Training in progress, step 2500, checkpoint
Browse files- checkpoint-2500/config.json +62 -0
- checkpoint-2500/model.safetensors +3 -0
- checkpoint-2500/optimizer.pt +3 -0
- checkpoint-2500/preprocessor_config.json +26 -0
- checkpoint-2500/rng_state.pth +3 -0
- checkpoint-2500/scheduler.pt +3 -0
- checkpoint-2500/trainer_state.json +408 -0
- checkpoint-2500/training_args.bin +3 -0
checkpoint-2500/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-2500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:092ceeef925aaea8feed76be5d3c5832939384af34ee5831ee10adda94eb8199
|
| 3 |
+
size 166904424
|
checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e53bacc566f99d4a919551e8f40ea5b0f1c30ac6c6dfb5ed572c4b74c26dc51c
|
| 3 |
+
size 331310970
|
checkpoint-2500/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-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:978669f998784777cd414a0f2bf45babc66b4a82678d001684f2d64ba1d7695b
|
| 3 |
+
size 14244
|
checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a516174e5b2d60e59edc248e5b54c02e68800246046cb89ccafc4223f2a6cf
|
| 3 |
+
size 1064
|
checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,408 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 12.820512820512821,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 2500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.5128205128205128,
|
| 13 |
+
"grad_norm": 485.6934509277344,
|
| 14 |
+
"learning_rate": 9.9907e-06,
|
| 15 |
+
"loss": 3.7897,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5128205128205128,
|
| 20 |
+
"eval_loss": 2.913217067718506,
|
| 21 |
+
"eval_runtime": 36.1065,
|
| 22 |
+
"eval_samples_per_second": 10.884,
|
| 23 |
+
"eval_steps_per_second": 1.385,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.0256410256410255,
|
| 28 |
+
"grad_norm": 35.502872467041016,
|
| 29 |
+
"learning_rate": 9.980700000000001e-06,
|
| 30 |
+
"loss": 2.6449,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0256410256410255,
|
| 35 |
+
"eval_loss": 2.1936488151550293,
|
| 36 |
+
"eval_runtime": 35.8618,
|
| 37 |
+
"eval_samples_per_second": 10.959,
|
| 38 |
+
"eval_steps_per_second": 1.394,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.5384615384615383,
|
| 43 |
+
"grad_norm": 44.5572624206543,
|
| 44 |
+
"learning_rate": 9.970700000000001e-06,
|
| 45 |
+
"loss": 2.123,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.5384615384615383,
|
| 50 |
+
"eval_loss": 1.9975601434707642,
|
| 51 |
+
"eval_runtime": 36.0033,
|
| 52 |
+
"eval_samples_per_second": 10.916,
|
| 53 |
+
"eval_steps_per_second": 1.389,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.051282051282051,
|
| 58 |
+
"grad_norm": 91.06848907470703,
|
| 59 |
+
"learning_rate": 9.960700000000001e-06,
|
| 60 |
+
"loss": 1.9616,
|
| 61 |
+
"step": 400
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.051282051282051,
|
| 65 |
+
"eval_loss": 1.9457911252975464,
|
| 66 |
+
"eval_runtime": 35.8591,
|
| 67 |
+
"eval_samples_per_second": 10.96,
|
| 68 |
+
"eval_steps_per_second": 1.394,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.564102564102564,
|
| 73 |
+
"grad_norm": 62.52458953857422,
|
| 74 |
+
"learning_rate": 9.950700000000001e-06,
|
| 75 |
+
"loss": 1.9329,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.564102564102564,
|
| 80 |
+
"eval_loss": 1.8983820676803589,
