Training in progress, step 6000, checkpoint
Browse files- checkpoint-6000/config.json +62 -0
- checkpoint-6000/model.safetensors +3 -0
- checkpoint-6000/optimizer.pt +3 -0
- checkpoint-6000/preprocessor_config.json +26 -0
- checkpoint-6000/rng_state.pth +3 -0
- checkpoint-6000/scheduler.pt +3 -0
- checkpoint-6000/trainer_state.json +933 -0
- checkpoint-6000/training_args.bin +3 -0
checkpoint-6000/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-6000/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e40dbfd8936fe9024f479730e635edaf6927b07c3bfe219c8113ba3371b50067
|
| 3 |
+
size 166904424
|
checkpoint-6000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9902fe02eaafaf673a1f533e1d82efb9a941d3bacd21a5e617627a20c175179
|
| 3 |
+
size 331310970
|
checkpoint-6000/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-6000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9601feaf6944ba715997368fadfc79a733018c34ec6a9460cdcde64ae2c11ea3
|
| 3 |
+
size 14244
|
checkpoint-6000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8567d591222b382694cd6e49842033857a421cedc7df37c1fddcf70c2e792734
|
| 3 |
+
size 1064
|
checkpoint-6000/trainer_state.json
ADDED
|
@@ -0,0 +1,933 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 30.76923076923077,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 6000,
|
| 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": 81.8341293334961,
|
| 14 |
+
"learning_rate": 9.990900000000001e-06,
|
| 15 |
+
"loss": 3.5606,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5128205128205128,
|
| 20 |
+
"eval_loss": 2.2667126655578613,
|
| 21 |
+
"eval_runtime": 33.7385,
|
| 22 |
+
"eval_samples_per_second": 11.648,
|
| 23 |
+
"eval_steps_per_second": 1.482,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.0256410256410255,
|
| 28 |
+
"grad_norm": 30.16681671142578,
|
| 29 |
+
"learning_rate": 9.980900000000001e-06,
|
| 30 |
+
"loss": 2.1841,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0256410256410255,
|
| 35 |
+
"eval_loss": 2.059685230255127,
|
| 36 |
+
"eval_runtime": 33.6897,
|
| 37 |
+
"eval_samples_per_second": 11.665,
|
| 38 |
+
"eval_steps_per_second": 1.484,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.5384615384615383,
|
| 43 |
+
"grad_norm": 67.16844177246094,
|
| 44 |
+
"learning_rate": 9.970900000000001e-06,
|
| 45 |
+
"loss": 2.0949,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.5384615384615383,
|
| 50 |
+
"eval_loss": 1.9054155349731445,
|
| 51 |
+
"eval_runtime": 33.6472,
|
| 52 |
+
"eval_samples_per_second": 11.68,
|
| 53 |
+
"eval_steps_per_second": 1.486,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.051282051282051,
|
| 58 |
+
"grad_norm": 46.190330505371094,
|
| 59 |
+
"learning_rate": 9.960900000000001e-06,
|
| 60 |
+
"loss": 1.9236,
|
| 61 |
+
"step": 400
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.051282051282051,
|
| 65 |
+
"eval_loss": 1.8464823961257935,
|
| 66 |
+
"eval_runtime": 33.8143,
|
| 67 |
+
"eval_samples_per_second": 11.622,
|
| 68 |
+
"eval_steps_per_second": 1.479,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.564102564102564,
|
| 73 |
+
"grad_norm": 42.82326889038086,
|
| 74 |
+
"learning_rate": 9.950900000000002e-06,
|
| 75 |
+
"loss": 1.937,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.564102564102564,
|
| 80 |
+
"eval_loss": 1.8186373710632324,
|
| 81 |
+
"eval_runtime": 33.9112,
|
| 82 |
+
"eval_samples_per_second": 11.589,
|
| 83 |
+
"eval_steps_per_second": 1.474,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.076923076923077,
|
| 88 |
+
"grad_norm": 68.72016906738281,
|
| 89 |
+
"learning_rate": 9.940900000000002e-06,
|
| 90 |
+
"loss": 1.8648,
|
| 91 |
+
"step": 600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 3.076923076923077,
|
| 95 |
+
