch": 5.234301780693533,
|
| 8529 |
+
"grad_norm": 2.2534475326538086,
|
| 8530 |
+
"learning_rate": 9.34571227741331e-06,
|
| 8531 |
+
"loss": 0.1204,
|
| 8532 |
+
"step": 11170
|
| 8533 |
+
},
|
| 8534 |
+
{
|
| 8535 |
+
"epoch": 5.238987816307404,
|
| 8536 |
+
"grad_norm": 1.7294119596481323,
|
| 8537 |
+
"learning_rate": 9.345126522961575e-06,
|
| 8538 |
+
"loss": 0.1156,
|
| 8539 |
+
"step": 11180
|
| 8540 |
+
},
|
| 8541 |
+
{
|
| 8542 |
+
"epoch": 5.243673851921274,
|
| 8543 |
+
"grad_norm": 2.046323299407959,
|
| 8544 |
+
"learning_rate": 9.344540768509842e-06,
|
| 8545 |
+
"loss": 0.1052,
|
| 8546 |
+
"step": 11190
|
| 8547 |
+
},
|
| 8548 |
+
{
|
| 8549 |
+
"epoch": 5.248359887535146,
|
| 8550 |
+
"grad_norm": 1.4913642406463623,
|
| 8551 |
+
"learning_rate": 9.343955014058108e-06,
|
| 8552 |
+
"loss": 0.1108,
|
| 8553 |
+
"step": 11200
|
| 8554 |
+
},
|
| 8555 |
+
{
|
| 8556 |
+
"epoch": 5.253045923149016,
|
| 8557 |
+
"grad_norm": 2.705307722091675,
|
| 8558 |
+
"learning_rate": 9.343369259606374e-06,
|
| 8559 |
+
"loss": 0.1196,
|
| 8560 |
+
"step": 11210
|
| 8561 |
+
},
|
| 8562 |
+
{
|
| 8563 |
+
"epoch": 5.257731958762887,
|
| 8564 |
+
"grad_norm": 2.288198709487915,
|
| 8565 |
+
"learning_rate": 9.34278350515464e-06,
|
| 8566 |
+
"loss": 0.1111,
|
| 8567 |
+
"step": 11220
|
| 8568 |
+
},
|
| 8569 |
+
{
|
| 8570 |
+
"epoch": 5.262417994376757,
|
| 8571 |
+
"grad_norm": 1.7562745809555054,
|
| 8572 |
+
"learning_rate": 9.342197750702906e-06,
|
| 8573 |
+
"loss": 0.1091,
|
| 8574 |
+
"step": 11230
|
| 8575 |
+
},
|
| 8576 |
+
{
|
| 8577 |
+
"epoch": 5.2671040299906275,
|
| 8578 |
+
"grad_norm": 1.7820425033569336,
|
| 8579 |
+
"learning_rate": 9.341611996251173e-06,
|
| 8580 |
+
"loss": 0.1274,
|
| 8581 |
+
"step": 11240
|
| 8582 |
+
},
|
| 8583 |
+
{
|
| 8584 |
+
"epoch": 5.271790065604499,
|
| 8585 |
+
"grad_norm": 1.3509507179260254,
|
| 8586 |
+
"learning_rate": 9.341026241799438e-06,
|
| 8587 |
+
"loss": 0.1082,
|
| 8588 |
+
"step": 11250
|
| 8589 |
+
},
|
| 8590 |
+
{
|
| 8591 |
+
"epoch": 5.271790065604499,
|
| 8592 |
+
"eval_loss": 0.04377983510494232,
|
| 8593 |
+
"eval_pearson_cosine": 0.777409933262625,
|
| 8594 |
+
"eval_pearson_dot": 0.6039188474436514,
|
| 8595 |
+
"eval_pearson_euclidean": 0.7432758495109439,
|
| 8596 |
+
"eval_pearson_manhattan": 0.742989414571646,
|
| 8597 |
+
"eval_runtime": 40.4868,
|
| 8598 |
+
"eval_samples_per_second": 37.049,
|
| 8599 |
+
"eval_spearman_cosine": 0.7818314076527526,
|
| 8600 |
+
"eval_spearman_dot": 0.6129138744459114,
|
| 8601 |
+
"eval_spearman_euclidean": 0.7593037528355521,
|
| 8602 |
+
"eval_spearman_manhattan": 0.7591440996970567,
|
| 8603 |
+
"eval_steps_per_second": 37.049,
|
| 8604 |
+
"step": 11250
|
| 8605 |
+
},
|
