Training in progress, step 3000, checkpoint
Browse files- checkpoint-3000/config.json +62 -0
- checkpoint-3000/model.safetensors +3 -0
- checkpoint-3000/optimizer.pt +3 -0
- checkpoint-3000/preprocessor_config.json +26 -0
- checkpoint-3000/rng_state.pth +3 -0
- checkpoint-3000/scheduler.pt +3 -0
- checkpoint-3000/trainer_state.json +483 -0
- checkpoint-3000/training_args.bin +3 -0
checkpoint-3000/config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/detr-resnet-50-dc5",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "relu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"DetrForObjectDetection"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"auxiliary_loss": false,
|
| 10 |
+
"backbone": "resnet50",
|
| 11 |
+
"backbone_config": null,
|
| 12 |
+
"backbone_kwargs": {
|
| 13 |
+
"in_chans": 3,
|
| 14 |
+
"out_indices": [
|
| 15 |
+
1,
|
| 16 |
+
2,
|
| 17 |
+
3,
|
| 18 |
+
4
|
| 19 |
+
],
|
| 20 |
+
"output_stride": 16
|
| 21 |
+
},
|
| 22 |
+
"bbox_cost": 5,
|
| 23 |
+
"bbox_loss_coefficient": 5,
|
| 24 |
+
"class_cost": 1,
|
| 25 |
+
"classifier_dropout": 0.0,
|
| 26 |
+
"d_model": 256,
|
| 27 |
+
"decoder_attention_heads": 8,
|
| 28 |
+
"decoder_ffn_dim": 2048,
|
| 29 |
+
"decoder_layerdrop": 0.0,
|
| 30 |
+
"decoder_layers": 6,
|
| 31 |
+
"dice_loss_coefficient": 1,
|
| 32 |
+
"dilation": true,
|
| 33 |
+
"dropout": 0.1,
|
| 34 |
+
"encoder_attention_heads": 8,
|
| 35 |
+
"encoder_ffn_dim": 2048,
|
| 36 |
+
"encoder_layerdrop": 0.0,
|
| 37 |
+
"encoder_layers": 6,
|
| 38 |
+
"eos_coefficient": 0.1,
|
| 39 |
+
"giou_cost": 2,
|
| 40 |
+
"giou_loss_coefficient": 2,
|
| 41 |
+
"id2label": {
|
| 42 |
+
"0": "segment"
|
| 43 |
+
},
|
| 44 |
+
"init_std": 0.02,
|
| 45 |
+
"init_xavier_std": 1.0,
|
| 46 |
+
"is_encoder_decoder": true,
|
| 47 |
+
"label2id": {
|
| 48 |
+
"segment": 0
|
| 49 |
+
},
|
| 50 |
+
"mask_loss_coefficient": 1,
|
| 51 |
+
"max_position_embeddings": 1024,
|
| 52 |
+
"model_type": "detr",
|
| 53 |
+
"num_channels": 3,
|
| 54 |
+
"num_hidden_layers": 6,
|
| 55 |
+
"num_queries": 500,
|
| 56 |
+
"position_embedding_type": "sine",
|
| 57 |
+
"scale_embedding": false,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.44.2",
|
| 60 |
+
"use_pretrained_backbone": true,
|
| 61 |
+
"use_timm_backbone": true
|
| 62 |
+
}
|
checkpoint-3000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d92a8e87b92d0999cbe56ef6a3f4713fb6ab1fe57a43be32ec780a898349f6c0
|
| 3 |
+
size 166904424
|
checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe1f560773c77d9706a301c79b3908c5776ef7a94f1cce6a489e90375f938fab
|
| 3 |
+
size 331310970
|
checkpoint-3000/preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_annotations": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_pad": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"format": "coco_detection",
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.485,
|
| 10 |
+
0.456,
|
| 11 |
+
0.406
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "DetrImageProcessor",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.229,
|
| 16 |
+
0.224,
|
| 17 |
+
0.225
|
| 18 |
+
],
|
| 19 |
+
"pad_size": null,
|
| 20 |
+
"resample": 2,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 1333,
|
| 24 |
+
"shortest_edge": 800
|
| 25 |
+
}
|
| 26 |
+
}
|
checkpoint-3000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:916221a5745e3dc06173e24c61a544ba420e8758b75810e78cc77631e1303311
|
| 3 |
+
size 14180
|
checkpoint-3000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:023a2404d4cce68b541ad40d3e3f4ceccb29f3f102e2389a6506d40608ce8078
|
| 3 |
+
size 1064
|
checkpoint-3000/trainer_state.json