"eval_loss": 1.7807129621505737,
|
| 96 |
+
"eval_runtime": 33.4957,
|
| 97 |
+
"eval_samples_per_second": 11.733,
|
| 98 |
+
"eval_steps_per_second": 1.493,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.58974358974359,
|
| 103 |
+
"grad_norm": 51.390071868896484,
|
| 104 |
+
"learning_rate": 9.930900000000002e-06,
|
| 105 |
+
"loss": 1.8162,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.58974358974359,
|
| 110 |
+
"eval_loss": 1.7275961637496948,
|
| 111 |
+
"eval_runtime": 33.6095,
|
| 112 |
+
"eval_samples_per_second": 11.693,
|
| 113 |
+
"eval_steps_per_second": 1.488,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.102564102564102,
|
| 118 |
+
"grad_norm": 33.017948150634766,
|
| 119 |
+
"learning_rate": 9.920900000000002e-06,
|
| 120 |
+
"loss": 1.7331,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.102564102564102,
|
| 125 |
+
"eval_loss": 1.701725959777832,
|
| 126 |
+
"eval_runtime": 33.9602,
|
| 127 |
+
"eval_samples_per_second": 11.572,
|
| 128 |
+
"eval_steps_per_second": 1.472,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.615384615384615,
|
| 133 |
+
"grad_norm": 43.55423355102539,
|
| 134 |
+
"learning_rate": 9.9109e-06,
|
| 135 |
+
"loss": 1.7091,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.615384615384615,
|
| 140 |
+
"eval_loss": 1.6944857835769653,
|
| 141 |
+
"eval_runtime": 33.6785,
|
| 142 |
+
"eval_samples_per_second": 11.669,
|
| 143 |
+
"eval_steps_per_second": 1.485,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 5.128205128205128,
|
| 148 |
+
"grad_norm": 67.6618881225586,
|
| 149 |
+
"learning_rate": 9.9009e-06,
|
| 150 |
+
"loss": 1.7258,
|
| 151 |
+
"step": 1000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 5.128205128205128,
|
| 155 |
+
"eval_loss": 1.65646493434906,
|
| 156 |
+
"eval_runtime": 33.8316,
|
| 157 |
+
"eval_samples_per_second": 11.616,
|
| 158 |
+
"eval_steps_per_second": 1.478,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.641025641025641,
|
| 163 |
+
"grad_norm": 35.863487243652344,
|
| 164 |
+
"learning_rate": 9.8909e-06,
|
| 165 |
+
"loss": 1.661,
|
| 166 |
+
"step": 1100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 5.641025641025641,
|
| 170 |
+
"eval_loss": 1.6175495386123657,
|
| 171 |
+
"eval_runtime": 33.57,
|
| 172 |
+
"eval_samples_per_second": 11.707,
|
| 173 |
+
"eval_steps_per_second": 1.489,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 6.153846153846154,
|
| 178 |
+
"grad_norm": 56.98338317871094,
|
| 179 |
+
"learning_rate": 9.8809e-06,
|
| 180 |
+
"loss": 1.6368,
|
| 181 |
+
"step": 1200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 6.153846153846154,
|
| 185 |
+
"eval_loss": 1.6185818910598755,
|
| 186 |
+
"eval_runtime": 33.6954,
|
| 187 |
+
"eval_samples_per_second": 11.663,
|
| 188 |
+
"eval_steps_per_second": 1.484,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.666666666666667,
|
| 193 |
+
"grad_norm": 90.9850845336914,
|
| 194 |
+
"learning_rate": 9.8709e-06,
|
| 195 |
+
"loss": 1.6771,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 6.666666666666667,
|
| 200 |
+
"eval_loss": 1.597514033317566,
|
| 201 |
+
"eval_runtime": 33.5635,
|
| 202 |
+
"eval_samples_per_second": 11.709,
|
| 203 |
+
"eval_steps_per_second": 1.49,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 7.17948717948718,
|
| 208 |
+
"grad_norm": 83.6468276977539,
|
| 209 |
+
"learning_rate": 9.8609e-06,
|
| 210 |
+
"loss": 1.5796,
|
| 211 |
+
"step": 1400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 7.17948717948718,
|
| 215 |
+
"eval_loss": 1.57249116897583,
|
| 216 |
+
"eval_runtime": 33.6053,
|
| 217 |
+
"eval_samples_per_second": 11.695,
|
| 218 |
+
"eval_steps_per_second": 1.488,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.6923076923076925,
|
| 223 |
+
"grad_norm": 42.52065658569336,