|
| 81 |
+
"eval_runtime": 35.7607,
|
| 82 |
+
"eval_samples_per_second": 10.99,
|
| 83 |
+
"eval_steps_per_second": 1.398,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.076923076923077,
|
| 88 |
+
"grad_norm": 46.58191680908203,
|
| 89 |
+
"learning_rate": 9.940700000000001e-06,
|
| 90 |
+
"loss": 1.8998,
|
| 91 |
+
"step": 600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 3.076923076923077,
|
| 95 |
+
"eval_loss": 1.8464109897613525,
|
| 96 |
+
"eval_runtime": 35.5376,
|
| 97 |
+
"eval_samples_per_second": 11.059,
|
| 98 |
+
"eval_steps_per_second": 1.407,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.58974358974359,
|
| 103 |
+
"grad_norm": 43.859432220458984,
|
| 104 |
+
"learning_rate": 9.930700000000001e-06,
|
| 105 |
+
"loss": 1.8632,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.58974358974359,
|
| 110 |
+
"eval_loss": 1.8351906538009644,
|
| 111 |
+
"eval_runtime": 35.8606,
|
| 112 |
+
"eval_samples_per_second": 10.959,
|
| 113 |
+
"eval_steps_per_second": 1.394,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.102564102564102,
|
| 118 |
+
"grad_norm": 36.12472152709961,
|
| 119 |
+
"learning_rate": 9.920700000000001e-06,
|
| 120 |
+
"loss": 1.8202,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.102564102564102,
|
| 125 |
+
"eval_loss": 1.7837625741958618,
|
| 126 |
+
"eval_runtime": 35.8551,
|
| 127 |
+
"eval_samples_per_second": 10.961,
|
| 128 |
+
"eval_steps_per_second": 1.395,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.615384615384615,
|
| 133 |
+
"grad_norm": 56.74811553955078,
|
| 134 |
+
"learning_rate": 9.910700000000002e-06,
|
| 135 |
+
"loss": 1.7767,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.615384615384615,
|
| 140 |
+
"eval_loss": 1.777076005935669,
|
| 141 |
+
"eval_runtime": 35.652,
|
| 142 |
+
"eval_samples_per_second": 11.023,
|
| 143 |
+
"eval_steps_per_second": 1.402,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 5.128205128205128,
|
| 148 |
+
"grad_norm": 97.7017822265625,
|
| 149 |
+
"learning_rate": 9.900700000000002e-06,
|
| 150 |
+
"loss": 1.7757,
|
| 151 |
+
"step": 1000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 5.128205128205128,
|
| 155 |
+
"eval_loss": 1.7516826391220093,
|
| 156 |
+
"eval_runtime": 35.6867,
|
| 157 |
+
"eval_samples_per_second": 11.013,
|
| 158 |
+
"eval_steps_per_second": 1.401,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.641025641025641,
|
| 163 |
+
"grad_norm": 21.942626953125,
|
| 164 |
+
"learning_rate": 9.8907e-06,
|
| 165 |
+
"loss": 1.7592,
|
| 166 |
+
"step": 1100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 5.641025641025641,
|
| 170 |
+
"eval_loss": 1.7459185123443604,
|
| 171 |
+
"eval_runtime": 35.7882,
|
| 172 |
+
"eval_samples_per_second": 10.981,
|
| 173 |
+
"eval_steps_per_second": 1.397,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 6.153846153846154,
|
| 178 |
+
"grad_norm": 31.696691513061523,
|
| 179 |
+
"learning_rate": 9.8807e-06,
|
| 180 |
+
"loss": 1.8098,
|
| 181 |
+
"step": 1200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 6.153846153846154,
|
| 185 |
+
"eval_loss": 1.7705851793289185,
|
| 186 |
+
"eval_runtime": 35.6241,
|
| 187 |
+
"eval_samples_per_second": 11.032,
|
| 188 |
+
"eval_steps_per_second": 1.404,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.666666666666667,
