Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-0/checkpoint-117/model.safetensors +1 -1
- run-0/checkpoint-117/optimizer.pt +1 -1
- run-0/checkpoint-117/training_args.bin +2 -2
- run-0/checkpoint-156/model.safetensors +1 -1
- run-0/checkpoint-156/optimizer.pt +1 -1
- run-0/checkpoint-156/training_args.bin +2 -2
- run-0/checkpoint-195/model.safetensors +1 -1
- run-0/checkpoint-195/optimizer.pt +1 -1
- run-0/checkpoint-195/training_args.bin +2 -2
- run-0/checkpoint-78/model.safetensors +1 -1
- run-0/checkpoint-78/optimizer.pt +1 -1
- run-1/checkpoint-117/trainer_state.json +96 -19
- run-1/checkpoint-156/trainer_state.json +129 -24
- run-1/checkpoint-195/trainer_state.json +162 -29
- run-1/checkpoint-39/model.safetensors +1 -1
- run-1/checkpoint-39/optimizer.pt +1 -1
- run-1/checkpoint-39/trainer_state.json +29 -8
- run-1/checkpoint-39/training_args.bin +2 -2
- run-1/checkpoint-78/model.safetensors +1 -1
- run-1/checkpoint-78/optimizer.pt +1 -1
- run-1/checkpoint-78/trainer_state.json +60 -11
- run-1/checkpoint-78/training_args.bin +2 -2
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437958648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee88e6717263c77a0f03100cc35fa96932239afe69dfed14459f1fe5653ba1ec
|
| 3 |
size 437958648
|
run-0/checkpoint-117/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437958648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:336176c2d8a88b2ec65816f06390b706dbe724ea1904dd501b45b1739ccfd759
|
| 3 |
size 437958648
|
run-0/checkpoint-117/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 876038394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:55e7a1115fd5a22668d168f5999868b089bbfb6f929baaac6cabf742f3d263ab
|
| 3 |
size 876038394
|
run-0/checkpoint-117/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:ae96125486481670db20065f4109e420c062152dc014578dda8c216f7705ceba
|
| 3 |
+
size 5368
|
run-0/checkpoint-156/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437958648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c92a6da78f2dd0bc10260aec0dc55e7510c8aaf81228f55b626fd6ec25f47bb
|
| 3 |
size 437958648
|
run-0/checkpoint-156/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 876038394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e5b3242df5ac190669a37d08e52b465a6effc1e6f43cbdf6984accb9742743c
|
| 3 |
size 876038394
|
run-0/checkpoint-156/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:ae96125486481670db20065f4109e420c062152dc014578dda8c216f7705ceba
|
| 3 |
+
size 5368
|
run-0/checkpoint-195/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437958648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2362d3726c931e4f20b4c1fb1325c6d7926a7bc6dd4ad834532d3c27d4b143e
|
| 3 |
size 437958648
|
run-0/checkpoint-195/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 876038394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37dcaf11b786b8617a26d4f3203cd341c40e0dfd9aa43f1ee41581f4f9a9b537
|
| 3 |
size 876038394
|
run-0/checkpoint-195/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:ae96125486481670db20065f4109e420c062152dc014578dda8c216f7705ceba
|
| 3 |
+
size 5368
|
run-0/checkpoint-78/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437958648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31175051979c65e9fcea303433b87161573a7f06d6d47162a5046877fbcdc3d2
|
| 3 |
size 437958648
|
run-0/checkpoint-78/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 876038394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdb897a419dd2c7023b461da3f70182ae7bf34843ee0185ad6525342aa20894c
|
| 3 |
size 876038394
|
run-1/checkpoint-117/trainer_state.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-
|
| 5 |
"epoch": 3.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 117,
|
|
@@ -9,35 +9,112 @@
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
{
|
| 13 |
"epoch": 1.0,
|
| 14 |
-
"eval_accuracy": 0.
|
| 15 |
-
"eval_loss": 0.
|
| 16 |
-
"eval_runtime": 0.
|
| 17 |
-
"eval_samples_per_second":
|
| 18 |
-
"eval_steps_per_second": 14.
|
| 19 |
"step": 39
|
| 20 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
{
|
| 22 |
"epoch": 2.0,
|
| 23 |
"eval_accuracy": 0.6895306859205776,
|
| 24 |
-
"eval_loss": 0.
|
| 25 |
-
"eval_runtime": 0.
|
| 26 |
-
"eval_samples_per_second":
|
| 27 |
-
"eval_steps_per_second": 14.
|
| 28 |
"step": 78
|
| 29 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
{
|
| 31 |
"epoch": 3.0,
|
| 32 |
-
"eval_accuracy": 0.
|
| 33 |
-
"eval_loss": 0.
|
| 34 |
-
"eval_runtime": 0.
