Training in progress, step 2000, checkpoint
Browse files- checkpoint-2000/config.json +62 -0
- checkpoint-2000/model.safetensors +3 -0
- checkpoint-2000/optimizer.pt +3 -0
- checkpoint-2000/preprocessor_config.json +26 -0
- checkpoint-2000/rng_state.pth +3 -0
- checkpoint-2000/scheduler.pt +3 -0
- checkpoint-2000/trainer_state.json +633 -0
- checkpoint-2000/training_args.bin +3 -0
checkpoint-2000/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-2000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2682bef79edd2cb0324d2005739903917e5ddefdea11a570dcc906cac28e669c
|
| 3 |
+
size 166904424
|
checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb1226b0e585cf453a18b2151153550a5273ad46d1fd871fd5664fe8d9409e2c
|
| 3 |
+
size 331310970
|
checkpoint-2000/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-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:938681ee75e0d5d5b1a625181c315f670f0a0d88da807c182132419475c5b3cc
|
| 3 |
+
size 14308
|
checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0556d2d6acdaa1ec02cd8ece08ed0f3b287f6697445bce62ebcc60c830267098
|
| 3 |
+
size 1064
|
checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.76923076923077,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 2000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.7692307692307693,
|
| 13 |
+
"grad_norm": 97.95333099365234,
|
| 14 |
+
"learning_rate": 4.9978e-05,
|
| 15 |
+
"loss": 5.4721,
|
| 16 |
+
"step": 50
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.7692307692307693,
|
| 20 |
+
"eval_loss": 5.876021385192871,
|
| 21 |
+
"eval_runtime": 12.8977,
|
| 22 |
+
"eval_samples_per_second": 10.157,
|
| 23 |
+
"eval_steps_per_second": 1.318,
|
| 24 |
+
"step": 50
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.5384615384615383,
|
| 28 |
+
"grad_norm": 104.74186706542969,
|
| 29 |
+
"learning_rate": 4.99535e-05,
|
| 30 |
+
"loss": 3.089,
|
| 31 |
+
"step": 100
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.5384615384615383,
|
| 35 |
+
"eval_loss": 5.774240970611572,
|
| 36 |
+
"eval_runtime": 11.4924,
|
| 37 |
+
"eval_samples_per_second": 11.399,
|
| 38 |
+
"eval_steps_per_second": 1.479,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.3076923076923075,
|
| 43 |
+
"grad_norm": 41.090965270996094,
|
| 44 |
+
"learning_rate": 4.99285e-05,
|
| 45 |
+
"loss": 2.764,
|
| 46 |
+
"step": 150
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.3076923076923075,
|
| 50 |
+
"eval_loss": 5.597934722900391,
|
| 51 |
+
"eval_runtime": 11.4654,
|
| 52 |
+
"eval_samples_per_second": 11.426,
|
| 53 |
+
"eval_steps_per_second": 1.483,
|
| 54 |
+
"step": 150
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 3.076923076923077,
|
| 58 |
+
"grad_norm": 73.45726776123047,
|
| 59 |
+
"learning_rate": 4.99035e-05,
|
| 60 |
+
"loss": 2.5945,
|
| 61 |
+
"step": 200
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 3.076923076923077,
|
| 65 |
+
"eval_loss": 5.421833515167236,
|
| 66 |
+
"eval_runtime": 11.5159,
|
| 67 |
+
"eval_samples_per_second": 11.376,
|
| 68 |
+
"eval_steps_per_second": 1.476,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 3.8461538461538463,
|
| 73 |
+
"grad_norm": 71.80171203613281,
|
| 74 |
+
"learning_rate": 4.98785e-05,
|
| 75 |
+
"loss": 2.6367,
|
| 76 |
+
"step": 250
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 3.8461538461538463,
|
| 80 |
+
"eval_loss": 5.8073201179504395,
|
| 81 |
+
"eval_runtime": 11.5047,
|
| 82 |
+
"eval_samples_per_second": 11.387,