|
| 224 |
+
"learning_rate": 9.8509e-06,
|
| 225 |
+
"loss": 1.6012,
|
| 226 |
+
"step": 1500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.6923076923076925,
|
| 230 |
+
"eval_loss": 1.5940505266189575,
|
| 231 |
+
"eval_runtime": 33.6416,
|
| 232 |
+
"eval_samples_per_second": 11.682,
|
| 233 |
+
"eval_steps_per_second": 1.486,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 8.205128205128204,
|
| 238 |
+
"grad_norm": 64.46149444580078,
|
| 239 |
+
"learning_rate": 9.840900000000001e-06,
|
| 240 |
+
"loss": 1.6107,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.205128205128204,
|
| 245 |
+
"eval_loss": 1.57711923122406,
|
| 246 |
+
"eval_runtime": 33.8072,
|
| 247 |
+
"eval_samples_per_second": 11.625,
|
| 248 |
+
"eval_steps_per_second": 1.479,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 8.717948717948717,
|
| 253 |
+
"grad_norm": 47.13843536376953,
|
| 254 |
+
"learning_rate": 9.830900000000001e-06,
|
| 255 |
+
"loss": 1.6094,
|
| 256 |
+
"step": 1700
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 8.717948717948717,
|
| 260 |
+
"eval_loss": 1.5567021369934082,
|
| 261 |
+
"eval_runtime": 33.6256,
|
| 262 |
+
"eval_samples_per_second": 11.688,
|
| 263 |
+
"eval_steps_per_second": 1.487,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 9.23076923076923,
|
| 268 |
+
"grad_norm": 60.96649932861328,
|
| 269 |
+
"learning_rate": 9.820900000000001e-06,
|
| 270 |
+
"loss": 1.5679,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 9.23076923076923,
|
| 275 |
+
"eval_loss": 1.5404459238052368,
|
| 276 |
+
"eval_runtime": 33.5651,
|
| 277 |
+
"eval_samples_per_second": 11.709,
|
| 278 |
+
"eval_steps_per_second": 1.49,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 9.743589743589745,
|
| 283 |
+
"grad_norm": 48.0488395690918,
|
| 284 |
+
"learning_rate": 9.810900000000001e-06,
|
| 285 |
+
"loss": 1.541,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 9.743589743589745,
|
| 290 |
+
"eval_loss": 1.5000860691070557,
|
| 291 |
+
"eval_runtime": 33.729,
|
| 292 |
+
"eval_samples_per_second": 11.652,
|
| 293 |
+
"eval_steps_per_second": 1.482,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 10.256410256410255,
|
| 298 |
+
"grad_norm": 21.072124481201172,
|
| 299 |
+
"learning_rate": 9.800900000000001e-06,
|
| 300 |
+
"loss": 1.4747,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 10.256410256410255,
|
| 305 |
+
"eval_loss": 1.4845048189163208,
|
| 306 |
+
"eval_runtime": 33.6789,
|
| 307 |
+
"eval_samples_per_second": 11.669,
|
| 308 |
+
"eval_steps_per_second": 1.485,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 10.76923076923077,
|
| 313 |
+
"grad_norm": 60.55208969116211,
|
| 314 |
+
"learning_rate": 9.790900000000001e-06,
|
| 315 |
+
"loss": 1.5105,
|
| 316 |
+
"step": 2100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 10.76923076923077,
|
| 320 |
+
"eval_loss": 1.4587421417236328,
|
| 321 |
+
"eval_runtime": 33.4313,
|
| 322 |
+
"eval_samples_per_second": 11.755,
|
| 323 |
+
"eval_steps_per_second": 1.496,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 11.282051282051283,
|
| 328 |
+
"grad_norm": 26.457704544067383,
|
| 329 |
+
"learning_rate": 9.780900000000002e-06,
|
| 330 |
+
"loss": 1.4769,
|
| 331 |
+
"step": 2200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 11.282051282051283,
|
| 335 |
+
"eval_loss": 1.4588648080825806,
|
| 336 |
+
"eval_runtime": 33.5978,
|
| 337 |
+
"eval_samples_per_second": 11.697,
|
| 338 |
+
"eval_steps_per_second": 1.488,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 11.794871794871796,
|
| 343 |
+
"grad_norm": 23.801916122436523,
|
| 344 |
+
"learning_rate": 9.770900000000002e-06,
|
| 345 |
+
"loss": 1.4555,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 11.794871794871796,