|
| 35 |
-
"eval_samples_per_second":
|
| 36 |
-
"eval_steps_per_second":
|
| 37 |
"step": 117
|
| 38 |
}
|
| 39 |
],
|
| 40 |
-
"logging_steps":
|
| 41 |
"max_steps": 195,
|
| 42 |
"num_input_tokens_seen": 0,
|
| 43 |
"num_train_epochs": 5,
|
|
@@ -54,7 +131,7 @@
|
|
| 54 |
"attributes": {}
|
| 55 |
}
|
| 56 |
},
|
| 57 |
-
"total_flos": 0,
|
| 58 |
"train_batch_size": 64,
|
| 59 |
"trial_name": null,
|
| 60 |
"trial_params": {
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 117,
|
| 3 |
+
"best_metric": 0.7003610108303249,
|
| 4 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-117",
|
| 5 |
"epoch": 3.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 117,
|
|
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2564102564102564,
|
| 14 |
+
"grad_norm": 1.6625864505767822,
|
| 15 |
+
"learning_rate": 9.487179487179487e-05,
|
| 16 |
+
"loss": 0.696,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5128205128205128,
|
| 21 |
+
"grad_norm": 2.0310187339782715,
|
| 22 |
+
"learning_rate": 8.974358974358975e-05,
|
| 23 |
+
"loss": 0.6793,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7692307692307693,
|
| 28 |
+
"grad_norm": 4.6874542236328125,
|
| 29 |
+
"learning_rate": 8.461538461538461e-05,
|
| 30 |
+
"loss": 0.6504,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
{
|
| 34 |
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.6173285198555957,
|
| 36 |
+
"eval_loss": 0.635858952999115,
|
| 37 |
+
"eval_runtime": 0.6367,
|
| 38 |
+
"eval_samples_per_second": 435.081,
|
| 39 |
+
"eval_steps_per_second": 14.136,
|
| 40 |
"step": 39
|
| 41 |
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.0256410256410255,
|
| 44 |
+
"grad_norm": 2.9923806190490723,
|
| 45 |
+
"learning_rate": 7.948717948717948e-05,
|
| 46 |
+
"loss": 0.6828,
|
| 47 |
+
"step": 40
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.282051282051282,
|
| 51 |
+
"grad_norm": 5.838254928588867,
|
| 52 |
+
"learning_rate": 7.435897435897436e-05,
|
| 53 |
+
"loss": 0.5479,
|
| 54 |
+
"step": 50
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.5384615384615383,
|
| 58 |
+
"grad_norm": 11.470205307006836,
|
| 59 |
+
"learning_rate": 6.923076923076924e-05,
|
| 60 |
+
"loss": 0.5428,
|
| 61 |
+
"step": 60
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.7948717948717947,
|
| 65 |
+
"grad_norm": 6.020153045654297,
|
| 66 |
+
"learning_rate": 6.410256410256412e-05,
|
| 67 |
+
"loss": 0.5377,
|
| 68 |
+
"step": 70
|
| 69 |
+
},
|
| 70 |
{
|
| 71 |
"epoch": 2.0,
|
| 72 |
"eval_accuracy": 0.6895306859205776,
|
| 73 |
+
"eval_loss": 0.655694842338562,
|
| 74 |
+
"eval_runtime": 0.6409,
|
| 75 |
+
"eval_samples_per_second": 432.172,
|
| 76 |
+
"eval_steps_per_second": 14.042,
|
| 77 |
"step": 78
|
| 78 |
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 2.051282051282051,
|
| 81 |
+
"grad_norm": 6.008265018463135,
|
| 82 |
+
"learning_rate": 5.897435897435898e-05,
|
| 83 |
+
"loss": 0.4698,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.3076923076923075,
|
| 88 |
+
"grad_norm": 3.914435386657715,
|
| 89 |
+
"learning_rate": 5.384615384615385e-05,
|
| 90 |
+
"loss": 0.3238,
|
| 91 |
+
"step": 90
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 2.564102564102564,
|
| 95 |
+
"grad_norm": 5.716212749481201,
|
| 96 |
+
"learning_rate": 4.871794871794872e-05,
|
| 97 |
+
"loss": 0.3333,
|
| 98 |
+
"step": 100
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.8205128205128203,
|
| 102 |
+
"grad_norm": 4.88173246383667,
|
| 103 |
+
"learning_rate": 4.358974358974359e-05,
|
| 104 |
+
"loss": 0.2856,
|
| 105 |
+
"step": 110
|
| 106 |
+
},
|
| 107 |
{
|
| 108 |
"epoch": 3.0,
|
| 109 |
+
"eval_accuracy": 0.7003610108303249,
|
| 110 |
+
"eval_loss": 0.6911355257034302,
|
| 111 |
+
"eval_runtime": 0.6387,
|
| 112 |
+
"eval_samples_per_second": 433.671,
|
| 113 |
+
"eval_steps_per_second": 14.09,
|
| 114 |
"step": 117
|
| 115 |
}
|
| 116 |
],
|
| 117 |
+
"logging_steps": 10,
|
| 118 |
"max_steps": 195,
|
| 119 |
"num_input_tokens_seen": 0,
|
| 120 |
"num_train_epochs": 5,
|
|
|
|
| 131 |
"attributes": {}
|
| 132 |
}
|
| 133 |
},
|
| 134 |
+
"total_flos": 718007458971120.0,
|
| 135 |
"train_batch_size": 64,
|
| 136 |
"trial_name": null,
|
| 137 |
"trial_params": {
|
run-1/checkpoint-156/trainer_state.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-
|
| 5 |
"epoch": 4.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 156,
|
|
@@ -9,44 +9,149 @@
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
{
|
| 13 |
"epoch": 1.0,
|
| 14 |
-
"eval_accuracy": 0.