| 8606 |
+
{
|
| 8607 |
+
"epoch": 5.276476101218369,
|
| 8608 |
+
"grad_norm": 1.9400215148925781,
|
| 8609 |
+
"learning_rate": 9.340440487347705e-06,
|
| 8610 |
+
"loss": 0.1033,
|
| 8611 |
+
"step": 11260
|
| 8612 |
+
},
|
| 8613 |
+
{
|
| 8614 |
+
"epoch": 5.28116213683224,
|
| 8615 |
+
"grad_norm": 2.5327563285827637,
|
| 8616 |
+
"learning_rate": 9.339854732895972e-06,
|
| 8617 |
+
"loss": 0.1006,
|
| 8618 |
+
"step": 11270
|
| 8619 |
+
},
|
| 8620 |
+
{
|
| 8621 |
+
"epoch": 5.28584817244611,
|
| 8622 |
+
"grad_norm": 2.5133285522460938,
|
| 8623 |
+
"learning_rate": 9.339268978444237e-06,
|
| 8624 |
+
"loss": 0.1092,
|
| 8625 |
+
"step": 11280
|
| 8626 |
+
},
|
| 8627 |
+
{
|
| 8628 |
+
"epoch": 5.290534208059981,
|
| 8629 |
+
"grad_norm": 2.192230224609375,
|
| 8630 |
+
"learning_rate": 9.338683223992502e-06,
|
| 8631 |
+
"loss": 0.0995,
|
| 8632 |
+
"step": 11290
|
| 8633 |
+
},
|
| 8634 |
+
{
|
| 8635 |
+
"epoch": 5.295220243673852,
|
| 8636 |
+
"grad_norm": 2.7413835525512695,
|
| 8637 |
+
"learning_rate": 9.33809746954077e-06,
|
| 8638 |
+
"loss": 0.1253,
|
| 8639 |
+
"step": 11300
|
| 8640 |
+
},
|
| 8641 |
+
{
|
| 8642 |
+
"epoch": 5.299906279287723,
|
| 8643 |
+
"grad_norm": 2.4897637367248535,
|
| 8644 |
+
"learning_rate": 9.337511715089036e-06,
|
| 8645 |
+
"loss": 0.1231,
|
| 8646 |
+
"step": 11310
|
| 8647 |
+
},
|
| 8648 |
+
{
|
| 8649 |
+
"epoch": 5.304592314901593,
|
| 8650 |
+
"grad_norm": 2.837437629699707,
|
| 8651 |
+
"learning_rate": 9.336925960637301e-06,
|
| 8652 |
+
"loss": 0.1061,
|
| 8653 |
+
"step": 11320
|
| 8654 |
+
},
|
| 8655 |
+
{
|
| 8656 |
+
"epoch": 5.309278350515464,
|
| 8657 |
+
"grad_norm": 2.932845115661621,
|
| 8658 |
+
"learning_rate": 9.336340206185568e-06,
|
| 8659 |
+
"loss": 0.1128,
|
| 8660 |
+
"step": 11330
|
| 8661 |
+
},
|
| 8662 |
+
{
|
| 8663 |
+
"epoch": 5.313964386129334,
|
| 8664 |
+
"grad_norm": 2.7689220905303955,
|
| 8665 |
+
"learning_rate": 9.335754451733833e-06,
|
| 8666 |
+
"loss": 0.106,
|
| 8667 |
+
"step": 11340
|
| 8668 |
+
},
|
| 8669 |
+
{
|
| 8670 |
+
"epoch": 5.318650421743206,
|
| 8671 |
+
"grad_norm": 2.0174484252929688,
|
| 8672 |
+
"learning_rate": 9.3351686972821e-06,
|
| 8673 |
+
"loss": 0.1068,
|
| 8674 |
+
"step": 11350
|
| 8675 |
+
},
|
| 8676 |
+
{
|
| 8677 |
+
"epoch": 5.323336457357076,
|
| 8678 |
+
"grad_norm": 1.9986820220947266,
|
| 8679 |
+
"learning_rate": 9.334582942830366e-06,
|
| 8680 |
+
"loss": 0.1138,
|
| 8681 |
+
"step": 11360
|
| 8682 |
+
},
|
| 8683 |
+
{
|
| 8684 |
+
"epoch": 5.3280224929709465,
|
| 8685 |
+
"grad_norm": 2.263935089111328,
|
| 8686 |
+
"learning_rate": 9.333997188378632e-06,
|
| 8687 |
+
"loss": 0.1215,
|
| 8688 |
+
"step": 11370
|
| 8689 |
+
},
|
| 8690 |
+
{
|
| 8691 |
+