|
| 350 |
+
"eval_loss": 1.4805899858474731,
|
| 351 |
+
"eval_runtime": 33.4947,
|
| 352 |
+
"eval_samples_per_second": 11.733,
|
| 353 |
+
"eval_steps_per_second": 1.493,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 12.307692307692308,
|
| 358 |
+
"grad_norm": 24.780275344848633,
|
| 359 |
+
"learning_rate": 9.760900000000002e-06,
|
| 360 |
+
"loss": 1.4537,
|
| 361 |
+
"step": 2400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 12.307692307692308,
|
| 365 |
+
"eval_loss": 1.4648451805114746,
|
| 366 |
+
"eval_runtime": 33.6877,
|
| 367 |
+
"eval_samples_per_second": 11.666,
|
| 368 |
+
"eval_steps_per_second": 1.484,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 12.820512820512821,
|
| 373 |
+
"grad_norm": 65.28894805908203,
|
| 374 |
+
"learning_rate": 9.7509e-06,
|
| 375 |
+
"loss": 1.4788,
|
| 376 |
+
"step": 2500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 12.820512820512821,
|
| 380 |
+
"eval_loss": 1.4453215599060059,
|
| 381 |
+
"eval_runtime": 33.972,
|
| 382 |
+
"eval_samples_per_second": 11.568,
|
| 383 |
+
"eval_steps_per_second": 1.472,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 13.333333333333334,
|
| 388 |
+
"grad_norm": 23.36334800720215,
|
| 389 |
+
"learning_rate": 9.7409e-06,
|
| 390 |
+
"loss": 1.4397,
|
| 391 |
+
"step": 2600
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 13.333333333333334,
|
| 395 |
+
"eval_loss": 1.4110159873962402,
|
| 396 |
+
"eval_runtime": 33.3905,
|
| 397 |
+
"eval_samples_per_second": 11.77,
|
| 398 |
+
"eval_steps_per_second": 1.497,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 13.846153846153847,
|
| 403 |
+
"grad_norm": 24.13091468811035,
|
| 404 |
+
"learning_rate": 9.7309e-06,
|
| 405 |
+
"loss": 1.42,
|
| 406 |
+
"step": 2700
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 13.846153846153847,
|
| 410 |
+
"eval_loss": 1.3875733613967896,
|
| 411 |
+
"eval_runtime": 33.5662,
|
| 412 |
+
"eval_samples_per_second": 11.708,
|
| 413 |
+
"eval_steps_per_second": 1.49,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 14.35897435897436,
|
| 418 |
+
"grad_norm": 41.02390670776367,
|
| 419 |
+
"learning_rate": 9.7209e-06,
|
| 420 |
+
"loss": 1.3833,
|
| 421 |
+
"step": 2800
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 14.35897435897436,
|
| 425 |
+
"eval_loss": 1.3958121538162231,
|
| 426 |
+
"eval_runtime": 33.6111,
|
| 427 |
+
"eval_samples_per_second": 11.693,
|
| 428 |
+
"eval_steps_per_second": 1.488,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 14.871794871794872,
|
| 433 |
+
"grad_norm": 25.11317253112793,
|
| 434 |
+
"learning_rate": 9.7109e-06,
|
| 435 |
+
"loss": 1.3839,
|
| 436 |
+
"step": 2900
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 14.871794871794872,
|
| 440 |
+
"eval_loss": 1.4024689197540283,
|
| 441 |
+
"eval_runtime": 33.5271,
|
| 442 |
+
"eval_samples_per_second": 11.722,
|
| 443 |
+
"eval_steps_per_second": 1.491,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 15.384615384615385,
|
| 448 |
+
"grad_norm": 32.921974182128906,
|
| 449 |
+
"learning_rate": 9.7009e-06,
|
| 450 |
+
"loss": 1.3998,
|
| 451 |
+
"step": 3000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 15.384615384615385,
|
| 455 |
+
"eval_loss": 1.3834290504455566,
|
| 456 |
+
"eval_runtime": 33.4449,
|
| 457 |
+
"eval_samples_per_second": 11.751,
|
| 458 |
+
"eval_steps_per_second": 1.495,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 15.897435897435898,
|
| 463 |
+
"grad_norm": 71.14076232910156,
|
| 464 |
+
"learning_rate": 9.6909e-06,
|
| 465 |
+
"loss": 1.3753,
|
| 466 |
+
"step": 3100
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 15.897435897435898,
|
| 470 |
+
"eval_loss": 1.371915578842163,
|
| 471 |
+
"eval_runtime": 33.5787,
|
| 472 |
+