|
| 15 |
-
"eval_loss": 0.
|
| 16 |
-
"eval_runtime": 0.
|
| 17 |
-
"eval_samples_per_second":
|
| 18 |
-
"eval_steps_per_second": 14.
|
| 19 |
"step": 39
|
| 20 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
{
|
| 22 |
"epoch": 2.0,
|
| 23 |
"eval_accuracy": 0.6895306859205776,
|
| 24 |
-
"eval_loss": 0.
|
| 25 |
-
"eval_runtime": 0.
|
| 26 |
-
"eval_samples_per_second":
|
| 27 |
-
"eval_steps_per_second": 14.
|
| 28 |
"step": 78
|
| 29 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
{
|
| 31 |
"epoch": 3.0,
|
| 32 |
-
"eval_accuracy": 0.
|
| 33 |
-
"eval_loss": 0.
|
| 34 |
-
"eval_runtime": 0.
|
| 35 |
-
"eval_samples_per_second":
|
| 36 |
-
"eval_steps_per_second":
|
| 37 |
"step": 117
|
| 38 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
{
|
| 40 |
"epoch": 4.0,
|
| 41 |
-
"eval_accuracy": 0.
|
| 42 |
-
"eval_loss":
|
| 43 |
-
"eval_runtime": 0.
|
| 44 |
-
"eval_samples_per_second":
|
| 45 |
-
"eval_steps_per_second":
|
| 46 |
"step": 156
|
| 47 |
}
|
| 48 |
],
|
| 49 |
-
"logging_steps":
|
| 50 |
"max_steps": 195,
|
| 51 |
"num_input_tokens_seen": 0,
|
| 52 |
"num_train_epochs": 5,
|
|
@@ -63,7 +168,7 @@
|
|
| 63 |
"attributes": {}
|
| 64 |
}
|
| 65 |
},
|
| 66 |
-
"total_flos": 0,
|
| 67 |
"train_batch_size": 64,
|
| 68 |
"trial_name": null,
|
| 69 |
"trial_params": {
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 156,
|
| 3 |
+
"best_metric": 0.7148014440433214,
|
| 4 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-156",
|
| 5 |
"epoch": 4.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 156,
|
|
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2564102564102564,
|
| 14 |
+
"grad_norm": 1.6625864505767822,
|
| 15 |
+
"learning_rate": 9.487179487179487e-05,
|
| 16 |
+
"loss": 0.696,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5128205128205128,
|
| 21 |
+
"grad_norm": 2.0310187339782715,
|
| 22 |
+
"learning_rate": 8.974358974358975e-05,
|
| 23 |
+
"loss": 0.6793,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7692307692307693,
|
| 28 |
+
"grad_norm": 4.6874542236328125,
|
| 29 |
+
"learning_rate": 8.461538461538461e-05,
|
| 30 |
+
"loss": 0.6504,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
{
|
| 34 |
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.6173285198555957,
|
| 36 |
+
"eval_loss": 0.635858952999115,
|
| 37 |
+
"eval_runtime": 0.6367,
|
| 38 |
+
"eval_samples_per_second": 435.081,
|
| 39 |
+
"eval_steps_per_second": 14.136,
|
| 40 |
"step": 39
|
| 41 |
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.0256410256410255,
|
| 44 |
+
"grad_norm": 2.9923806190490723,
|
| 45 |
+
"learning_rate": 7.948717948717948e-05,
|
| 46 |
+
"loss": 0.6828,
|
| 47 |
+
"step": 40
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.282051282051282,
|
| 51 |
+
"grad_norm": 5.838254928588867,
|
| 52 |
+
"learning_rate": 7.435897435897436e-05,
|
| 53 |
+
"loss": 0.5479,
|
| 54 |
+
"step": 50
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.5384615384615383,
|
| 58 |
+
"grad_norm": 11.470205307006836,
|
| 59 |
+
"learning_rate": 6.923076923076924e-05,
|
| 60 |
+
"loss": 0.5428,
|
| 61 |
+
"step": 60
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.7948717948717947,
|
| 65 |
+
"grad_norm": 6.020153045654297,
|
| 66 |
+
"learning_rate": 6.410256410256412e-05,
|
| 67 |
+
"loss": 0.5377,
|
| 68 |
+
"step": 70
|
| 69 |
+
},
|
| 70 |
{
|
| 71 |