|
| 83 |
+
"eval_steps_per_second": 1.478,
|
| 84 |
+
"step": 250
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 4.615384615384615,
|
| 88 |
+
"grad_norm": 43.557945251464844,
|
| 89 |
+
"learning_rate": 4.98535e-05,
|
| 90 |
+
"loss": 2.5105,
|
| 91 |
+
"step": 300
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 4.615384615384615,
|
| 95 |
+
"eval_loss": 4.3725128173828125,
|
| 96 |
+
"eval_runtime": 11.497,
|
| 97 |
+
"eval_samples_per_second": 11.394,
|
| 98 |
+
"eval_steps_per_second": 1.479,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 5.384615384615385,
|
| 103 |
+
"grad_norm": 108.88764953613281,
|
| 104 |
+
"learning_rate": 4.98285e-05,
|
| 105 |
+
"loss": 2.5468,
|
| 106 |
+
"step": 350
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 5.384615384615385,
|
| 110 |
+
"eval_loss": 5.673581123352051,
|
| 111 |
+
"eval_runtime": 11.5715,
|
| 112 |
+
"eval_samples_per_second": 11.321,
|
| 113 |
+
"eval_steps_per_second": 1.469,
|
| 114 |
+
"step": 350
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 6.153846153846154,
|
| 118 |
+
"grad_norm": 83.45320129394531,
|
| 119 |
+
"learning_rate": 4.9803500000000005e-05,
|
| 120 |
+
"loss": 2.4749,
|
| 121 |
+
"step": 400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 6.153846153846154,
|
| 125 |
+
"eval_loss": 5.851593971252441,
|
| 126 |
+
"eval_runtime": 11.522,
|
| 127 |
+
"eval_samples_per_second": 11.37,
|
| 128 |
+
"eval_steps_per_second": 1.475,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 6.923076923076923,
|
| 133 |
+
"grad_norm": 68.41734313964844,
|
| 134 |
+
"learning_rate": 4.97785e-05,
|
| 135 |
+
"loss": 2.3658,
|
| 136 |
+
"step": 450
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 6.923076923076923,
|
| 140 |
+
"eval_loss": 5.2119598388671875,
|
| 141 |
+
"eval_runtime": 11.4672,
|
| 142 |
+
"eval_samples_per_second": 11.424,
|
| 143 |
+
"eval_steps_per_second": 1.482,
|
| 144 |
+
"step": 450
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 7.6923076923076925,
|
| 148 |
+
"grad_norm": 102.76841735839844,
|
| 149 |
+
"learning_rate": 4.9753500000000004e-05,
|
| 150 |
+
"loss": 2.5853,
|
| 151 |
+
"step": 500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 7.6923076923076925,
|
| 155 |
+
"eval_loss": 4.767831325531006,
|
| 156 |
+
"eval_runtime": 11.4763,
|
| 157 |
+
"eval_samples_per_second": 11.415,
|
| 158 |
+
"eval_steps_per_second": 1.481,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 8.461538461538462,
|
| 163 |
+
"grad_norm": 112.57891845703125,
|
| 164 |
+
"learning_rate": 4.97285e-05,
|
| 165 |
+
"loss": 2.3775,
|
| 166 |
+
"step": 550
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 8.461538461538462,
|
| 170 |
+
"eval_loss": 5.561651229858398,
|
| 171 |
+
"eval_runtime": 11.6114,
|
| 172 |
+
"eval_samples_per_second": 11.282,
|
| 173 |
+
"eval_steps_per_second": 1.464,
|
| 174 |
+
"step": 550
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 9.23076923076923,
|
| 178 |
+
"grad_norm": 69.39505004882812,
|
| 179 |
+
"learning_rate": 4.97035e-05,
|
| 180 |
+
"loss": 2.6571,
|
| 181 |
+
"step": 600
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 9.23076923076923,
|
| 185 |
+
"eval_loss": 4.059703350067139,
|
| 186 |
+
"eval_runtime": 11.3835,
|
| 187 |
+
"eval_samples_per_second": 11.508,
|
| 188 |
+
"eval_steps_per_second": 1.493,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 10.0,
|
| 193 |
+
"grad_norm": 54.98592758178711,
|
| 194 |
+
"learning_rate": 4.96785e-05,