"eval_samples_per_second": 11.704,
|
| 473 |
+
"eval_steps_per_second": 1.489,
|
| 474 |
+
"step": 3100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 16.41025641025641,
|
| 478 |
+
"grad_norm": 85.71231842041016,
|
| 479 |
+
"learning_rate": 9.6809e-06,
|
| 480 |
+
"loss": 1.3639,
|
| 481 |
+
"step": 3200
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 16.41025641025641,
|
| 485 |
+
"eval_loss": 1.3810721635818481,
|
| 486 |
+
"eval_runtime": 33.5802,
|
| 487 |
+
"eval_samples_per_second": 11.703,
|
| 488 |
+
"eval_steps_per_second": 1.489,
|
| 489 |
+
"step": 3200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 16.923076923076923,
|
| 493 |
+
"grad_norm": 39.7967529296875,
|
| 494 |
+
"learning_rate": 9.670900000000001e-06,
|
| 495 |
+
"loss": 1.3609,
|
| 496 |
+
"step": 3300
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 16.923076923076923,
|
| 500 |
+
"eval_loss": 1.3853365182876587,
|
| 501 |
+
"eval_runtime": 33.6581,
|
| 502 |
+
"eval_samples_per_second": 11.676,
|
| 503 |
+
"eval_steps_per_second": 1.486,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 17.435897435897434,
|
| 508 |
+
"grad_norm": 19.84697723388672,
|
| 509 |
+
"learning_rate": 9.660900000000001e-06,
|
| 510 |
+
"loss": 1.3314,
|
| 511 |
+
"step": 3400
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 17.435897435897434,
|
| 515 |
+
"eval_loss": 1.3581265211105347,
|
| 516 |
+
"eval_runtime": 33.4833,
|
| 517 |
+
"eval_samples_per_second": 11.737,
|
| 518 |
+
"eval_steps_per_second": 1.493,
|
| 519 |
+
"step": 3400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 17.94871794871795,
|
| 523 |
+
"grad_norm": 43.280426025390625,
|
| 524 |
+
"learning_rate": 9.650900000000001e-06,
|
| 525 |
+
"loss": 1.3408,
|
| 526 |
+
"step": 3500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 17.94871794871795,
|
| 530 |
+
"eval_loss": 1.3400689363479614,
|
| 531 |
+
"eval_runtime": 33.4394,
|
| 532 |
+
"eval_samples_per_second": 11.753,
|
| 533 |
+
"eval_steps_per_second": 1.495,
|
| 534 |
+
"step": 3500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 18.46153846153846,
|
| 538 |
+
"grad_norm": 35.393314361572266,
|
| 539 |
+
"learning_rate": 9.640900000000001e-06,
|
| 540 |
+
"loss": 1.3471,
|
| 541 |
+
"step": 3600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 18.46153846153846,
|
| 545 |
+
"eval_loss": 1.3405698537826538,
|
| 546 |
+
"eval_runtime": 33.6347,
|
| 547 |
+
"eval_samples_per_second": 11.684,
|
| 548 |
+
"eval_steps_per_second": 1.487,
|
| 549 |
+
"step": 3600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 18.974358974358974,
|
| 553 |
+
"grad_norm": 32.50804138183594,
|
| 554 |
+
"learning_rate": 9.630900000000001e-06,
|
| 555 |
+
"loss": 1.3213,
|
| 556 |
+
"step": 3700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 18.974358974358974,
|
| 560 |
+
"eval_loss": 1.3345987796783447,
|
| 561 |
+
"eval_runtime": 33.5369,
|
| 562 |
+
"eval_samples_per_second": 11.718,
|
| 563 |
+
"eval_steps_per_second": 1.491,
|
| 564 |
+
"step": 3700
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 19.487179487179485,
|
| 568 |
+
"grad_norm": 28.999061584472656,
|
| 569 |
+
"learning_rate": 9.620900000000001e-06,
|
| 570 |
+
"loss": 1.3251,
|
| 571 |
+
"step": 3800
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 19.487179487179485,
|
| 575 |
+
"eval_loss": 1.3227241039276123,
|
| 576 |
+
"eval_runtime": 33.5001,
|
| 577 |
+
"eval_samples_per_second": 11.731,
|
| 578 |
+
"eval_steps_per_second": 1.493,
|
| 579 |
+
"step": 3800
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 20.0,
|
| 583 |
+
"grad_norm": 41.793636322021484,
|
| 584 |
+
"learning_rate": 9.610900000000001e-06,
|
| 585 |
+
"loss": 1.3297,
|
| 586 |
+
"step": 3900
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 20.0,