"epoch": 5.332708528584817,
|
| 8692 |
+
"grad_norm": 2.540949821472168,
|
| 8693 |
+
"learning_rate": 9.3334114339269e-06,
|
| 8694 |
+
"loss": 0.1139,
|
| 8695 |
+
"step": 11380
|
| 8696 |
+
},
|
| 8697 |
+
{
|
| 8698 |
+
"epoch": 5.3373945641986875,
|
| 8699 |
+
"grad_norm": 2.293947219848633,
|
| 8700 |
+
"learning_rate": 9.332825679475165e-06,
|
| 8701 |
+
"loss": 0.1113,
|
| 8702 |
+
"step": 11390
|
| 8703 |
+
},
|
| 8704 |
+
{
|
| 8705 |
+
"epoch": 5.342080599812559,
|
| 8706 |
+
"grad_norm": 1.2586168050765991,
|
| 8707 |
+
"learning_rate": 9.332239925023432e-06,
|
| 8708 |
+
"loss": 0.1072,
|
| 8709 |
+
"step": 11400
|
| 8710 |
+
},
|
| 8711 |
+
{
|
| 8712 |
+
"epoch": 5.346766635426429,
|
| 8713 |
+
"grad_norm": 2.605865955352783,
|
| 8714 |
+
"learning_rate": 9.331654170571697e-06,
|
| 8715 |
+
"loss": 0.1032,
|
| 8716 |
+
"step": 11410
|
| 8717 |
+
},
|
| 8718 |
+
{
|
| 8719 |
+
"epoch": 5.3514526710403,
|
| 8720 |
+
"grad_norm": 2.003467321395874,
|
| 8721 |
+
"learning_rate": 9.331068416119962e-06,
|
| 8722 |
+
"loss": 0.1107,
|
| 8723 |
+
"step": 11420
|
| 8724 |
+
},
|
| 8725 |
+
{
|
| 8726 |
+
"epoch": 5.35613870665417,
|
| 8727 |
+
"grad_norm": 2.439173460006714,
|
| 8728 |
+
"learning_rate": 9.33048266166823e-06,
|
| 8729 |
+
"loss": 0.1055,
|
| 8730 |
+
"step": 11430
|
| 8731 |
+
},
|
| 8732 |
+
{
|
| 8733 |
+
"epoch": 5.360824742268041,
|
| 8734 |
+
"grad_norm": 2.154588460922241,
|
| 8735 |
+
"learning_rate": 9.329896907216496e-06,
|
| 8736 |
+
"loss": 0.1008,
|
| 8737 |
+
"step": 11440
|
| 8738 |
+
},
|
| 8739 |
+
{
|
| 8740 |
+
"epoch": 5.365510777881912,
|
| 8741 |
+
"grad_norm": 2.530766725540161,
|
| 8742 |
+
"learning_rate": 9.329311152764761e-06,
|
| 8743 |
+
"loss": 0.1062,
|
| 8744 |
+
"step": 11450
|
| 8745 |
+
},
|
| 8746 |
+
{
|
| 8747 |
+
"epoch": 5.370196813495783,
|
| 8748 |
+
"grad_norm": 1.994178056716919,
|
| 8749 |
+
"learning_rate": 9.328725398313028e-06,
|
| 8750 |
+
"loss": 0.1472,
|
| 8751 |
+
"step": 11460
|
| 8752 |
+
},
|
| 8753 |
+
{
|
| 8754 |
+
"epoch": 5.374882849109653,
|
| 8755 |
+
"grad_norm": 2.8370258808135986,
|
| 8756 |
+
"learning_rate": 9.328139643861293e-06,
|
| 8757 |
+
"loss": 0.1098,
|
| 8758 |
+
"step": 11470
|
| 8759 |
+
},
|
| 8760 |
+
{
|
| 8761 |
+
"epoch": 5.379568884723524,
|
| 8762 |
+
"grad_norm": 1.487667441368103,
|
| 8763 |
+
"learning_rate": 9.32755388940956e-06,
|
| 8764 |
+
"loss": 0.1124,
|
| 8765 |
+
"step": 11480
|
| 8766 |
+
},
|
| 8767 |
+
{
|
| 8768 |
+
"epoch": 5.384254920337394,
|
| 8769 |
+
"grad_norm": 2.180283308029175,
|
| 8770 |
+
"learning_rate": 9.326968134957827e-06,
|
| 8771 |
+
"loss": 0.1181,
|
| 8772 |
+
"step": 11490
|
| 8773 |
+
},
|
| 8774 |
+
{
|
| 8775 |
+
"epoch": 5.3889409559512655,
|
| 8776 |