"epoch": 2.0,
|
| 72 |
"eval_accuracy": 0.6895306859205776,
|
| 73 |
+
"eval_loss": 0.655694842338562,
|
| 74 |
+
"eval_runtime": 0.6409,
|
| 75 |
+
"eval_samples_per_second": 432.172,
|
| 76 |
+
"eval_steps_per_second": 14.042,
|
| 77 |
"step": 78
|
| 78 |
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 2.051282051282051,
|
| 81 |
+
"grad_norm": 6.008265018463135,
|
| 82 |
+
"learning_rate": 5.897435897435898e-05,
|
| 83 |
+
"loss": 0.4698,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.3076923076923075,
|
| 88 |
+
"grad_norm": 3.914435386657715,
|
| 89 |
+
"learning_rate": 5.384615384615385e-05,
|
| 90 |
+
"loss": 0.3238,
|
| 91 |
+
"step": 90
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 2.564102564102564,
|
| 95 |
+
"grad_norm": 5.716212749481201,
|
| 96 |
+
"learning_rate": 4.871794871794872e-05,
|
| 97 |
+
"loss": 0.3333,
|
| 98 |
+
"step": 100
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.8205128205128203,
|
| 102 |
+
"grad_norm": 4.88173246383667,
|
| 103 |
+
"learning_rate": 4.358974358974359e-05,
|
| 104 |
+
"loss": 0.2856,
|
| 105 |
+
"step": 110
|
| 106 |
+
},
|
| 107 |
{
|
| 108 |
"epoch": 3.0,
|
| 109 |
+
"eval_accuracy": 0.7003610108303249,
|
| 110 |
+
"eval_loss": 0.6911355257034302,
|
| 111 |
+
"eval_runtime": 0.6387,
|
| 112 |
+
"eval_samples_per_second": 433.671,
|
| 113 |
+
"eval_steps_per_second": 14.09,
|
| 114 |
"step": 117
|
| 115 |
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.076923076923077,
|
| 118 |
+
"grad_norm": 2.6747496128082275,
|
| 119 |
+
"learning_rate": 3.846153846153846e-05,
|
| 120 |
+
"loss": 0.2572,
|
| 121 |
+
"step": 120
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.3333333333333335,
|
| 125 |
+
"grad_norm": 12.598614692687988,
|
| 126 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 127 |
+
"loss": 0.1804,
|
| 128 |
+
"step": 130
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.58974358974359,
|
| 132 |
+
"grad_norm": 3.0282769203186035,
|
| 133 |
+
"learning_rate": 2.8205128205128207e-05,
|
| 134 |
+
"loss": 0.154,
|
| 135 |
+
"step": 140
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.8461538461538463,
|
| 139 |
+
"grad_norm": 4.283105850219727,
|
| 140 |
+
"learning_rate": 2.307692307692308e-05,
|
| 141 |
+
"loss": 0.1396,
|
| 142 |
+
"step": 150
|
| 143 |
+
},
|
| 144 |
{
|
| 145 |
"epoch": 4.0,
|
| 146 |
+
"eval_accuracy": 0.7148014440433214,
|
| 147 |
+
"eval_loss": 0.8559210896492004,
|
| 148 |
+
"eval_runtime": 0.6397,
|
| 149 |
+
"eval_samples_per_second": 433.035,
|
| 150 |
+
"eval_steps_per_second": 14.07,
|
| 151 |
"step": 156
|
| 152 |
}
|
| 153 |
],
|
| 154 |
+
"logging_steps": 10,
|
| 155 |
"max_steps": 195,
|
| 156 |
"num_input_tokens_seen": 0,
|
| 157 |
"num_train_epochs": 5,
|
|
|
|
| 168 |
"attributes": {}
|
| 169 |
}
|
| 170 |
},
|
| 171 |
+
"total_flos": 971430683050560.0,
|
| 172 |
"train_batch_size": 64,
|
| 173 |
"trial_name": null,
|
| 174 |
"trial_params": {
|
run-1/checkpoint-195/trainer_state.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"best_global_step":
|
| 3 |
-
"best_metric": 0.
|
| 4 |
-
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-
|
| 5 |
"epoch": 5.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 195,
|
|
@@ -9,53 +9,186 @@
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
{
|
| 13 |
"epoch": 1.0,
|
| 14 |
-
"eval_accuracy": 0.
|
| 15 |
-
"eval_loss": 0.
