Training in progress, step 2400, checkpoint
Browse files- checkpoint-2400/config.json +62 -0
- checkpoint-2400/model.safetensors +3 -0
- checkpoint-2400/optimizer.pt +3 -0
- checkpoint-2400/preprocessor_config.json +26 -0
- checkpoint-2400/rng_state.pth +3 -0
- checkpoint-2400/scheduler.pt +3 -0
- checkpoint-2400/trainer_state.json +369 -0
- checkpoint-2400/training_args.bin +3 -0
checkpoint-2400/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": "4.44.1",
|
| 60 |
+
"use_pretrained_backbone": true,
|
| 61 |
+
"use_timm_backbone": true
|
| 62 |
+
}
|
checkpoint-2400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f343f2c3bbbb5cbd7b846edaaaf1854c0ab157c7949d68645f255f1b85b703a3
|
| 3 |
+
size 166904424
|
checkpoint-2400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3982a7fd3619d2e52a1db4d995be5de04ff21daa88d93db0d58192567b81fee
|
| 3 |
+
size 1072390
|
checkpoint-2400/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-2400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:844ac620d7404e8ddc38dfb1c42150856a69e8fe97c49ee33b262c07b3a058f6
|
| 3 |
+
size 14308
|
checkpoint-2400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d035518c1b00b9312df70cd1276d2bded788dd12cbb3019f01dd19762f55df6f
|
| 3 |
+
size 1064
|
checkpoint-2400/trainer_state.json
ADDED
|
@@ -0,0 +1,369 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 29.62962962962963,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.6172839506172839,
|
| 13 |
+
"grad_norm": 14.113041877746582,
|
| 14 |
+
"learning_rate": 9.953000000000001e-06,
|
| 15 |
+
"loss": 9.3136,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 1.2345679012345678,
|
| 20 |
+
"grad_norm": 11.032143592834473,
|
| 21 |
+
"learning_rate": 9.903e-06,
|
| 22 |
+
"loss": 8.8439,
|
| 23 |
+
"step": 100
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.8518518518518519,
|
| 27 |
+
"grad_norm": 21.83379554748535,
|
| 28 |
+
"learning_rate": 9.853e-06,
|
| 29 |
+
"loss": 8.9582,
|
| 30 |
+
"step": 150
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 2.4691358024691357,
|
| 34 |
+
"grad_norm": 13.823728561401367,
|
| 35 |
+
"learning_rate": 9.803e-06,
|
| 36 |
+
"loss": 8.5429,
|
| 37 |
+
"step": 200
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 3.0864197530864197,
|
| 41 |
+
"grad_norm": 14.090177536010742,
|
| 42 |
+
"learning_rate": 9.753e-06,
|
| 43 |
+
"loss": 8.0873,
|
| 44 |
+
"step": 250
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 3.7037037037037037,
|
| 48 |
+
"grad_norm": 16.695327758789062,
|
| 49 |
+
"learning_rate": 9.703000000000002e-06,
|
| 50 |
+
"loss": 7.5718,
|
| 51 |
+
"step": 300
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 4.320987654320987,
|
| 55 |
+
"grad_norm": 12.39268970489502,
|
| 56 |
+
"learning_rate": 9.653e-06,
|
| 57 |
+
"loss": 7.2107,
|
| 58 |
+
"step": 350
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 4.938271604938271,
|
| 62 |
+
"grad_norm": 20.64848518371582,
|
| 63 |
+
"learning_rate": 9.603000000000001e-06,
|
| 64 |
+
"loss": 6.633,
|
| 65 |
+
"step": 400
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 5.555555555555555,
|
| 69 |
+
"grad_norm": 10.930610656738281,
|
| 70 |
+
"learning_rate": 9.553000000000002e-06,
|
| 71 |
+
"loss": 6.3085,
|
| 72 |
+
"step": 450
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 6.172839506172839,
|
| 76 |
+
"grad_norm": 7.421260833740234,
|
| 77 |
+
"learning_rate": 9.503e-06,
|
| 78 |
+
"loss": 5.9761,
|
| 79 |
+
"step": 500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 6.790123456790123,
|
| 83 |
+
"grad_norm": 19.653493881225586,
|
| 84 |
+
"learning_rate": 9.453e-06,
|
| 85 |
+
"loss": 6.0252,
|
| 86 |
+
"step": 550
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 7.407407407407407,
|
| 90 |
+
"grad_norm": 10.195016860961914,
|
| 91 |
+
"learning_rate": 9.403000000000001e-06,
|
| 92 |
+
"loss": 5.9531,
|
| 93 |
+
"step": 600
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 8.024691358024691,
|
| 97 |
+
"grad_norm": 15.588345527648926,
|
| 98 |
+
"learning_rate": 9.353000000000002e-06,
|
| 99 |
+
"loss": 5.979,
|
| 100 |
+
"step": 650
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 8.641975308641975,