ADDED
|
@@ -0,0 +1,483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 46.15384615384615,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 3000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.5384615384615383,
|
| 13 |
+
"grad_norm": 47.11796188354492,
|
| 14 |
+
"learning_rate": 9.990900000000001e-06,
|
| 15 |
+
"loss": 3.6644,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.5384615384615383,
|
| 20 |
+
"eval_loss": 2.4919605255126953,
|
| 21 |
+
"eval_runtime": 12.5517,
|
| 22 |
+
"eval_samples_per_second": 10.437,
|
| 23 |
+
"eval_steps_per_second": 1.354,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 3.076923076923077,
|
| 28 |
+
"grad_norm": 31.28130531311035,
|
| 29 |
+
"learning_rate": 9.980900000000001e-06,
|
| 30 |
+
"loss": 2.2347,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 3.076923076923077,
|
| 35 |
+
"eval_loss": 2.156316041946411,
|
| 36 |
+
"eval_runtime": 11.1792,
|
| 37 |
+
"eval_samples_per_second": 11.718,
|
| 38 |
+
"eval_steps_per_second": 1.521,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.615384615384615,
|
| 43 |
+
"grad_norm": 39.616390228271484,
|
| 44 |
+
"learning_rate": 9.970900000000001e-06,
|
| 45 |
+
"loss": 2.0254,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 4.615384615384615,
|
| 50 |
+
"eval_loss": 2.024153709411621,
|
| 51 |
+
"eval_runtime": 11.1934,
|
| 52 |
+
"eval_samples_per_second": 11.703,
|
| 53 |
+
"eval_steps_per_second": 1.519,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 6.153846153846154,
|
| 58 |
+
"grad_norm": 28.285825729370117,
|
| 59 |
+
"learning_rate": 9.960900000000001e-06,
|
| 60 |
+
"loss": 1.9361,
|
| 61 |
+
"step": 400
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 6.153846153846154,
|
| 65 |
+
"eval_loss": 1.9094743728637695,
|
| 66 |
+
"eval_runtime": 11.3855,
|
| 67 |
+
"eval_samples_per_second": 11.506,
|
| 68 |
+
"eval_steps_per_second": 1.493,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 7.6923076923076925,
|
| 73 |
+
"grad_norm": 34.14302062988281,
|
| 74 |
+
"learning_rate": 9.950900000000002e-06,
|
| 75 |
+
"loss": 1.8531,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 7.6923076923076925,
|
| 80 |
+
"eval_loss": 1.8729331493377686,
|
| 81 |
+
"eval_runtime": 11.2935,
|
| 82 |
+
"eval_samples_per_second": 11.6,
|
| 83 |
+
"eval_steps_per_second": 1.505,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 9.23076923076923,
|
| 88 |
+
"grad_norm": 39.09531784057617,
|
| 89 |
+
"learning_rate": 9.940900000000002e-06,
|
| 90 |
+
"loss": 1.7669,
|
| 91 |
+
"step": 600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 9.23076923076923,
|
| 95 |
+
"eval_loss": 1.831756830215454,
|
| 96 |
+
"eval_runtime": 11.0535,
|
| 97 |
+
"eval_samples_per_second": 11.851,
|
| 98 |
+
"eval_steps_per_second": 1.538,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 10.76923076923077,
|
| 103 |
+
"grad_norm": 93.24444580078125,
|
| 104 |
+
"learning_rate": 9.930900000000002e-06,
|
| 105 |
+
"loss": 1.7518,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 10.76923076923077,
|
| 110 |
+
"eval_loss": 1.7832175493240356,
|
| 111 |
+
"eval_runtime": 11.1684,
|
| 112 |
+
"eval_samples_per_second": 11.729,
|
| 113 |
+
"eval_steps_per_second": 1.522,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 12.307692307692308,
|
| 118 |
+
"grad_norm": 32.21013641357422,
|
| 119 |
+
"learning_rate": 9.920900000000002e-06,
|
| 120 |
+
"loss": 1.7149,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 12.307692307692308,
|
| 125 |
+
"eval_loss": 1.7581098079681396,
|
| 126 |
+
"eval_runtime": 11.101,
|
| 127 |
+