|
| 590 |
+
"eval_loss": 1.3213008642196655,
|
| 591 |
+
"eval_runtime": 33.561,
|
| 592 |
+
"eval_samples_per_second": 11.71,
|
| 593 |
+
"eval_steps_per_second": 1.49,
|
| 594 |
+
"step": 3900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 20.51282051282051,
|
| 598 |
+
"grad_norm": 53.55360794067383,
|
| 599 |
+
"learning_rate": 9.600900000000002e-06,
|
| 600 |
+
"loss": 1.331,
|
| 601 |
+
"step": 4000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 20.51282051282051,
|
| 605 |
+
"eval_loss": 1.3293949365615845,
|
| 606 |
+
"eval_runtime": 33.5542,
|
| 607 |
+
"eval_samples_per_second": 11.712,
|
| 608 |
+
"eval_steps_per_second": 1.49,
|
| 609 |
+
"step": 4000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 21.025641025641026,
|
| 613 |
+
"grad_norm": 73.3389892578125,
|
| 614 |
+
"learning_rate": 9.5909e-06,
|
| 615 |
+
"loss": 1.2856,
|
| 616 |
+
"step": 4100
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 21.025641025641026,
|
| 620 |
+
"eval_loss": 1.316487193107605,
|
| 621 |
+
"eval_runtime": 33.5602,
|
| 622 |
+
"eval_samples_per_second": 11.71,
|
| 623 |
+
"eval_steps_per_second": 1.49,
|
| 624 |
+
"step": 4100
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 21.53846153846154,
|
| 628 |
+
"grad_norm": 62.724456787109375,
|
| 629 |
+
"learning_rate": 9.5809e-06,
|
| 630 |
+
"loss": 1.3186,
|
| 631 |
+
"step": 4200
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 21.53846153846154,
|
| 635 |
+
"eval_loss": 1.3179290294647217,
|
| 636 |
+
"eval_runtime": 33.621,
|
| 637 |
+
"eval_samples_per_second": 11.689,
|
| 638 |
+
"eval_steps_per_second": 1.487,
|
| 639 |
+
"step": 4200
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 22.05128205128205,
|
| 643 |
+
"grad_norm": 30.242937088012695,
|
| 644 |
+
"learning_rate": 9.5709e-06,
|
| 645 |
+
"loss": 1.2623,
|
| 646 |
+
"step": 4300
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 22.05128205128205,
|
| 650 |
+
"eval_loss": 1.2920558452606201,
|
| 651 |
+
"eval_runtime": 33.6166,
|
| 652 |
+
"eval_samples_per_second": 11.691,
|
| 653 |
+
"eval_steps_per_second": 1.487,
|
| 654 |
+
"step": 4300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 22.564102564102566,
|
| 658 |
+
"grad_norm": 17.423118591308594,
|
| 659 |
+
"learning_rate": 9.5609e-06,
|
| 660 |
+
"loss": 1.3045,
|
| 661 |
+
"step": 4400
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 22.564102564102566,
|
| 665 |
+
"eval_loss": 1.302635669708252,
|
| 666 |
+
"eval_runtime": 33.7322,
|
| 667 |
+
"eval_samples_per_second": 11.651,
|
| 668 |
+
"eval_steps_per_second": 1.482,
|
| 669 |
+
"step": 4400
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 23.076923076923077,
|
| 673 |
+
"grad_norm": 115.05293273925781,
|
| 674 |
+
"learning_rate": 9.5509e-06,
|
| 675 |
+
"loss": 1.2997,
|
| 676 |
+
"step": 4500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 23.076923076923077,
|
| 680 |
+
"eval_loss": 1.2834452390670776,
|
| 681 |
+
"eval_runtime": 33.5349,
|
| 682 |
+
"eval_samples_per_second": 11.719,
|
| 683 |
+
"eval_steps_per_second": 1.491,
|
| 684 |
+
"step": 4500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 23.58974358974359,
|
| 688 |
+
"grad_norm": 35.13385009765625,
|
| 689 |
+
"learning_rate": 9.5409e-06,
|
| 690 |
+
"loss": 1.2591,
|
| 691 |
+
"step": 4600
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 23.58974358974359,
|
| 695 |
+
"eval_loss": 1.2677439451217651,
|
| 696 |
+
"eval_runtime": 33.5991,
|
| 697 |
+
"eval_samples_per_second": 11.697,
|
| 698 |
+
"eval_steps_per_second": 1.488,
|
| 699 |
+
"step": 4600
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 24.102564102564102,
|
| 703 |
+
"grad_norm": 22.429704666137695,
|
| 704 |
+
"learning_rate": 9.5309e-06,
|
| 705 |
+
"loss": 1.3057,
|
| 706 |