|
| 104 |
+
"grad_norm": 11.010184288024902,
|
| 105 |
+
"learning_rate": 9.303e-06,
|
| 106 |
+
"loss": 5.9684,
|
| 107 |
+
"step": 700
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 9.25925925925926,
|
| 111 |
+
"grad_norm": 12.536541938781738,
|
| 112 |
+
"learning_rate": 9.253000000000001e-06,
|
| 113 |
+
"loss": 6.0309,
|
| 114 |
+
"step": 750
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 9.876543209876543,
|
| 118 |
+
"grad_norm": 10.15280818939209,
|
| 119 |
+
"learning_rate": 9.203000000000002e-06,
|
| 120 |
+
"loss": 5.7873,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 10.493827160493828,
|
| 125 |
+
"grad_norm": 18.81814956665039,
|
| 126 |
+
"learning_rate": 9.153e-06,
|
| 127 |
+
"loss": 5.7782,
|
| 128 |
+
"step": 850
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 11.11111111111111,
|
| 132 |
+
"grad_norm": 21.824844360351562,
|
| 133 |
+
"learning_rate": 9.103e-06,
|
| 134 |
+
"loss": 5.9619,
|
| 135 |
+
"step": 900
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 11.728395061728396,
|
| 139 |
+
"grad_norm": 14.213790893554688,
|
| 140 |
+
"learning_rate": 9.053000000000001e-06,
|
| 141 |
+
"loss": 5.7755,
|
| 142 |
+
"step": 950
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 12.345679012345679,
|
| 146 |
+
"grad_norm": 16.542211532592773,
|
| 147 |
+
"learning_rate": 9.003e-06,
|
| 148 |
+
"loss": 5.837,
|
| 149 |
+
"step": 1000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 12.962962962962964,
|
| 153 |
+
"grad_norm": 20.188156127929688,
|
| 154 |
+
"learning_rate": 8.953e-06,
|
| 155 |
+
"loss": 5.7611,
|
| 156 |
+
"step": 1050
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 13.580246913580247,
|
| 160 |
+
"grad_norm": 14.349571228027344,
|
| 161 |
+
"learning_rate": 8.903000000000001e-06,
|
| 162 |
+
"loss": 5.8904,
|
| 163 |
+
"step": 1100
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 14.197530864197532,
|
| 167 |
+
"grad_norm": 22.795913696289062,
|
| 168 |
+
"learning_rate": 8.853e-06,
|
| 169 |
+
"loss": 5.7211,
|
| 170 |
+
"step": 1150
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 14.814814814814815,
|
| 174 |
+
"grad_norm": 10.970526695251465,
|
| 175 |
+
"learning_rate": 8.803e-06,
|
| 176 |
+
"loss": 5.7186,
|
| 177 |
+
"step": 1200
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 15.432098765432098,
|
| 181 |
+
"grad_norm": 22.462017059326172,
|
| 182 |
+
"learning_rate": 8.753e-06,
|
| 183 |
+
"loss": 5.6172,
|
| 184 |
+
"step": 1250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 16.049382716049383,
|
| 188 |
+
"grad_norm": 15.98877239227295,
|
| 189 |
+
"learning_rate": 8.703e-06,
|
| 190 |
+
"loss": 5.7045,
|
| 191 |
+
"step": 1300
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 16.666666666666668,
|
| 195 |
+
"grad_norm": 10.7304048538208,
|
| 196 |
+
"learning_rate": 8.653e-06,
|
| 197 |
+
"loss": 5.77,
|
| 198 |
+
"step": 1350
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 17.28395061728395,
|
| 202 |
+
"grad_norm": 14.929125785827637,
|
| 203 |
+
"learning_rate": 8.603e-06,
|
| 204 |
+
"loss": 5.6916,
|
| 205 |
+
"step": 1400
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 17.901234567901234,
|
| 209 |
+
"grad_norm": 12.337247848510742,
|
| 210 |
+
"learning_rate": 8.553000000000001e-06,
|
| 211 |
+
"loss": 5.6017,
|
| 212 |
+
"step": 1450
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 18.51851851851852,
|
| 216 |
+
"grad_norm": 10.826752662658691,
|
| 217 |
+
"learning_rate": 8.503e-06,
|
| 218 |
+
"loss": 5.5774,
|
| 219 |
+
"step": 1500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 19.135802469135804,
|
| 223 |
+
"grad_norm": 31.670007705688477,
|
| 224 |
+
"learning_rate": 8.453000000000002e-06,
|
| 225 |
+
"loss": 5.6931,
|
| 226 |
+
"step": 1550
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 19.753086419753085,
|
| 230 |
+
"grad_norm": 11.033102989196777,
|
| 231 |
+
"learning_rate": 8.403e-06,
|
| 232 |
+
"loss": 5.6504,
|
| 233 |
+
"step": 1600
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 20.37037037037037,
|
| 237 |
+
"grad_norm": 12.53508472442627,
|
| 238 |
+
"learning_rate": 8.353000000000001e-06,