"eval_samples_per_second": 11.801,
|
| 128 |
+
"eval_steps_per_second": 1.531,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 13.846153846153847,
|
| 133 |
+
"grad_norm": 59.90657043457031,
|
| 134 |
+
"learning_rate": 9.9109e-06,
|
| 135 |
+
"loss": 1.6734,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 13.846153846153847,
|
| 140 |
+
"eval_loss": 1.7163844108581543,
|
| 141 |
+
"eval_runtime": 11.1167,
|
| 142 |
+
"eval_samples_per_second": 11.784,
|
| 143 |
+
"eval_steps_per_second": 1.529,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 15.384615384615385,
|
| 148 |
+
"grad_norm": 20.61592674255371,
|
| 149 |
+
"learning_rate": 9.9009e-06,
|
| 150 |
+
"loss": 1.6612,
|
| 151 |
+
"step": 1000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 15.384615384615385,
|
| 155 |
+
"eval_loss": 1.6949567794799805,
|
| 156 |
+
"eval_runtime": 11.0663,
|
| 157 |
+
"eval_samples_per_second": 11.838,
|
| 158 |
+
"eval_steps_per_second": 1.536,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 16.923076923076923,
|
| 163 |
+
"grad_norm": 17.60099220275879,
|
| 164 |
+
"learning_rate": 9.8909e-06,
|
| 165 |
+
"loss": 1.6199,
|
| 166 |
+
"step": 1100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 16.923076923076923,
|
| 170 |
+
"eval_loss": 1.6769332885742188,
|
| 171 |
+
"eval_runtime": 11.0531,
|
| 172 |
+
"eval_samples_per_second": 11.852,
|
| 173 |
+
"eval_steps_per_second": 1.538,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 18.46153846153846,
|
| 178 |
+
"grad_norm": 20.802692413330078,
|
| 179 |
+
"learning_rate": 9.8809e-06,
|
| 180 |
+
"loss": 1.6008,
|
| 181 |
+
"step": 1200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 18.46153846153846,
|
| 185 |
+
"eval_loss": 1.6524990797042847,
|
| 186 |
+
"eval_runtime": 11.0831,
|
| 187 |
+
"eval_samples_per_second": 11.82,
|
| 188 |
+
"eval_steps_per_second": 1.534,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 20.0,
|
| 193 |
+
"grad_norm": 21.809823989868164,
|
| 194 |
+
"learning_rate": 9.8709e-06,
|
| 195 |
+
"loss": 1.5812,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 20.0,
|
| 200 |
+
"eval_loss": 1.6428295373916626,
|
| 201 |
+
"eval_runtime": 11.1093,
|
| 202 |
+
"eval_samples_per_second": 11.792,
|
| 203 |
+
"eval_steps_per_second": 1.53,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 21.53846153846154,
|
| 208 |
+
"grad_norm": 46.8908576965332,
|
| 209 |
+
"learning_rate": 9.8609e-06,
|
| 210 |
+
"loss": 1.5419,
|
| 211 |
+
"step": 1400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 21.53846153846154,
|
| 215 |
+
"eval_loss": 1.6006404161453247,
|
| 216 |
+
"eval_runtime": 11.2393,
|
| 217 |
+
"eval_samples_per_second": 11.655,
|
| 218 |
+
"eval_steps_per_second": 1.513,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 23.076923076923077,
|
| 223 |
+
"grad_norm": 27.15238380432129,
|
| 224 |
+
"learning_rate": 9.8509e-06,
|
| 225 |
+
"loss": 1.5374,
|
| 226 |
+
"step": 1500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 23.076923076923077,
|
| 230 |
+
"eval_loss": 1.5862094163894653,
|
| 231 |
+
"eval_runtime": 11.1815,
|
| 232 |
+
"eval_samples_per_second": 11.716,
|
| 233 |
+
"eval_steps_per_second": 1.52,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 24.615384615384617,
|
| 238 |
+
"grad_norm": 40.26778030395508,
|
| 239 |
+
"learning_rate": 9.840900000000001e-06,
|
| 240 |
+
"loss": 1.4923,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 24.615384615384617,
|
| 245 |
+
"eval_loss": 1.576373815536499,
|
| 246 |
+
"eval_runtime": 11.1215,
|
| 247 |
+
"eval_samples_per_second": 11.779,
|
| 248 |
+