|
| 16 |
-
"eval_runtime": 0.
|
| 17 |
-
"eval_samples_per_second":
|
| 18 |
-
"eval_steps_per_second": 14.
|
| 19 |
"step": 39
|
| 20 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
{
|
| 22 |
"epoch": 2.0,
|
| 23 |
"eval_accuracy": 0.6895306859205776,
|
| 24 |
-
"eval_loss": 0.
|
| 25 |
-
"eval_runtime": 0.
|
| 26 |
-
"eval_samples_per_second":
|
| 27 |
-
"eval_steps_per_second": 14.
|
| 28 |
"step": 78
|
| 29 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 30 |
{
|
| 31 |
"epoch": 3.0,
|
| 32 |
-
"eval_accuracy": 0.
|
| 33 |
-
"eval_loss": 0.
|
| 34 |
-
"eval_runtime": 0.
|
| 35 |
-
"eval_samples_per_second":
|
| 36 |
-
"eval_steps_per_second":
|
| 37 |
"step": 117
|
| 38 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 39 |
{
|
| 40 |
"epoch": 4.0,
|
| 41 |
-
"eval_accuracy": 0.
|
| 42 |
-
"eval_loss":
|
| 43 |
-
"eval_runtime": 0.
|
| 44 |
-
"eval_samples_per_second":
|
| 45 |
-
"eval_steps_per_second":
|
| 46 |
"step": 156
|
| 47 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
{
|
| 49 |
"epoch": 5.0,
|
| 50 |
-
"eval_accuracy": 0.
|
| 51 |
-
"eval_loss": 1.
|
| 52 |
-
"eval_runtime": 0.
|
| 53 |
-
"eval_samples_per_second":
|
| 54 |
-
"eval_steps_per_second":
|
| 55 |
"step": 195
|
| 56 |
}
|
| 57 |
],
|
| 58 |
-
"logging_steps":
|
| 59 |
"max_steps": 195,
|
| 60 |
"num_input_tokens_seen": 0,
|
| 61 |
"num_train_epochs": 5,
|
|
@@ -72,7 +205,7 @@
|
|
| 72 |
"attributes": {}
|
| 73 |
}
|
| 74 |
},
|
| 75 |
-
"total_flos": 0,
|
| 76 |
"train_batch_size": 64,
|
| 77 |
"trial_name": null,
|
| 78 |
"trial_params": {
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_global_step": 195,
|
| 3 |
+
"best_metric": 0.7184115523465704,
|
| 4 |
+
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-195",
|
| 5 |
"epoch": 5.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
"global_step": 195,
|
|
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2564102564102564,
|
| 14 |
+
"grad_norm": 1.6625864505767822,
|
| 15 |
+
"learning_rate": 9.487179487179487e-05,
|
| 16 |
+
"loss": 0.696,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5128205128205128,
|
| 21 |
+
"grad_norm": 2.0310187339782715,
|
| 22 |
+
"learning_rate": 8.974358974358975e-05,
|
| 23 |
+
"loss": 0.6793,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7692307692307693,
|
| 28 |
+
"grad_norm": 4.6874542236328125,
|
| 29 |
+
"learning_rate": 8.461538461538461e-05,
|
| 30 |
+
"loss": 0.6504,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
{
|
| 34 |
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.6173285198555957,
|
| 36 |
+
"eval_loss": 0.635858952999115,
|
| 37 |
+
"eval_runtime": 0.6367,
|
| 38 |
+
"eval_samples_per_second": 435.081,
|
| 39 |
+
"eval_steps_per_second": 14.136,
|
| 40 |
"step": 39
|
| 41 |
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.0256410256410255,
|
| 44 |
+
"grad_norm": 2.9923806190490723,
|
| 45 |
+
"learning_rate": 7.948717948717948e-05,
|
| 46 |
+
"loss": 0.6828,
|
| 47 |
+
"step": 40
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.282051282051282,
|
| 51 |
+
"grad_norm": 5.838254928588867,
|
| 52 |
+
"learning_rate": 7.435897435897436e-05,
|
| 53 |
+
"loss": 0.5479,
|
| 54 |
+
"step": 50
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.5384615384615383,
|
| 58 |
+
"grad_norm": 11.470205307006836,
|
| 59 |
+
"learning_rate": 6.923076923076924e-05,
|
| 60 |
+
"loss": 0.5428,
|
| 61 |
+
"step": 60
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.7948717948717947,
|
| 65 |
+
"grad_norm": 6.020153045654297,
|
| 66 |
+
"learning_rate": 6.410256410256412e-05,
|
| 67 |
+
"loss": 0.5377,
|
| 68 |
+
"step": 70
|
| 69 |
+
},
|
| 70 |
{
|
| 71 |
"epoch": 2.0,
|
| 72 |
"eval_accuracy": 0.6895306859205776,
|
| 73 |
+
"eval_loss": 0.655694842338562,
|
| 74 |
+
"eval_runtime": 0.6409,
|
| 75 |
+
"eval_samples_per_second": 432.172,
|
| 76 |
+
"eval_steps_per_second": 14.042,
|
| 77 |
"step": 78
|
| 78 |
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 2.051282051282051,
|
| 81 |
+
"grad_norm": 6.008265018463135,
|
| 82 |
+
"learning_rate": 5.897435897435898e-05,
|
| 83 |
+
"loss": 0.4698,
|
| 84 |
+
"step": 80
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.3076923076923075,
|