+
"grad_norm": 2.2690398693084717,
|
| 8777 |
+
"learning_rate": 9.326382380506092e-06,
|
| 8778 |
+
"loss": 0.1138,
|
| 8779 |
+
"step": 11500
|
| 8780 |
+
},
|
| 8781 |
+
{
|
| 8782 |
+
"epoch": 5.3889409559512655,
|
| 8783 |
+
"eval_loss": 0.04145639017224312,
|
| 8784 |
+
"eval_pearson_cosine": 0.782895609059949,
|
| 8785 |
+
"eval_pearson_dot": 0.63470693002958,
|
| 8786 |
+
"eval_pearson_euclidean": 0.740956945446257,
|
| 8787 |
+
"eval_pearson_manhattan": 0.740521959356709,
|
| 8788 |
+
"eval_runtime": 40.2743,
|
| 8789 |
+
"eval_samples_per_second": 37.245,
|
| 8790 |
+
"eval_spearman_cosine": 0.7869693899558259,
|
| 8791 |
+
"eval_spearman_dot": 0.6463692784357133,
|
| 8792 |
+
"eval_spearman_euclidean": 0.7560888074878002,
|
| 8793 |
+
"eval_spearman_manhattan": 0.7559675920990712,
|
| 8794 |
+
"eval_steps_per_second": 37.245,
|
| 8795 |
+
"step": 11500
|
| 8796 |
+
},
|
| 8797 |
+
{
|
| 8798 |
+
"epoch": 5.393626991565136,
|
| 8799 |
+
"grad_norm": 1.9818650484085083,
|
| 8800 |
+
"learning_rate": 9.32579662605436e-06,
|
| 8801 |
+
"loss": 0.1057,
|
| 8802 |
+
"step": 11510
|
| 8803 |
+
},
|
| 8804 |
+
{
|
| 8805 |
+
"epoch": 5.3983130271790065,
|
| 8806 |
+
"grad_norm": 2.286259651184082,
|
| 8807 |
+
"learning_rate": 9.325210871602624e-06,
|
| 8808 |
+
"loss": 0.1091,
|
| 8809 |
+
"step": 11520
|
| 8810 |
+
},
|
| 8811 |
+
{
|
| 8812 |
+
"epoch": 5.402999062792877,
|
| 8813 |
+
"grad_norm": 1.2215278148651123,
|
| 8814 |
+
"learning_rate": 9.324625117150891e-06,
|
| 8815 |
+
"loss": 0.0859,
|
| 8816 |
+
"step": 11530
|
| 8817 |
+
},
|
| 8818 |
+
{
|
| 8819 |
+
"epoch": 5.4076850984067475,
|
| 8820 |
+
"grad_norm": 2.2619011402130127,
|
| 8821 |
+
"learning_rate": 9.324039362699158e-06,
|
| 8822 |
+
"loss": 0.1281,
|
| 8823 |
+
"step": 11540
|
| 8824 |
+
},
|
| 8825 |
+
{
|
| 8826 |
+
"epoch": 5.412371134020619,
|
| 8827 |
+
"grad_norm": 1.313723087310791,
|
| 8828 |
+
"learning_rate": 9.323453608247423e-06,
|
| 8829 |
+
"loss": 0.0844,
|
| 8830 |
+
"step": 11550
|
| 8831 |
+
},
|
| 8832 |
+
{
|
| 8833 |
+
"epoch": 5.417057169634489,
|
| 8834 |
+
"grad_norm": 1.5897408723831177,
|
| 8835 |
+
"learning_rate": 9.32286785379569e-06,
|
| 8836 |
+
"loss": 0.1006,
|
| 8837 |
+
"step": 11560
|
| 8838 |
+
},
|
| 8839 |
+
{
|
| 8840 |
+
"epoch": 5.42174320524836,
|
| 8841 |
+
"grad_norm": 2.7910852432250977,
|
| 8842 |
+
"learning_rate": 9.322282099343956e-06,
|
| 8843 |
+
"loss": 0.1199,
|
| 8844 |
+
"step": 11570
|
| 8845 |
+
},
|
| 8846 |
+
{
|
| 8847 |
+
"epoch": 5.42642924086223,
|
| 8848 |
+
"grad_norm": 1.7807790040969849,
|
| 8849 |
+
"learning_rate": 9.32169634489222e-06,
|
| 8850 |
+
"loss": 0.1063,
|
| 8851 |
+
"step": 11580
|
| 8852 |
+
},
|
| 8853 |
+
{
|
| 8854 |
+