|
| 239 |
+
"loss": 5.7015,
|
| 240 |
+
"step": 1650
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 20.987654320987655,
|
| 244 |
+
"grad_norm": 13.549042701721191,
|
| 245 |
+
"learning_rate": 8.304e-06,
|
| 246 |
+
"loss": 5.6826,
|
| 247 |
+
"step": 1700
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 21.604938271604937,
|
| 251 |
+
"grad_norm": 13.270482063293457,
|
| 252 |
+
"learning_rate": 8.254000000000001e-06,
|
| 253 |
+
"loss": 5.5371,
|
| 254 |
+
"step": 1750
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 22.22222222222222,
|
| 258 |
+
"grad_norm": 15.088618278503418,
|
| 259 |
+
"learning_rate": 8.204000000000001e-06,
|
| 260 |
+
"loss": 5.6817,
|
| 261 |
+
"step": 1800
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 22.839506172839506,
|
| 265 |
+
"grad_norm": 12.706061363220215,
|
| 266 |
+
"learning_rate": 8.154e-06,
|
| 267 |
+
"loss": 5.6142,
|
| 268 |
+
"step": 1850
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 23.45679012345679,
|
| 272 |
+
"grad_norm": 12.286702156066895,
|
| 273 |
+
"learning_rate": 8.104e-06,
|
| 274 |
+
"loss": 5.4426,
|
| 275 |
+
"step": 1900
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 24.074074074074073,
|
| 279 |
+
"grad_norm": 19.067840576171875,
|
| 280 |
+
"learning_rate": 8.054000000000001e-06,
|
| 281 |
+
"loss": 5.5586,
|
| 282 |
+
"step": 1950
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 24.691358024691358,
|
| 286 |
+
"grad_norm": 17.961570739746094,
|
| 287 |
+
"learning_rate": 8.004e-06,
|
| 288 |
+
"loss": 5.5784,
|
| 289 |
+
"step": 2000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 25.308641975308642,
|
| 293 |
+
"grad_norm": 15.893245697021484,
|
| 294 |
+
"learning_rate": 7.954e-06,
|
| 295 |
+
"loss": 5.4392,
|
| 296 |
+
"step": 2050
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 25.925925925925927,
|
| 300 |
+
"grad_norm": 20.282608032226562,
|
| 301 |
+
"learning_rate": 7.904000000000001e-06,
|
| 302 |
+
"loss": 5.6877,
|
| 303 |
+
"step": 2100
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 26.54320987654321,
|
| 307 |
+
"grad_norm": 10.545083045959473,
|
| 308 |
+
"learning_rate": 7.854e-06,
|
| 309 |
+
"loss": 5.5013,
|
| 310 |
+
"step": 2150
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 27.160493827160494,
|
| 314 |
+
"grad_norm": 14.949348449707031,
|
| 315 |
+
"learning_rate": 7.804e-06,
|
| 316 |
+
"loss": 5.5302,
|
| 317 |
+
"step": 2200
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 27.77777777777778,
|
| 321 |
+
"grad_norm": 12.412175178527832,
|
| 322 |
+
"learning_rate": 7.754e-06,
|
| 323 |
+
"loss": 5.4353,
|
| 324 |
+
"step": 2250
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 28.395061728395063,
|
| 328 |
+
"grad_norm": 45.30052185058594,
|
| 329 |
+
"learning_rate": 7.704000000000001e-06,
|
| 330 |
+
"loss": 5.4165,
|
| 331 |
+
"step": 2300
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 29.012345679012345,
|
| 335 |
+
"grad_norm": 17.286645889282227,
|
| 336 |
+
"learning_rate": 7.654e-06,
|
| 337 |
+
"loss": 5.5977,
|
| 338 |
+
"step": 2350
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 29.62962962962963,
|
| 342 |
+
"grad_norm": 19.336837768554688,
|
| 343 |
+
"learning_rate": 7.604e-06,
|
| 344 |
+
"loss": 5.546,
|
| 345 |
+
"step": 2400
|
| 346 |
+
}
|
| 347 |
+
],
|
| 348 |
+
"logging_steps": 50,
|
| 349 |
+
"max_steps": 10000,
|
| 350 |
+
"num_input_tokens_seen": 0,
|
| 351 |
+
"num_train_epochs": 124,
|
| 352 |
+
"save_steps": 100,
|
| 353 |
+
"stateful_callbacks": {
|
| 354 |
+
"TrainerControl": {
|
| 355 |
+
"args": {
|
| 356 |
+
"should_epoch_stop": false,
|
| 357 |
+
"should_evaluate": false,
|
| 358 |
+
"should_log": false,
|
| 359 |
+
"should_save": true,
|
| 360 |
+
"should_training_stop": false
|
| 361 |
+
},
|
| 362 |
+
"attributes": {}
|
| 363 |
+
}
|
| 364 |
+
},
|
| 365 |
+
"total_flos": 9.173835988992e+18,
|
| 366 |
+
"train_batch_size": 8,
|
| 367 |
+
"trial_name": null,
|
| 368 |
+
"trial_params": null
|
| 369 |
+
}
|
checkpoint-2400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e10f18946db6a2f229ca0327743a6277178ea5088c71de2a2cdecf2c028b988a
|
| 3 |
+
size 5240
|