| 88 |
+
"grad_norm": 3.914435386657715,
|
| 89 |
+
"learning_rate": 5.384615384615385e-05,
|
| 90 |
+
"loss": 0.3238,
|
| 91 |
+
"step": 90
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 2.564102564102564,
|
| 95 |
+
"grad_norm": 5.716212749481201,
|
| 96 |
+
"learning_rate": 4.871794871794872e-05,
|
| 97 |
+
"loss": 0.3333,
|
| 98 |
+
"step": 100
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 2.8205128205128203,
|
| 102 |
+
"grad_norm": 4.88173246383667,
|
| 103 |
+
"learning_rate": 4.358974358974359e-05,
|
| 104 |
+
"loss": 0.2856,
|
| 105 |
+
"step": 110
|
| 106 |
+
},
|
| 107 |
{
|
| 108 |
"epoch": 3.0,
|
| 109 |
+
"eval_accuracy": 0.7003610108303249,
|
| 110 |
+
"eval_loss": 0.6911355257034302,
|
| 111 |
+
"eval_runtime": 0.6387,
|
| 112 |
+
"eval_samples_per_second": 433.671,
|
| 113 |
+
"eval_steps_per_second": 14.09,
|
| 114 |
"step": 117
|
| 115 |
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.076923076923077,
|
| 118 |
+
"grad_norm": 2.6747496128082275,
|
| 119 |
+
"learning_rate": 3.846153846153846e-05,
|
| 120 |
+
"loss": 0.2572,
|
| 121 |
+
"step": 120
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.3333333333333335,
|
| 125 |
+
"grad_norm": 12.598614692687988,
|
| 126 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 127 |
+
"loss": 0.1804,
|
| 128 |
+
"step": 130
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 3.58974358974359,
|
| 132 |
+
"grad_norm": 3.0282769203186035,
|
| 133 |
+
"learning_rate": 2.8205128205128207e-05,
|
| 134 |
+
"loss": 0.154,
|
| 135 |
+
"step": 140
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 3.8461538461538463,
|
| 139 |
+
"grad_norm": 4.283105850219727,
|
| 140 |
+
"learning_rate": 2.307692307692308e-05,
|
| 141 |
+
"loss": 0.1396,
|
| 142 |
+
"step": 150
|
| 143 |
+
},
|
| 144 |
{
|
| 145 |
"epoch": 4.0,
|
| 146 |
+
"eval_accuracy": 0.7148014440433214,
|
| 147 |
+
"eval_loss": 0.8559210896492004,
|
| 148 |
+
"eval_runtime": 0.6397,
|
| 149 |
+
"eval_samples_per_second": 433.035,
|
| 150 |
+
"eval_steps_per_second": 14.07,
|
| 151 |
"step": 156
|
| 152 |
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 4.102564102564102,
|
| 155 |
+
"grad_norm": 2.513899564743042,
|
| 156 |
+
"learning_rate": 1.794871794871795e-05,
|
| 157 |
+
"loss": 0.1126,
|
| 158 |
+
"step": 160
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 4.358974358974359,
|
| 162 |
+
"grad_norm": 5.151243209838867,
|
| 163 |
+
"learning_rate": 1.282051282051282e-05,
|
| 164 |
+
"loss": 0.0718,
|
| 165 |
+
"step": 170
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 4.615384615384615,
|
| 169 |
+
"grad_norm": 3.647749423980713,
|
| 170 |
+
"learning_rate": 7.692307692307694e-06,
|
| 171 |
+
"loss": 0.0471,
|
| 172 |
+
"step": 180
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 4.871794871794872,
|
| 176 |
+
"grad_norm": 2.2977404594421387,
|
| 177 |
+
"learning_rate": 2.564102564102564e-06,
|
| 178 |
+
"loss": 0.0753,
|
| 179 |
+
"step": 190
|
| 180 |
+
},
|
| 181 |
{
|
| 182 |
"epoch": 5.0,
|
| 183 |
+
"eval_accuracy": 0.7184115523465704,
|
| 184 |
+
"eval_loss": 1.0575038194656372,
|
| 185 |
+
"eval_runtime": 0.643,
|
| 186 |
+
"eval_samples_per_second": 430.784,
|
| 187 |
+
"eval_steps_per_second": 13.997,
|
| 188 |
"step": 195
|
| 189 |
}
|
| 190 |
],
|
| 191 |
+
"logging_steps": 10,
|
| 192 |
"max_steps": 195,
|
| 193 |
"num_input_tokens_seen": 0,
|
| 194 |
"num_train_epochs": 5,
|
|
|
|
| 205 |
"attributes": {}
|
| 206 |
}
|
| 207 |
},
|
| 208 |
+
"total_flos": 1230830433641400.0,
|
| 209 |
"train_batch_size": 64,
|
| 210 |
"trial_name": null,
|
| 211 |
"trial_params": {
|
run-1/checkpoint-39/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437958648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee88e6717263c77a0f03100cc35fa96932239afe69dfed14459f1fe5653ba1ec
|
| 3 |
size 437958648
|
run-1/checkpoint-39/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 876038394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:050edea9509040a97c466e80b805ce4bb13c72cf46c38be765b0aa4f1629e0bf
|
| 3 |
size 876038394
|
run-1/checkpoint-39/trainer_state.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"best_global_step": 39,
|
| 3 |
-
"best_metric": 0.