"epoch": 5.431115276476101,
|
| 8855 |
+
"grad_norm": 2.412628650665283,
|
| 8856 |
+
"learning_rate": 9.32111059044049e-06,
|
| 8857 |
+
"loss": 0.103,
|
| 8858 |
+
"step": 11590
|
| 8859 |
+
},
|
| 8860 |
+
{
|
| 8861 |
+
"epoch": 5.435801312089972,
|
| 8862 |
+
"grad_norm": 1.029317855834961,
|
| 8863 |
+
"learning_rate": 9.320524835988755e-06,
|
| 8864 |
+
"loss": 0.1025,
|
| 8865 |
+
"step": 11600
|
| 8866 |
+
},
|
| 8867 |
+
{
|
| 8868 |
+
"epoch": 5.440487347703843,
|
| 8869 |
+
"grad_norm": 2.206700563430786,
|
| 8870 |
+
"learning_rate": 9.31993908153702e-06,
|
| 8871 |
+
"loss": 0.114,
|
| 8872 |
+
"step": 11610
|
| 8873 |
+
},
|
| 8874 |
+
{
|
| 8875 |
+
"epoch": 5.445173383317713,
|
| 8876 |
+
"grad_norm": 1.643839716911316,
|
| 8877 |
+
"learning_rate": 9.319353327085287e-06,
|
| 8878 |
+
"loss": 0.1155,
|
| 8879 |
+
"step": 11620
|
| 8880 |
+
},
|
| 8881 |
+
{
|
| 8882 |
+
"epoch": 5.449859418931584,
|
| 8883 |
+
"grad_norm": 2.211933135986328,
|
| 8884 |
+
"learning_rate": 9.318767572633552e-06,
|
| 8885 |
+
"loss": 0.1096,
|
| 8886 |
+
"step": 11630
|
| 8887 |
+
},
|
| 8888 |
+
{
|
| 8889 |
+
"epoch": 5.454545454545454,
|
| 8890 |
+
"grad_norm": 2.2456345558166504,
|
| 8891 |
+
"learning_rate": 9.318181818181819e-06,
|
| 8892 |
+
"loss": 0.1153,
|
| 8893 |
+
"step": 11640
|
| 8894 |
+
},
|
| 8895 |
+
{
|
| 8896 |
+
"epoch": 5.4592314901593255,
|
| 8897 |
+
"grad_norm": 2.144434928894043,
|
| 8898 |
+
"learning_rate": 9.317596063730086e-06,
|
| 8899 |
+
"loss": 0.1245,
|
| 8900 |
+
"step": 11650
|
| 8901 |
+
},
|
| 8902 |
+
{
|
| 8903 |
+
"epoch": 5.463917525773196,
|
| 8904 |
+
"grad_norm": 1.8856313228607178,
|
| 8905 |
+
"learning_rate": 9.317010309278351e-06,
|
| 8906 |
+
"loss": 0.1139,
|
| 8907 |
+
"step": 11660
|
| 8908 |
+
},
|
| 8909 |
+
{
|
| 8910 |
+
"epoch": 5.4686035613870665,
|
| 8911 |
+
"grad_norm": 2.399268627166748,
|
| 8912 |
+
"learning_rate": 9.316424554826618e-06,
|
| 8913 |
+
"loss": 0.1189,
|
| 8914 |
+
"step": 11670
|
| 8915 |
+
},
|
| 8916 |
+
{
|
| 8917 |
+
"epoch": 5.473289597000937,
|
| 8918 |
+
"grad_norm": 2.7165584564208984,
|
| 8919 |
+
"learning_rate": 9.315838800374883e-06,
|
| 8920 |
+
"loss": 0.1016,
|
| 8921 |
+
"step": 11680
|
| 8922 |
+
},
|
| 8923 |
+
{
|
| 8924 |
+
"epoch": 5.4779756326148075,
|
| 8925 |
+
"grad_norm": 2.1864237785339355,
|
| 8926 |
+
"learning_rate": 9.31525304592315e-06,
|
| 8927 |
+
"loss": 0.1164,
|
| 8928 |
+
"step": 11690
|
| 8929 |
+
},
|
| 8930 |
+
{
|
| 8931 |
+
"epoch": 5.482661668228679,
|
| 8932 |
+
"grad_norm": 1.5643881559371948,
|
| 8933 |
+
"learning_rate": 9.314667291471417e-06,
|
| 8934 |
+
"loss": 0.1069,
|
| 8935 |
+
"step": 11700
|
| 8936 |
+
},
|
| 8937 |
+
{
|
| 8938 |
+
"epoch": 5.487347703842549,
|
| 8939 |
+