"eval_steps_per_second": 1.529,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 26.153846153846153,
|
| 253 |
+
"grad_norm": 35.266971588134766,
|
| 254 |
+
"learning_rate": 9.830900000000001e-06,
|
| 255 |
+
"loss": 1.4989,
|
| 256 |
+
"step": 1700
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 26.153846153846153,
|
| 260 |
+
"eval_loss": 1.5671430826187134,
|
| 261 |
+
"eval_runtime": 11.1873,
|
| 262 |
+
"eval_samples_per_second": 11.71,
|
| 263 |
+
"eval_steps_per_second": 1.52,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 27.692307692307693,
|
| 268 |
+
"grad_norm": 26.813480377197266,
|
| 269 |
+
"learning_rate": 9.820900000000001e-06,
|
| 270 |
+
"loss": 1.4711,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 27.692307692307693,
|
| 275 |
+
"eval_loss": 1.522908329963684,
|
| 276 |
+
"eval_runtime": 11.2106,
|
| 277 |
+
"eval_samples_per_second": 11.685,
|
| 278 |
+
"eval_steps_per_second": 1.516,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 29.23076923076923,
|
| 283 |
+
"grad_norm": 24.576723098754883,
|
| 284 |
+
"learning_rate": 9.810900000000001e-06,
|
| 285 |
+
"loss": 1.4421,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 29.23076923076923,
|
| 290 |
+
"eval_loss": 1.5039104223251343,
|
| 291 |
+
"eval_runtime": 11.257,
|
| 292 |
+
"eval_samples_per_second": 11.637,
|
| 293 |
+
"eval_steps_per_second": 1.51,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 30.76923076923077,
|
| 298 |
+
"grad_norm": 28.480438232421875,
|
| 299 |
+
"learning_rate": 9.800900000000001e-06,
|
| 300 |
+
"loss": 1.4347,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 30.76923076923077,
|
| 305 |
+
"eval_loss": 1.5123459100723267,
|
| 306 |
+
"eval_runtime": 11.187,
|
| 307 |
+
"eval_samples_per_second": 11.71,
|
| 308 |
+
"eval_steps_per_second": 1.52,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 32.30769230769231,
|
| 313 |
+
"grad_norm": 56.582088470458984,
|
| 314 |
+
"learning_rate": 9.790900000000001e-06,
|
| 315 |
+
"loss": 1.4212,
|
| 316 |
+
"step": 2100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 32.30769230769231,
|
| 320 |
+
"eval_loss": 1.481844425201416,
|
| 321 |
+
"eval_runtime": 11.2075,
|
| 322 |
+
"eval_samples_per_second": 11.689,
|
| 323 |
+
"eval_steps_per_second": 1.517,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 33.84615384615385,
|
| 328 |
+
"grad_norm": 38.5254020690918,
|
| 329 |
+
"learning_rate": 9.780900000000002e-06,
|
| 330 |
+
"loss": 1.3908,
|
| 331 |
+
"step": 2200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 33.84615384615385,
|
| 335 |
+
"eval_loss": 1.4529048204421997,
|
| 336 |
+
"eval_runtime": 11.197,
|
| 337 |
+
"eval_samples_per_second": 11.7,
|
| 338 |
+
"eval_steps_per_second": 1.518,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 35.38461538461539,
|
| 343 |
+
"grad_norm": 44.74857711791992,
|
| 344 |
+
"learning_rate": 9.770900000000002e-06,
|
| 345 |
+
"loss": 1.3734,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 35.38461538461539,
|
| 350 |
+
"eval_loss": 1.4617427587509155,
|
| 351 |
+
"eval_runtime": 11.1235,
|
| 352 |
+
"eval_samples_per_second": 11.777,
|
| 353 |
+
"eval_steps_per_second": 1.528,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 36.92307692307692,
|
| 358 |
+
"grad_norm": 28.926782608032227,
|
| 359 |
+
"learning_rate": 9.760900000000002e-06,
|
| 360 |
+
"loss": 1.365,
|
| 361 |
+
"step": 2400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 36.92307692307692,
|
| 365 |
+
"eval_loss": 1.4297789335250854,
|
| 366 |
+
"eval_runtime": 11.3007,
|
| 367 |
+
"eval_samples_per_second": 11.592,
|
| 368 |
+