|
| 4 |
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-39",
|
| 5 |
"epoch": 1.0,
|
| 6 |
"eval_steps": 500,
|
|
@@ -9,17 +9,38 @@
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
{
|
| 13 |
"epoch": 1.0,
|
| 14 |
-
"eval_accuracy": 0.
|
| 15 |
-
"eval_loss": 0.
|
| 16 |
-
"eval_runtime": 0.
|
| 17 |
-
"eval_samples_per_second":
|
| 18 |
-
"eval_steps_per_second": 14.
|
| 19 |
"step": 39
|
| 20 |
}
|
| 21 |
],
|
| 22 |
-
"logging_steps":
|
| 23 |
"max_steps": 195,
|
| 24 |
"num_input_tokens_seen": 0,
|
| 25 |
"num_train_epochs": 5,
|
|
@@ -36,7 +57,7 @@
|
|
| 36 |
"attributes": {}
|
| 37 |
}
|
| 38 |
},
|
| 39 |
-
"total_flos": 0,
|
| 40 |
"train_batch_size": 64,
|
| 41 |
"trial_name": null,
|
| 42 |
"trial_params": {
|
|
|
|
| 1 |
{
|
| 2 |
"best_global_step": 39,
|
| 3 |
+
"best_metric": 0.6173285198555957,
|
| 4 |
"best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-39",
|
| 5 |
"epoch": 1.0,
|
| 6 |
"eval_steps": 500,
|
|
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2564102564102564,
|
| 14 |
+
"grad_norm": 1.6625864505767822,
|
| 15 |
+
"learning_rate": 9.487179487179487e-05,
|
| 16 |
+
"loss": 0.696,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5128205128205128,
|
| 21 |
+
"grad_norm": 2.0310187339782715,
|
| 22 |
+
"learning_rate": 8.974358974358975e-05,
|
| 23 |
+
"loss": 0.6793,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7692307692307693,
|
| 28 |
+
"grad_norm": 4.6874542236328125,
|
| 29 |
+
"learning_rate": 8.461538461538461e-05,
|
| 30 |
+
"loss": 0.6504,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
{
|
| 34 |
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.6173285198555957,
|
| 36 |
+
"eval_loss": 0.635858952999115,
|
| 37 |
+
"eval_runtime": 0.6367,
|
| 38 |
+
"eval_samples_per_second": 435.081,
|
| 39 |
+
"eval_steps_per_second": 14.136,
|
| 40 |
"step": 39
|
| 41 |
}
|
| 42 |
],
|
| 43 |
+
"logging_steps": 10,
|
| 44 |
"max_steps": 195,
|
| 45 |
"num_input_tokens_seen": 0,
|
| 46 |
"num_train_epochs": 5,
|
|
|
|
| 57 |
"attributes": {}
|
| 58 |
}
|
| 59 |
},
|
| 60 |
+
"total_flos": 194932403139840.0,
|
| 61 |
"train_batch_size": 64,
|
| 62 |
"trial_name": null,
|
| 63 |
"trial_params": {
|
run-1/checkpoint-39/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:ae96125486481670db20065f4109e420c062152dc014578dda8c216f7705ceba
|
| 3 |
+
size 5368
|
run-1/checkpoint-78/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 437958648
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6d0ef39d6541dd1c5ccf5898ba411fc412bc3cd59054fe9e43b414186cedc079
|
| 3 |
size 437958648
|
run-1/checkpoint-78/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 876038394
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:108f1d7db984131dac0bd5fc4638a9596f3439a893c9b1d10ef16e23c7c30c39
|
| 3 |
size 876038394
|
run-1/checkpoint-78/trainer_state.json
CHANGED
|
@@ -9,26 +9,75 @@
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
{
|
| 13 |
"epoch": 1.0,
|
| 14 |
-
"eval_accuracy": 0.