+
"step": 4700
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 24.102564102564102,
|
| 710 |
+
"eval_loss": 1.2759162187576294,
|
| 711 |
+
"eval_runtime": 33.8336,
|
| 712 |
+
"eval_samples_per_second": 11.616,
|
| 713 |
+
"eval_steps_per_second": 1.478,
|
| 714 |
+
"step": 4700
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 24.615384615384617,
|
| 718 |
+
"grad_norm": 19.258209228515625,
|
| 719 |
+
"learning_rate": 9.5209e-06,
|
| 720 |
+
"loss": 1.2526,
|
| 721 |
+
"step": 4800
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 24.615384615384617,
|
| 725 |
+
"eval_loss": 1.2712483406066895,
|
| 726 |
+
"eval_runtime": 33.585,
|
| 727 |
+
"eval_samples_per_second": 11.702,
|
| 728 |
+
"eval_steps_per_second": 1.489,
|
| 729 |
+
"step": 4800
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 25.128205128205128,
|
| 733 |
+
"grad_norm": 18.289043426513672,
|
| 734 |
+
"learning_rate": 9.5109e-06,
|
| 735 |
+
"loss": 1.2436,
|
| 736 |
+
"step": 4900
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 25.128205128205128,
|
| 740 |
+
"eval_loss": 1.277999758720398,
|
| 741 |
+
"eval_runtime": 33.6639,
|
| 742 |
+
"eval_samples_per_second": 11.674,
|
| 743 |
+
"eval_steps_per_second": 1.485,
|
| 744 |
+
"step": 4900
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 25.641025641025642,
|
| 748 |
+
"grad_norm": 53.41452407836914,
|
| 749 |
+
"learning_rate": 9.501000000000001e-06,
|
| 750 |
+
"loss": 1.2768,
|
| 751 |
+
"step": 5000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 25.641025641025642,
|
| 755 |
+
"eval_loss": 1.2602609395980835,
|
| 756 |
+
"eval_runtime": 33.6751,
|
| 757 |
+
"eval_samples_per_second": 11.67,
|
| 758 |
+
"eval_steps_per_second": 1.485,
|
| 759 |
+
"step": 5000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 26.153846153846153,
|
| 763 |
+
"grad_norm": 28.17922019958496,
|
| 764 |
+
"learning_rate": 9.491000000000001e-06,
|
| 765 |
+
"loss": 1.2221,
|
| 766 |
+
"step": 5100
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 26.153846153846153,
|
| 770 |
+
"eval_loss": 1.28999662399292,
|
| 771 |
+
"eval_runtime": 33.8104,
|
| 772 |
+
"eval_samples_per_second": 11.624,
|
| 773 |
+
"eval_steps_per_second": 1.479,
|
| 774 |
+
"step": 5100
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 26.666666666666668,
|
| 778 |
+
"grad_norm": 28.119773864746094,
|
| 779 |
+
"learning_rate": 9.481000000000001e-06,
|
| 780 |
+
"loss": 1.233,
|
| 781 |
+
"step": 5200
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 26.666666666666668,
|
| 785 |
+
"eval_loss": 1.2724733352661133,
|
| 786 |
+
"eval_runtime": 33.9553,
|
| 787 |
+
"eval_samples_per_second": 11.574,
|
| 788 |
+
"eval_steps_per_second": 1.473,
|
| 789 |
+
"step": 5200
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 27.17948717948718,
|
| 793 |
+
"grad_norm": 102.97128295898438,
|
| 794 |
+
"learning_rate": 9.471000000000001e-06,
|
| 795 |
+
"loss": 1.2667,
|
| 796 |
+
"step": 5300
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 27.17948717948718,
|
| 800 |
+
"eval_loss": 1.265009880065918,
|
| 801 |
+
"eval_runtime": 33.7879,
|
| 802 |
+
"eval_samples_per_second": 11.631,
|
| 803 |
+
"eval_steps_per_second": 1.48,
|
| 804 |
+
"step": 5300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 27.692307692307693,
|
| 808 |
+
"grad_norm": 23.439664840698242,
|
| 809 |
+
"learning_rate": 9.461000000000001e-06,
|
| 810 |
+
"loss": 1.2255,
|
| 811 |
+
"step": 5400
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 27.692307692307693,
|
| 815 |
+
"eval_loss": 1.2421387434005737,
|
| 816 |
+
"eval_runtime": 33.867,
|
| 817 |
+
"eval_samples_per_second": 11.604,
|
| 818 |
+
"eval_steps_per_second": 1.476,
|
| 819 |
+
"step": 5400
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 28.205128205128204,