"grad_norm": 2.7151424884796143,
|
| 8940 |
+
"learning_rate": 9.314081537019682e-06,
|
| 8941 |
+
"loss": 0.1268,
|
| 8942 |
+
"step": 11710
|
| 8943 |
+
},
|
| 8944 |
+
{
|
| 8945 |
+
"epoch": 5.49203373945642,
|
| 8946 |
+
"grad_norm": 2.5677719116210938,
|
| 8947 |
+
"learning_rate": 9.31349578256795e-06,
|
| 8948 |
+
"loss": 0.0967,
|
| 8949 |
+
"step": 11720
|
| 8950 |
+
},
|
| 8951 |
+
{
|
| 8952 |
+
"epoch": 5.49671977507029,
|
| 8953 |
+
"grad_norm": 1.8421558141708374,
|
| 8954 |
+
"learning_rate": 9.312910028116214e-06,
|
| 8955 |
+
"loss": 0.111,
|
| 8956 |
+
"step": 11730
|
| 8957 |
+
},
|
| 8958 |
+
{
|
| 8959 |
+
"epoch": 5.501405810684162,
|
| 8960 |
+
"grad_norm": 2.0751326084136963,
|
| 8961 |
+
"learning_rate": 9.31232427366448e-06,
|
| 8962 |
+
"loss": 0.12,
|
| 8963 |
+
"step": 11740
|
| 8964 |
+
},
|
| 8965 |
+
{
|
| 8966 |
+
"epoch": 5.506091846298032,
|
| 8967 |
+
"grad_norm": 2.1153831481933594,
|
| 8968 |
+
"learning_rate": 9.311738519212747e-06,
|
| 8969 |
+
"loss": 0.1015,
|
| 8970 |
+
"step": 11750
|
| 8971 |
+
},
|
| 8972 |
+
{
|
| 8973 |
+
"epoch": 5.506091846298032,
|
| 8974 |
+
"eval_loss": 0.041955165565013885,
|
| 8975 |
+
"eval_pearson_cosine": 0.777849777417785,
|
| 8976 |
+
"eval_pearson_dot": 0.6249138636860323,
|
| 8977 |
+
"eval_pearson_euclidean": 0.7435429429906506,
|
| 8978 |
+
"eval_pearson_manhattan": 0.7436891262385359,
|
| 8979 |
+
"eval_runtime": 40.2707,
|
| 8980 |
+
"eval_samples_per_second": 37.248,
|
| 8981 |
+
"eval_spearman_cosine": 0.7810709480369951,
|
| 8982 |
+
"eval_spearman_dot": 0.6369677452237958,
|
| 8983 |
+
"eval_spearman_euclidean": 0.7589293041705764,
|
| 8984 |
+
"eval_spearman_manhattan": 0.7592155214560544,
|
| 8985 |
+
"eval_steps_per_second": 37.248,
|
| 8986 |
+
"step": 11750
|
| 8987 |
+
},
|
| 8988 |
+
{
|
| 8989 |
+
"epoch": 5.510777881911903,
|
| 8990 |
+
"grad_norm": 2.5980823040008545,
|
| 8991 |
+
"learning_rate": 9.311152764761013e-06,
|
| 8992 |
+
"loss": 0.097,
|
| 8993 |
+
"step": 11760
|
| 8994 |
+
},
|
| 8995 |
+
{
|
| 8996 |
+
"epoch": 5.515463917525773,
|
| 8997 |
+
"grad_norm": 2.678083658218384,
|
| 8998 |
+
"learning_rate": 9.310567010309279e-06,
|
| 8999 |
+
"loss": 0.1082,
|
| 9000 |
+
"step": 11770
|
| 9001 |
+
},
|
| 9002 |
+
{
|
| 9003 |
+
"epoch": 5.520149953139644,
|
| 9004 |
+
"grad_norm": 2.221808910369873,
|
| 9005 |
+
"learning_rate": 9.309981255857546e-06,
|
| 9006 |
+
"loss": 0.0951,
|
| 9007 |
+
"step": 11780
|
| 9008 |
+
},
|
| 9009 |
+
{
|
| 9010 |
+
"epoch": 5.524835988753514,
|
| 9011 |
+
"grad_norm": 3.2802789211273193,
|
| 9012 |
+
"learning_rate": 9.30939550140581e-06,
|
| 9013 |
+
"loss": 0.1153,
|
| 9014 |
+
"step": 11790
|
| 9015 |
+
},
|
| 9016 |
+
{
|
| 9017 |
+
"epoch": 5.5295220243673855,