|
| 195 |
+
"loss": 2.2724,
|
| 196 |
+
"step": 650
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 10.0,
|
| 200 |
+
"eval_loss": 4.133812427520752,
|
| 201 |
+
"eval_runtime": 11.5354,
|
| 202 |
+
"eval_samples_per_second": 11.356,
|
| 203 |
+
"eval_steps_per_second": 1.474,
|
| 204 |
+
"step": 650
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 10.76923076923077,
|
| 208 |
+
"grad_norm": 43.64970397949219,
|
| 209 |
+
"learning_rate": 4.96535e-05,
|
| 210 |
+
"loss": 2.2554,
|
| 211 |
+
"step": 700
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 10.76923076923077,
|
| 215 |
+
"eval_loss": 5.351332187652588,
|
| 216 |
+
"eval_runtime": 11.5138,
|
| 217 |
+
"eval_samples_per_second": 11.378,
|
| 218 |
+
"eval_steps_per_second": 1.476,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 11.538461538461538,
|
| 223 |
+
"grad_norm": 66.37532043457031,
|
| 224 |
+
"learning_rate": 4.96285e-05,
|
| 225 |
+
"loss": 2.3946,
|
| 226 |
+
"step": 750
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 11.538461538461538,
|
| 230 |
+
"eval_loss": 4.791417121887207,
|
| 231 |
+
"eval_runtime": 11.5206,
|
| 232 |
+
"eval_samples_per_second": 11.371,
|
| 233 |
+
"eval_steps_per_second": 1.476,
|
| 234 |
+
"step": 750
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 12.307692307692308,
|
| 238 |
+
"grad_norm": 155.59654235839844,
|
| 239 |
+
"learning_rate": 4.96035e-05,
|
| 240 |
+
"loss": 2.2003,
|
| 241 |
+
"step": 800
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 12.307692307692308,
|
| 245 |
+
"eval_loss": 5.445430278778076,
|
| 246 |
+
"eval_runtime": 11.6906,
|
| 247 |
+
"eval_samples_per_second": 11.206,
|
| 248 |
+
"eval_steps_per_second": 1.454,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 13.076923076923077,
|
| 253 |
+
"grad_norm": 64.81100463867188,
|
| 254 |
+
"learning_rate": 4.95785e-05,
|
| 255 |
+
"loss": 2.4835,
|
| 256 |
+
"step": 850
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 13.076923076923077,
|
| 260 |
+
"eval_loss": 4.8099870681762695,
|
| 261 |
+
"eval_runtime": 11.4569,
|
| 262 |
+
"eval_samples_per_second": 11.434,
|
| 263 |
+
"eval_steps_per_second": 1.484,
|
| 264 |
+
"step": 850
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 13.846153846153847,
|
| 268 |
+
"grad_norm": 36.99908447265625,
|
| 269 |
+
"learning_rate": 4.9553500000000006e-05,
|
| 270 |
+
"loss": 2.2851,
|
| 271 |
+
"step": 900
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 13.846153846153847,
|
| 275 |
+
"eval_loss": 4.230841636657715,
|
| 276 |
+
"eval_runtime": 11.4365,
|
| 277 |
+
"eval_samples_per_second": 11.455,
|
| 278 |
+
"eval_steps_per_second": 1.486,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 14.615384615384615,
|
| 283 |
+
"grad_norm": 59.919151306152344,
|
| 284 |
+
"learning_rate": 4.95285e-05,
|
| 285 |
+
"loss": 2.1306,
|
| 286 |
+
"step": 950
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 14.615384615384615,
|
| 290 |
+
"eval_loss": 5.253855228424072,
|
| 291 |
+
"eval_runtime": 11.6552,
|
| 292 |
+
"eval_samples_per_second": 11.24,
|
| 293 |
+
"eval_steps_per_second": 1.459,
|
| 294 |
+
"step": 950
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 15.384615384615385,
|
| 298 |
+
"grad_norm": 74.30262756347656,
|
| 299 |
+
"learning_rate": 4.9503500000000005e-05,
|
| 300 |
+
"loss": 2.3075,
|
| 301 |
+
"step": 1000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 15.384615384615385,
|
| 305 |
+