|
| 193 |
+
"grad_norm": 69.51777648925781,
|
| 194 |
+
"learning_rate": 9.8707e-06,
|
| 195 |
+
"loss": 1.6903,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 6.666666666666667,
|
| 200 |
+
"eval_loss": 1.717505693435669,
|
| 201 |
+
"eval_runtime": 35.7343,
|
| 202 |
+
"eval_samples_per_second": 10.998,
|
| 203 |
+
"eval_steps_per_second": 1.399,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 7.17948717948718,
|
| 208 |
+
"grad_norm": 159.8116455078125,
|
| 209 |
+
"learning_rate": 9.8607e-06,
|
| 210 |
+
"loss": 1.7428,
|
| 211 |
+
"step": 1400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 7.17948717948718,
|
| 215 |
+
"eval_loss": 1.7039239406585693,
|
| 216 |
+
"eval_runtime": 35.6477,
|
| 217 |
+
"eval_samples_per_second": 11.025,
|
| 218 |
+
"eval_steps_per_second": 1.403,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.6923076923076925,
|
| 223 |
+
"grad_norm": 52.08290100097656,
|
| 224 |
+
"learning_rate": 9.8507e-06,
|
| 225 |
+
"loss": 1.6913,
|
| 226 |
+
"step": 1500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.6923076923076925,
|
| 230 |
+
"eval_loss": 1.6931686401367188,
|
| 231 |
+
"eval_runtime": 35.6627,
|
| 232 |
+
"eval_samples_per_second": 11.02,
|
| 233 |
+
"eval_steps_per_second": 1.402,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 8.205128205128204,
|
| 238 |
+
"grad_norm": 67.04603576660156,
|
| 239 |
+
"learning_rate": 9.8407e-06,
|
| 240 |
+
"loss": 1.7072,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.205128205128204,
|
| 245 |
+
"eval_loss": 1.6624616384506226,
|
| 246 |
+
"eval_runtime": 35.7439,
|
| 247 |
+
"eval_samples_per_second": 10.995,
|
| 248 |
+
"eval_steps_per_second": 1.399,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 8.717948717948717,
|
| 253 |
+
"grad_norm": 22.715839385986328,
|
| 254 |
+
"learning_rate": 9.8307e-06,
|
| 255 |
+
"loss": 1.6593,
|
| 256 |
+
"step": 1700
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 8.717948717948717,
|
| 260 |
+
"eval_loss": 1.6604528427124023,
|
| 261 |
+
"eval_runtime": 35.8353,
|
| 262 |
+
"eval_samples_per_second": 10.967,
|
| 263 |
+
"eval_steps_per_second": 1.395,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 9.23076923076923,
|
| 268 |
+
"grad_norm": 36.652496337890625,
|
| 269 |
+
"learning_rate": 9.8207e-06,
|
| 270 |
+
"loss": 1.7015,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 9.23076923076923,
|
| 275 |
+
"eval_loss": 1.691542148590088,
|
| 276 |
+
"eval_runtime": 35.7641,
|
| 277 |
+
"eval_samples_per_second": 10.989,
|
| 278 |
+
"eval_steps_per_second": 1.398,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 9.743589743589745,
|
| 283 |
+
"grad_norm": 55.04361343383789,
|
| 284 |
+
"learning_rate": 9.8107e-06,
|
| 285 |
+
"loss": 1.6452,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 9.743589743589745,
|
| 290 |
+
"eval_loss": 1.64271080493927,
|
| 291 |
+
"eval_runtime": 35.6018,
|
| 292 |
+
"eval_samples_per_second": 11.039,
|
| 293 |
+
"eval_steps_per_second": 1.404,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 10.256410256410255,
|
| 298 |
+
"grad_norm": 48.84671401977539,
|
| 299 |
+
"learning_rate": 9.800700000000001e-06,
|
| 300 |
+
"loss": 1.6642,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 10.256410256410255,
|
| 305 |
+
"eval_loss": 1.6221907138824463,