"eval_steps_per_second": 1.504,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 38.46153846153846,
|
| 373 |
+
"grad_norm": 27.750213623046875,
|
| 374 |
+
"learning_rate": 9.7509e-06,
|
| 375 |
+
"loss": 1.3306,
|
| 376 |
+
"step": 2500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 38.46153846153846,
|
| 380 |
+
"eval_loss": 1.4345914125442505,
|
| 381 |
+
"eval_runtime": 11.2795,
|
| 382 |
+
"eval_samples_per_second": 11.614,
|
| 383 |
+
"eval_steps_per_second": 1.507,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 40.0,
|
| 388 |
+
"grad_norm": 35.288352966308594,
|
| 389 |
+
"learning_rate": 9.7409e-06,
|
| 390 |
+
"loss": 1.3677,
|
| 391 |
+
"step": 2600
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 40.0,
|
| 395 |
+
"eval_loss": 1.447089433670044,
|
| 396 |
+
"eval_runtime": 11.1366,
|
| 397 |
+
"eval_samples_per_second": 11.763,
|
| 398 |
+
"eval_steps_per_second": 1.527,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 41.53846153846154,
|
| 403 |
+
"grad_norm": 65.49736022949219,
|
| 404 |
+
"learning_rate": 9.7309e-06,
|
| 405 |
+
"loss": 1.3453,
|
| 406 |
+
"step": 2700
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 41.53846153846154,
|
| 410 |
+
"eval_loss": 1.405300259590149,
|
| 411 |
+
"eval_runtime": 11.1549,
|
| 412 |
+
"eval_samples_per_second": 11.744,
|
| 413 |
+
"eval_steps_per_second": 1.524,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 43.07692307692308,
|
| 418 |
+
"grad_norm": 24.333518981933594,
|
| 419 |
+
"learning_rate": 9.7209e-06,
|
| 420 |
+
"loss": 1.3206,
|
| 421 |
+
"step": 2800
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 43.07692307692308,
|
| 425 |
+
"eval_loss": 1.4218717813491821,
|
| 426 |
+
"eval_runtime": 11.3113,
|
| 427 |
+
"eval_samples_per_second": 11.581,
|
| 428 |
+
"eval_steps_per_second": 1.503,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 44.61538461538461,
|
| 433 |
+
"grad_norm": 45.50777816772461,
|
| 434 |
+
"learning_rate": 9.7109e-06,
|
| 435 |
+
"loss": 1.3363,
|
| 436 |
+
"step": 2900
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 44.61538461538461,
|
| 440 |
+
"eval_loss": 1.4220006465911865,
|
| 441 |
+
"eval_runtime": 11.156,
|
| 442 |
+
"eval_samples_per_second": 11.743,
|
| 443 |
+
"eval_steps_per_second": 1.524,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 46.15384615384615,
|
| 448 |
+
"grad_norm": 25.898344039916992,
|
| 449 |
+
"learning_rate": 9.7009e-06,
|
| 450 |
+
"loss": 1.2995,
|
| 451 |
+
"step": 3000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 46.15384615384615,
|
| 455 |
+
"eval_loss": 1.3942431211471558,
|
| 456 |
+
"eval_runtime": 11.2282,
|
| 457 |
+
"eval_samples_per_second": 11.667,
|
| 458 |
+
"eval_steps_per_second": 1.514,
|
| 459 |
+
"step": 3000
|
| 460 |
+
}
|
| 461 |
+
],
|
| 462 |
+
"logging_steps": 100,
|
| 463 |
+
"max_steps": 100000,
|
| 464 |
+
"num_input_tokens_seen": 0,
|
| 465 |
+
"num_train_epochs": 1539,
|
| 466 |
+
"save_steps": 500,
|
| 467 |
+
"stateful_callbacks": {
|
| 468 |
+
"TrainerControl": {
|
| 469 |
+
"args": {
|
| 470 |
+
"should_epoch_stop": false,
|
| 471 |
+
"should_evaluate": false,
|
| 472 |
+
"should_log": false,
|
| 473 |
+
"should_save": true,
|
| 474 |
+
"should_training_stop": false
|
| 475 |
+
},
|
| 476 |
+
"attributes": {}
|
| 477 |
+
}
|
| 478 |
+
},
|
| 479 |
+
"total_flos": 1.146729498624e+19,
|
| 480 |
+
"train_batch_size": 8,
|
| 481 |
+
"trial_name": null,
|
| 482 |
+
"trial_params": null
|
| 483 |
+
}
|
checkpoint-3000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ad9d755c74ae76083891287d009fdddb96b730c67f38d8947352435e2637ed7
|
| 3 |
+
size 5304
|