"eval_loss": 4.480749130249023,
|
| 306 |
+
"eval_runtime": 11.4324,
|
| 307 |
+
"eval_samples_per_second": 11.459,
|
| 308 |
+
"eval_steps_per_second": 1.487,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 16.153846153846153,
|
| 313 |
+
"grad_norm": 35.21226501464844,
|
| 314 |
+
"learning_rate": 4.94785e-05,
|
| 315 |
+
"loss": 2.2353,
|
| 316 |
+
"step": 1050
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 16.153846153846153,
|
| 320 |
+
"eval_loss": 4.612100601196289,
|
| 321 |
+
"eval_runtime": 11.4602,
|
| 322 |
+
"eval_samples_per_second": 11.431,
|
| 323 |
+
"eval_steps_per_second": 1.483,
|
| 324 |
+
"step": 1050
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 16.923076923076923,
|
| 328 |
+
"grad_norm": 34.0900993347168,
|
| 329 |
+
"learning_rate": 4.9453500000000003e-05,
|
| 330 |
+
"loss": 2.0935,
|
| 331 |
+
"step": 1100
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 16.923076923076923,
|
| 335 |
+
"eval_loss": 4.5592217445373535,
|
| 336 |
+
"eval_runtime": 11.4581,
|
| 337 |
+
"eval_samples_per_second": 11.433,
|
| 338 |
+
"eval_steps_per_second": 1.484,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 17.692307692307693,
|
| 343 |
+
"grad_norm": 45.47126388549805,
|
| 344 |
+
"learning_rate": 4.94285e-05,
|
| 345 |
+
"loss": 2.0857,
|
| 346 |
+
"step": 1150
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 17.692307692307693,
|
| 350 |
+
"eval_loss": 4.384246826171875,
|
| 351 |
+
"eval_runtime": 11.4099,
|
| 352 |
+
"eval_samples_per_second": 11.481,
|
| 353 |
+
"eval_steps_per_second": 1.49,
|
| 354 |
+
"step": 1150
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 18.46153846153846,
|
| 358 |
+
"grad_norm": 104.21978759765625,
|
| 359 |
+
"learning_rate": 4.94035e-05,
|
| 360 |
+
"loss": 2.1022,
|
| 361 |
+
"step": 1200
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 18.46153846153846,
|
| 365 |
+
"eval_loss": 5.295970916748047,
|
| 366 |
+
"eval_runtime": 11.5074,
|
| 367 |
+
"eval_samples_per_second": 11.384,
|
| 368 |
+
"eval_steps_per_second": 1.477,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 19.23076923076923,
|
| 373 |
+
"grad_norm": 34.15141677856445,
|
| 374 |
+
"learning_rate": 4.93785e-05,
|
| 375 |
+
"loss": 2.1064,
|
| 376 |
+
"step": 1250
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 19.23076923076923,
|
| 380 |
+
"eval_loss": 4.713132858276367,
|
| 381 |
+
"eval_runtime": 11.4545,
|
| 382 |
+
"eval_samples_per_second": 11.437,
|
| 383 |
+
"eval_steps_per_second": 1.484,
|
| 384 |
+
"step": 1250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 20.0,
|
| 388 |
+
"grad_norm": 62.586063385009766,
|
| 389 |
+
"learning_rate": 4.93535e-05,
|
| 390 |
+
"loss": 2.0908,
|
| 391 |
+
"step": 1300
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 20.0,
|
| 395 |
+
"eval_loss": 4.591387748718262,
|
| 396 |
+
"eval_runtime": 11.4781,
|
| 397 |
+
"eval_samples_per_second": 11.413,
|
| 398 |
+
"eval_steps_per_second": 1.481,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 20.76923076923077,
|
| 403 |
+
"grad_norm": 45.80879211425781,
|
| 404 |
+
"learning_rate": 4.93285e-05,
|
| 405 |
+
"loss": 2.058,
|
| 406 |
+
"step": 1350
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 20.76923076923077,
|
| 410 |
+
"eval_loss": 4.475380897521973,
|
| 411 |
+
"eval_runtime": 11.5397,
|
| 412 |
+
"eval_samples_per_second": 11.352,
|
| 413 |
+
"eval_steps_per_second": 1.473,
|
| 414 |
+
"step": 1350
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 21.53846153846154,