|
| 306 |
+
"eval_runtime": 35.7515,
|
| 307 |
+
"eval_samples_per_second": 10.993,
|
| 308 |
+
"eval_steps_per_second": 1.399,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 10.76923076923077,
|
| 313 |
+
"grad_norm": 32.97844314575195,
|
| 314 |
+
"learning_rate": 9.790700000000001e-06,
|
| 315 |
+
"loss": 1.6049,
|
| 316 |
+
"step": 2100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 10.76923076923077,
|
| 320 |
+
"eval_loss": 1.6168797016143799,
|
| 321 |
+
"eval_runtime": 36.4363,
|
| 322 |
+
"eval_samples_per_second": 10.786,
|
| 323 |
+
"eval_steps_per_second": 1.372,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 11.282051282051283,
|
| 328 |
+
"grad_norm": 28.999696731567383,
|
| 329 |
+
"learning_rate": 9.780700000000001e-06,
|
| 330 |
+
"loss": 1.6066,
|
| 331 |
+
"step": 2200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 11.282051282051283,
|
| 335 |
+
"eval_loss": 1.598867654800415,
|
| 336 |
+
"eval_runtime": 36.4424,
|
| 337 |
+
"eval_samples_per_second": 10.784,
|
| 338 |
+
"eval_steps_per_second": 1.372,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 11.794871794871796,
|
| 343 |
+
"grad_norm": 63.84739303588867,
|
| 344 |
+
"learning_rate": 9.770700000000001e-06,
|
| 345 |
+
"loss": 1.6018,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 11.794871794871796,
|
| 350 |
+
"eval_loss": 1.591909646987915,
|
| 351 |
+
"eval_runtime": 36.2873,
|
| 352 |
+
"eval_samples_per_second": 10.83,
|
| 353 |
+
"eval_steps_per_second": 1.378,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 12.307692307692308,
|
| 358 |
+
"grad_norm": 50.41542053222656,
|
| 359 |
+
"learning_rate": 9.760700000000001e-06,
|
| 360 |
+
"loss": 1.5905,
|
| 361 |
+
"step": 2400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 12.307692307692308,
|
| 365 |
+
"eval_loss": 1.5780647993087769,
|
| 366 |
+
"eval_runtime": 36.5696,
|
| 367 |
+
"eval_samples_per_second": 10.747,
|
| 368 |
+
"eval_steps_per_second": 1.367,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 12.820512820512821,
|
| 373 |
+
"grad_norm": 28.81470489501953,
|
| 374 |
+
"learning_rate": 9.750700000000001e-06,
|
| 375 |
+
"loss": 1.563,
|
| 376 |
+
"step": 2500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 12.820512820512821,
|
| 380 |
+
"eval_loss": 1.5548878908157349,
|
| 381 |
+
"eval_runtime": 36.2689,
|
| 382 |
+
"eval_samples_per_second": 10.836,
|
| 383 |
+
"eval_steps_per_second": 1.379,
|
| 384 |
+
"step": 2500
|
| 385 |
+
}
|
| 386 |
+
],
|
| 387 |
+
"logging_steps": 100,
|
| 388 |
+
"max_steps": 100000,
|
| 389 |
+
"num_input_tokens_seen": 0,
|
| 390 |
+
"num_train_epochs": 513,
|
| 391 |
+
"save_steps": 500,
|
| 392 |
+
"stateful_callbacks": {
|
| 393 |
+
"TrainerControl": {
|
| 394 |
+
"args": {
|
| 395 |
+
"should_epoch_stop": false,
|
| 396 |
+
"should_evaluate": false,
|
| 397 |
+
"should_log": false,
|
| 398 |
+
"should_save": true,
|
| 399 |
+
"should_training_stop": false
|
| 400 |
+
},
|
| 401 |
+
"attributes": {}
|
| 402 |
+
}
|
| 403 |
+
},
|
| 404 |
+
"total_flos": 9.5560791552e+18,
|
| 405 |
+
"train_batch_size": 8,
|
| 406 |
+
"trial_name": null,
|
| 407 |
+
"trial_params": null
|
| 408 |
+
}
|
checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e1ab50c89af47345b449e34818f6f00e03a868edf459f7a8b74e316d1f072ee
|
| 3 |
+
size 5368
|