|
| 823 |
+
"grad_norm": 34.7141227722168,
|
| 824 |
+
"learning_rate": 9.451000000000002e-06,
|
| 825 |
+
"loss": 1.2557,
|
| 826 |
+
"step": 5500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 28.205128205128204,
|
| 830 |
+
"eval_loss": 1.2613080739974976,
|
| 831 |
+
"eval_runtime": 33.9538,
|
| 832 |
+
"eval_samples_per_second": 11.575,
|
| 833 |
+
"eval_steps_per_second": 1.473,
|
| 834 |
+
"step": 5500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 28.71794871794872,
|
| 838 |
+
"grad_norm": 60.65612030029297,
|
| 839 |
+
"learning_rate": 9.441000000000002e-06,
|
| 840 |
+
"loss": 1.2407,
|
| 841 |
+
"step": 5600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 28.71794871794872,
|
| 845 |
+
"eval_loss": 1.2578727006912231,
|
| 846 |
+
"eval_runtime": 33.8423,
|
| 847 |
+
"eval_samples_per_second": 11.613,
|
| 848 |
+
"eval_steps_per_second": 1.477,
|
| 849 |
+
"step": 5600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 29.23076923076923,
|
| 853 |
+
"grad_norm": 39.73835754394531,
|
| 854 |
+
"learning_rate": 9.431000000000002e-06,
|
| 855 |
+
"loss": 1.2436,
|
| 856 |
+
"step": 5700
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 29.23076923076923,
|
| 860 |
+
"eval_loss": 1.2593867778778076,
|
| 861 |
+
"eval_runtime": 33.6929,
|
| 862 |
+
"eval_samples_per_second": 11.664,
|
| 863 |
+
"eval_steps_per_second": 1.484,
|
| 864 |
+
"step": 5700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 29.743589743589745,
|
| 868 |
+
"grad_norm": 24.647741317749023,
|
| 869 |
+
"learning_rate": 9.421000000000002e-06,
|
| 870 |
+
"loss": 1.207,
|
| 871 |
+
"step": 5800
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 29.743589743589745,
|
| 875 |
+
"eval_loss": 1.2388144731521606,
|
| 876 |
+
"eval_runtime": 33.7238,
|
| 877 |
+
"eval_samples_per_second": 11.654,
|
| 878 |
+
"eval_steps_per_second": 1.483,
|
| 879 |
+
"step": 5800
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 30.256410256410255,
|
| 883 |
+
"grad_norm": 63.13822937011719,
|
| 884 |
+
"learning_rate": 9.411000000000002e-06,
|
| 885 |
+
"loss": 1.2287,
|
| 886 |
+
"step": 5900
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 30.256410256410255,
|
| 890 |
+
"eval_loss": 1.2804478406906128,
|
| 891 |
+
"eval_runtime": 33.7389,
|
| 892 |
+
"eval_samples_per_second": 11.648,
|
| 893 |
+
"eval_steps_per_second": 1.482,
|
| 894 |
+
"step": 5900
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 30.76923076923077,
|
| 898 |
+
"grad_norm": 27.123302459716797,
|
| 899 |
+
"learning_rate": 9.401000000000002e-06,
|
| 900 |
+
"loss": 1.2249,
|
| 901 |
+
"step": 6000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 30.76923076923077,
|
| 905 |
+
"eval_loss": 1.2437323331832886,
|
| 906 |
+
"eval_runtime": 33.6856,
|
| 907 |
+
"eval_samples_per_second": 11.667,
|
| 908 |
+
"eval_steps_per_second": 1.484,
|
| 909 |
+
"step": 6000
|
| 910 |
+
}
|
| 911 |
+
],
|
| 912 |
+
"logging_steps": 100,
|
| 913 |
+
"max_steps": 100000,
|
| 914 |
+
"num_input_tokens_seen": 0,
|
| 915 |
+
"num_train_epochs": 513,
|
| 916 |
+
"save_steps": 500,
|
| 917 |
+
"stateful_callbacks": {
|
| 918 |
+
"TrainerControl": {
|
| 919 |
+
"args": {
|
| 920 |
+
"should_epoch_stop": false,
|
| 921 |
+
"should_evaluate": false,
|
| 922 |
+
"should_log": false,
|
| 923 |
+
"should_save": true,
|
| 924 |
+
"should_training_stop": false
|
| 925 |
+
},
|
| 926 |
+
"attributes": {}
|
| 927 |
+
}
|
| 928 |
+
},
|
| 929 |
+
"total_flos": 2.293458997248e+19,
|
| 930 |
+
"train_batch_size": 8,
|
| 931 |
+
"trial_name": null,
|
| 932 |
+
"trial_params": null
|
| 933 |
+
}
|
checkpoint-6000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12024124d98d6f3527d5a0e9a760923228a8928111a77f0d825458c2cc9072c6
|
| 3 |
+
size 5304
|