|
| 418 |
+
"grad_norm": 43.232906341552734,
|
| 419 |
+
"learning_rate": 4.93035e-05,
|
| 420 |
+
"loss": 2.098,
|
| 421 |
+
"step": 1400
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 21.53846153846154,
|
| 425 |
+
"eval_loss": 4.118782997131348,
|
| 426 |
+
"eval_runtime": 11.4494,
|
| 427 |
+
"eval_samples_per_second": 11.442,
|
| 428 |
+
"eval_steps_per_second": 1.485,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 22.307692307692307,
|
| 433 |
+
"grad_norm": 23.0355167388916,
|
| 434 |
+
"learning_rate": 4.92785e-05,
|
| 435 |
+
"loss": 2.0184,
|
| 436 |
+
"step": 1450
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 22.307692307692307,
|
| 440 |
+
"eval_loss": 4.232107639312744,
|
| 441 |
+
"eval_runtime": 11.3771,
|
| 442 |
+
"eval_samples_per_second": 11.514,
|
| 443 |
+
"eval_steps_per_second": 1.494,
|
| 444 |
+
"step": 1450
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 23.076923076923077,
|
| 448 |
+
"grad_norm": 40.55295181274414,
|
| 449 |
+
"learning_rate": 4.9253500000000005e-05,
|
| 450 |
+
"loss": 2.0399,
|
| 451 |
+
"step": 1500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 23.076923076923077,
|
| 455 |
+
"eval_loss": 3.9181947708129883,
|
| 456 |
+
"eval_runtime": 11.4083,
|
| 457 |
+
"eval_samples_per_second": 11.483,
|
| 458 |
+
"eval_steps_per_second": 1.49,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 23.846153846153847,
|
| 463 |
+
"grad_norm": 35.717044830322266,
|
| 464 |
+
"learning_rate": 4.92285e-05,
|
| 465 |
+
"loss": 1.9882,
|
| 466 |
+
"step": 1550
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 23.846153846153847,
|
| 470 |
+
"eval_loss": 4.631206512451172,
|
| 471 |
+
"eval_runtime": 11.4748,
|
| 472 |
+
"eval_samples_per_second": 11.416,
|
| 473 |
+
"eval_steps_per_second": 1.482,
|
| 474 |
+
"step": 1550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 24.615384615384617,
|
| 478 |
+
"grad_norm": 31.87916374206543,
|
| 479 |
+
"learning_rate": 4.9203500000000004e-05,
|
| 480 |
+
"loss": 1.9356,
|
| 481 |
+
"step": 1600
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 24.615384615384617,
|
| 485 |
+
"eval_loss": 4.68462610244751,
|
| 486 |
+
"eval_runtime": 11.4547,
|
| 487 |
+
"eval_samples_per_second": 11.436,
|
| 488 |
+
"eval_steps_per_second": 1.484,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 25.384615384615383,
|
| 493 |
+
"grad_norm": 32.03349304199219,
|
| 494 |
+
"learning_rate": 4.9178500000000004e-05,
|
| 495 |
+
"loss": 2.0485,
|
| 496 |
+
"step": 1650
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 25.384615384615383,
|
| 500 |
+
"eval_loss": 4.657995223999023,
|
| 501 |
+
"eval_runtime": 11.4448,
|
| 502 |
+
"eval_samples_per_second": 11.446,
|
| 503 |
+
"eval_steps_per_second": 1.485,
|
| 504 |
+
"step": 1650
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 26.153846153846153,
|
| 508 |
+
"grad_norm": 34.58638000488281,
|
| 509 |
+
"learning_rate": 4.91535e-05,
|
| 510 |
+
"loss": 2.0128,
|
| 511 |
+
"step": 1700
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 26.153846153846153,
|
| 515 |
+
"eval_loss": 4.415687084197998,
|
| 516 |
+
"eval_runtime": 11.3722,
|
| 517 |
+
"eval_samples_per_second": 11.519,
|
| 518 |
+
"eval_steps_per_second": 1.495,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 26.923076923076923,
|
| 523 |
+
"grad_norm": 37.93281555175781,
|
| 524 |
+
"learning_rate": 4.91285e-05,
|
| 525 |
+
"loss": 2.0954,
|
| 526 |
+