|
| 9018 |
+
"grad_norm": 2.6341254711151123,
|
| 9019 |
+
"learning_rate": 9.308809746954078e-06,
|
| 9020 |
+
"loss": 0.1173,
|
| 9021 |
+
"step": 11800
|
| 9022 |
+
},
|
| 9023 |
+
{
|
| 9024 |
+
"epoch": 5.534208059981256,
|
| 9025 |
+
"grad_norm": 1.4996163845062256,
|
| 9026 |
+
"learning_rate": 9.308223992502345e-06,
|
| 9027 |
+
"loss": 0.1066,
|
| 9028 |
+
"step": 11810
|
| 9029 |
+
},
|
| 9030 |
+
{
|
| 9031 |
+
"epoch": 5.5388940955951265,
|
| 9032 |
+
"grad_norm": 1.6984524726867676,
|
| 9033 |
+
"learning_rate": 9.30763823805061e-06,
|
| 9034 |
+
"loss": 0.0985,
|
| 9035 |
+
"step": 11820
|
| 9036 |
+
},
|
| 9037 |
+
{
|
| 9038 |
+
"epoch": 5.543580131208997,
|
| 9039 |
+
"grad_norm": 2.20283842086792,
|
| 9040 |
+
"learning_rate": 9.307052483598877e-06,
|
| 9041 |
+
"loss": 0.1011,
|
| 9042 |
+
"step": 11830
|
| 9043 |
+
},
|
| 9044 |
+
{
|
| 9045 |
+
"epoch": 5.548266166822868,
|
| 9046 |
+
"grad_norm": 1.3354145288467407,
|
| 9047 |
+
"learning_rate": 9.306466729147142e-06,
|
| 9048 |
+
"loss": 0.1067,
|
| 9049 |
+
"step": 11840
|
| 9050 |
+
},
|
| 9051 |
+
{
|
| 9052 |
+
"epoch": 5.552952202436739,
|
| 9053 |
+
"grad_norm": 2.6207938194274902,
|
| 9054 |
+
"learning_rate": 9.305880974695409e-06,
|
| 9055 |
+
"loss": 0.1159,
|
| 9056 |
+
"step": 11850
|
| 9057 |
+
},
|
| 9058 |
+
{
|
| 9059 |
+
"epoch": 5.557638238050609,
|
| 9060 |
+
"grad_norm": 2.9331352710723877,
|
| 9061 |
+
"learning_rate": 9.305295220243674e-06,
|
| 9062 |
+
"loss": 0.1152,
|
| 9063 |
+
"step": 11860
|
| 9064 |
+
},
|
| 9065 |
+
{
|
| 9066 |
+
"epoch": 5.56232427366448,
|
| 9067 |
+
"grad_norm": 1.8482978343963623,
|
| 9068 |
+
"learning_rate": 9.304709465791941e-06,
|
| 9069 |
+
"loss": 0.1121,
|
| 9070 |
+
"step": 11870
|
| 9071 |
+
},
|
| 9072 |
+
{
|
| 9073 |
+
"epoch": 5.56701030927835,
|
| 9074 |
+
"grad_norm": 1.7065162658691406,
|
| 9075 |
+
"learning_rate": 9.304123711340208e-06,
|
| 9076 |
+
"loss": 0.1256,
|
| 9077 |
+
"step": 11880
|
| 9078 |
+
},
|
| 9079 |
+
{
|
| 9080 |
+
"epoch": 5.571696344892221,
|
| 9081 |
+
"grad_norm": 2.6578869819641113,
|
| 9082 |
+
"learning_rate": 9.303537956888473e-06,
|
| 9083 |
+
"loss": 0.1033,
|
| 9084 |
+
"step": 11890
|
| 9085 |
+
},
|
| 9086 |
+
{
|
| 9087 |
+
"epoch": 5.576382380506092,
|
| 9088 |
+
"grad_norm": 2.356271266937256,
|
| 9089 |
+
"learning_rate": 9.302952202436738e-06,
|
| 9090 |
+
"loss": 0.1106,
|
| 9091 |
+
"step": 11900
|
| 9092 |
+
},
|
| 9093 |
+
{
|
| 9094 |
+
"epoch": 5.581068416119963,
|
| 9095 |
+
"grad_norm": 2.4331321716308594,
|
| 9096 |
+
"learning_rate": 9.302366447985005e-06,
|
| 9097 |
+
"loss": 0.1342,
|
| 9098 |
+
"step": 11910
|
| 9099 |
+
},
|
| 9100 |
+
{
|
| 9101 |
+
"epoch": 5.585754451733833,
|
| 9102 |
+