|
| 15 |
-
"eval_loss": 0.
|
| 16 |
-
"eval_runtime": 0.
|
| 17 |
-
"eval_samples_per_second":
|
| 18 |
-
"eval_steps_per_second": 14.
|
| 19 |
"step": 39
|
| 20 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
{
|
| 22 |
"epoch": 2.0,
|
| 23 |
"eval_accuracy": 0.6895306859205776,
|
| 24 |
-
"eval_loss": 0.
|
| 25 |
-
"eval_runtime": 0.
|
| 26 |
-
"eval_samples_per_second":
|
| 27 |
-
"eval_steps_per_second": 14.
|
| 28 |
"step": 78
|
| 29 |
}
|
| 30 |
],
|
| 31 |
-
"logging_steps":
|
| 32 |
"max_steps": 195,
|
| 33 |
"num_input_tokens_seen": 0,
|
| 34 |
"num_train_epochs": 5,
|
|
@@ -45,7 +94,7 @@
|
|
| 45 |
"attributes": {}
|
| 46 |
}
|
| 47 |
},
|
| 48 |
-
"total_flos": 0,
|
| 49 |
"train_batch_size": 64,
|
| 50 |
"trial_name": null,
|
| 51 |
"trial_params": {
|
|
|
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
| 11 |
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.2564102564102564,
|
| 14 |
+
"grad_norm": 1.6625864505767822,
|
| 15 |
+
"learning_rate": 9.487179487179487e-05,
|
| 16 |
+
"loss": 0.696,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.5128205128205128,
|
| 21 |
+
"grad_norm": 2.0310187339782715,
|
| 22 |
+
"learning_rate": 8.974358974358975e-05,
|
| 23 |
+
"loss": 0.6793,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.7692307692307693,
|
| 28 |
+
"grad_norm": 4.6874542236328125,
|
| 29 |
+
"learning_rate": 8.461538461538461e-05,
|
| 30 |
+
"loss": 0.6504,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
{
|
| 34 |
"epoch": 1.0,
|
| 35 |
+
"eval_accuracy": 0.6173285198555957,
|
| 36 |
+
"eval_loss": 0.635858952999115,
|
| 37 |
+
"eval_runtime": 0.6367,
|
| 38 |
+
"eval_samples_per_second": 435.081,
|
| 39 |
+
"eval_steps_per_second": 14.136,
|
| 40 |
"step": 39
|
| 41 |
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.0256410256410255,
|
| 44 |
+
"grad_norm": 2.9923806190490723,
|
| 45 |
+
"learning_rate": 7.948717948717948e-05,
|
| 46 |
+
"loss": 0.6828,
|
| 47 |
+
"step": 40
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.282051282051282,
|
| 51 |
+
"grad_norm": 5.838254928588867,
|
| 52 |
+
"learning_rate": 7.435897435897436e-05,
|
| 53 |
+
"loss": 0.5479,
|
| 54 |
+
"step": 50
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.5384615384615383,
|
| 58 |
+
"grad_norm": 11.470205307006836,
|
| 59 |
+
"learning_rate": 6.923076923076924e-05,
|
| 60 |
+
"loss": 0.5428,
|
| 61 |
+
"step": 60
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.7948717948717947,
|
| 65 |
+
"grad_norm": 6.020153045654297,
|
| 66 |
+
"learning_rate": 6.410256410256412e-05,
|
| 67 |
+
"loss": 0.5377,
|
| 68 |
+
"step": 70
|
| 69 |
+
},
|
| 70 |
{
|
| 71 |
"epoch": 2.0,
|
| 72 |
"eval_accuracy": 0.6895306859205776,
|
| 73 |
+
"eval_loss": 0.655694842338562,
|
| 74 |
+
"eval_runtime": 0.6409,
|
| 75 |
+
"eval_samples_per_second": 432.172,
|
| 76 |
+
"eval_steps_per_second": 14.042,
|
| 77 |
"step": 78
|
| 78 |
}
|
| 79 |
],
|
| 80 |
+
"logging_steps": 10,
|
| 81 |
"max_steps": 195,
|
| 82 |
"num_input_tokens_seen": 0,
|
| 83 |
"num_train_epochs": 5,
|
|
|
|
| 94 |
"attributes": {}
|
| 95 |
}
|
| 96 |
},
|
| 97 |
+
"total_flos": 457788569664960.0,
|
| 98 |
"train_batch_size": 64,
|
| 99 |
"trial_name": null,
|
| 100 |
"trial_params": {
|
run-1/checkpoint-78/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:ae96125486481670db20065f4109e420c062152dc014578dda8c216f7705ceba
|
| 3 |
+
size 5368
|