"step": 1750
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 26.923076923076923,
|
| 530 |
+
"eval_loss": 3.742335557937622,
|
| 531 |
+
"eval_runtime": 11.5178,
|
| 532 |
+
"eval_samples_per_second": 11.374,
|
| 533 |
+
"eval_steps_per_second": 1.476,
|
| 534 |
+
"step": 1750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 27.692307692307693,
|
| 538 |
+
"grad_norm": 35.21376419067383,
|
| 539 |
+
"learning_rate": 4.91035e-05,
|
| 540 |
+
"loss": 1.9582,
|
| 541 |
+
"step": 1800
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 27.692307692307693,
|
| 545 |
+
"eval_loss": 4.273777484893799,
|
| 546 |
+
"eval_runtime": 11.5104,
|
| 547 |
+
"eval_samples_per_second": 11.381,
|
| 548 |
+
"eval_steps_per_second": 1.477,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 28.46153846153846,
|
| 553 |
+
"grad_norm": 45.522491455078125,
|
| 554 |
+
"learning_rate": 4.907850000000001e-05,
|
| 555 |
+
"loss": 2.0381,
|
| 556 |
+
"step": 1850
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 28.46153846153846,
|
| 560 |
+
"eval_loss": 4.211084842681885,
|
| 561 |
+
"eval_runtime": 11.4427,
|
| 562 |
+
"eval_samples_per_second": 11.448,
|
| 563 |
+
"eval_steps_per_second": 1.486,
|
| 564 |
+
"step": 1850
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 29.23076923076923,
|
| 568 |
+
"grad_norm": 31.80489158630371,
|
| 569 |
+
"learning_rate": 4.90535e-05,
|
| 570 |
+
"loss": 1.9694,
|
| 571 |
+
"step": 1900
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 29.23076923076923,
|
| 575 |
+
"eval_loss": 4.326655864715576,
|
| 576 |
+
"eval_runtime": 11.495,
|
| 577 |
+
"eval_samples_per_second": 11.396,
|
| 578 |
+
"eval_steps_per_second": 1.479,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 30.0,
|
| 583 |
+
"grad_norm": 40.01383590698242,
|
| 584 |
+
"learning_rate": 4.902850000000001e-05,
|
| 585 |
+
"loss": 2.096,
|
| 586 |
+
"step": 1950
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 30.0,
|
| 590 |
+
"eval_loss": 4.649638652801514,
|
| 591 |
+
"eval_runtime": 11.4284,
|
| 592 |
+
"eval_samples_per_second": 11.463,
|
| 593 |
+
"eval_steps_per_second": 1.488,
|
| 594 |
+
"step": 1950
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 30.76923076923077,
|
| 598 |
+
"grad_norm": 56.41672897338867,
|
| 599 |
+
"learning_rate": 4.90035e-05,
|
| 600 |
+
"loss": 1.9365,
|
| 601 |
+
"step": 2000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 30.76923076923077,
|
| 605 |
+
"eval_loss": 4.189758777618408,
|
| 606 |
+
"eval_runtime": 11.4876,
|
| 607 |
+
"eval_samples_per_second": 11.404,
|
| 608 |
+
"eval_steps_per_second": 1.48,
|
| 609 |
+
"step": 2000
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 50,
|
| 613 |
+
"max_steps": 100000,
|
| 614 |
+
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 1539,
|
| 616 |
+
"save_steps": 500,
|
| 617 |
+
"stateful_callbacks": {
|
| 618 |
+
"TrainerControl": {
|
| 619 |
+
"args": {
|
| 620 |
+
"should_epoch_stop": false,
|
| 621 |
+
"should_evaluate": false,
|
| 622 |
+
"should_log": false,
|
| 623 |
+
"should_save": true,
|
| 624 |
+
"should_training_stop": false
|
| 625 |
+
},
|
| 626 |
+
"attributes": {}
|
| 627 |
+
}
|
| 628 |
+
},
|
| 629 |
+
"total_flos": 7.64486332416e+18,
|
| 630 |
+
"train_batch_size": 8,
|
| 631 |
+
"trial_name": null,
|
| 632 |
+
"trial_params": null
|
| 633 |
+
}
|
checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b1b85fea4c8b1c2a7be60102809409971174bcdf130b87ba93f7312e8b78a2e
|
| 3 |
+
size 5240
|