"grad_norm": 2.5583012104034424,
|
| 9103 |
+
"learning_rate": 9.30178069353327e-06,
|
| 9104 |
+
"loss": 0.1232,
|
| 9105 |
+
"step": 11920
|
| 9106 |
+
},
|
| 9107 |
+
{
|
| 9108 |
+
"epoch": 5.590440487347704,
|
| 9109 |
+
"grad_norm": 1.2320704460144043,
|
| 9110 |
+
"learning_rate": 9.301194939081537e-06,
|
| 9111 |
+
"loss": 0.1235,
|
| 9112 |
+
"step": 11930
|
| 9113 |
+
},
|
| 9114 |
+
{
|
| 9115 |
+
"epoch": 5.595126522961575,
|
| 9116 |
+
"grad_norm": 2.749943256378174,
|
| 9117 |
+
"learning_rate": 9.300609184629804e-06,
|
| 9118 |
+
"loss": 0.1204,
|
| 9119 |
+
"step": 11940
|
| 9120 |
+
},
|
| 9121 |
+
{
|
| 9122 |
+
"epoch": 5.5998125585754455,
|
| 9123 |
+
"grad_norm": 1.935255527496338,
|
| 9124 |
+
"learning_rate": 9.30002343017807e-06,
|
| 9125 |
+
"loss": 0.1194,
|
| 9126 |
+
"step": 11950
|
| 9127 |
+
},
|
| 9128 |
+
{
|
| 9129 |
+
"epoch": 5.604498594189316,
|
| 9130 |
+
"grad_norm": 2.05389666557312,
|
| 9131 |
+
"learning_rate": 9.299437675726337e-06,
|
| 9132 |
+
"loss": 0.1185,
|
| 9133 |
+
"step": 11960
|
| 9134 |
+
},
|
| 9135 |
+
{
|
| 9136 |
+
"epoch": 5.609184629803186,
|
| 9137 |
+
"grad_norm": 2.0948450565338135,
|
| 9138 |
+
"learning_rate": 9.298851921274602e-06,
|
| 9139 |
+
"loss": 0.117,
|
| 9140 |
+
"step": 11970
|
| 9141 |
+
},
|
| 9142 |
+
{
|
| 9143 |
+
"epoch": 5.613870665417057,
|
| 9144 |
+
"grad_norm": 2.4468414783477783,
|
| 9145 |
+
"learning_rate": 9.298266166822869e-06,
|
| 9146 |
+
"loss": 0.1042,
|
| 9147 |
+
"step": 11980
|
| 9148 |
+
},
|
| 9149 |
+
{
|
| 9150 |
+
"epoch": 5.618556701030927,
|
| 9151 |
+
"grad_norm": 1.7686811685562134,
|
| 9152 |
+
"learning_rate": 9.297680412371136e-06,
|
| 9153 |
+
"loss": 0.1323,
|
| 9154 |
+
"step": 11990
|
| 9155 |
+
},
|
| 9156 |
+
{
|
| 9157 |
+
"epoch": 5.623242736644799,
|
| 9158 |
+
"grad_norm": 2.70004940032959,
|
| 9159 |
+
"learning_rate": 9.2970946579194e-06,
|
| 9160 |
+
"loss": 0.1153,
|
| 9161 |
+
"step": 12000
|
| 9162 |
+
},
|
| 9163 |
+
{
|
| 9164 |
+
"epoch": 5.623242736644799,
|
| 9165 |
+
"eval_loss": 0.044810693711042404,
|
| 9166 |
+
"eval_pearson_cosine": 0.7729592983209912,
|
| 9167 |
+
"eval_pearson_dot": 0.6141014999130547,
|
| 9168 |
+
"eval_pearson_euclidean": 0.7453445610743417,
|
| 9169 |
+
"eval_pearson_manhattan": 0.7450714346494465,
|
| 9170 |
+
"eval_runtime": 39.9226,
|
| 9171 |
+
"eval_samples_per_second": 37.573,
|
| 9172 |
+
"eval_spearman_cosine": 0.7783555866745624,
|
| 9173 |
+
"eval_spearman_dot": 0.6213713696364336,
|
| 9174 |
+
"eval_spearman_euclidean": 0.7596029469985899,
|
| 9175 |
+
"eval_spearman_manhattan": 0.7598359774134882,
|
| 9176 |
+
"eval_steps_per_second": 37.573,
|
| 9177 |
+
"step": 12000
|
| 9178 |
}
|
| 9179 |
],
|
| 9180 |
"logging_steps": 10,
|