Training in progress, step 13500, checkpoint
Browse files- checkpoint-13500/config.json +62 -0
- checkpoint-13500/model.safetensors +3 -0
- checkpoint-13500/optimizer.pt +3 -0
- checkpoint-13500/preprocessor_config.json +26 -0
- checkpoint-13500/rng_state.pth +3 -0
- checkpoint-13500/scheduler.pt +3 -0
- checkpoint-13500/trainer_state.json +2058 -0
- checkpoint-13500/training_args.bin +3 -0
checkpoint-13500/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-13500/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:071c8202b4b7f99c0f8d92823a9ea89c600a6097da9d260cf1cc8d72f6dbbf64
|
| 3 |
+
size 166904424
|
checkpoint-13500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:093f37f4eae8cfb7dd5fdfcb7c378124bbc413aa8c97471eb783f089a1a87d0f
|
| 3 |
+
size 331310970
|
checkpoint-13500/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-13500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78aea0dda44540727fc12349af2f5296803403f298ae7633bf628febaf9ba00d
|
| 3 |
+
size 14244
|
checkpoint-13500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9c21148753cf023b1a1be5dd9ccef8b2b568be53afaf78dcde3d5abb9fb4a16
|
| 3 |
+
size 1064
|
checkpoint-13500/trainer_state.json
ADDED
|
@@ -0,0 +1,2058 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 69.23076923076923,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 13500,
|
| 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": 73.68424224853516,
|
| 14 |
+
"learning_rate": 9.9907e-06,
|
| 15 |
+
"loss": 3.1457,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.5128205128205128,
|
| 20 |
+
"eval_loss": 2.2357213497161865,
|
| 21 |
+
"eval_runtime": 36.4689,
|
| 22 |
+
"eval_samples_per_second": 10.776,
|
| 23 |
+
"eval_steps_per_second": 1.371,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 1.0256410256410255,
|
| 28 |
+
"grad_norm": 57.47202682495117,
|
| 29 |
+
"learning_rate": 9.980800000000001e-06,
|
| 30 |
+
"loss": 2.1614,
|
| 31 |
+
"step": 200
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.0256410256410255,
|
| 35 |
+
"eval_loss": 2.0913825035095215,
|
| 36 |
+
"eval_runtime": 36.349,
|
| 37 |
+
"eval_samples_per_second": 10.812,
|
| 38 |
+
"eval_steps_per_second": 1.376,
|
| 39 |
+
"step": 200
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.5384615384615383,
|
| 43 |
+
"grad_norm": 176.88357543945312,
|
| 44 |
+
"learning_rate": 9.970800000000001e-06,
|
| 45 |
+
"loss": 2.0388,
|
| 46 |
+
"step": 300
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.5384615384615383,
|
| 50 |
+
"eval_loss": 2.003911018371582,
|
| 51 |
+
"eval_runtime": 36.2551,
|
| 52 |
+
"eval_samples_per_second": 10.84,
|
| 53 |
+
"eval_steps_per_second": 1.379,
|
| 54 |
+
"step": 300
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 2.051282051282051,
|
| 58 |
+
"grad_norm": 55.31132507324219,
|
| 59 |
+
"learning_rate": 9.960800000000001e-06,
|
| 60 |
+
"loss": 1.9285,
|
| 61 |
+
"step": 400
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 2.051282051282051,
|
| 65 |
+
"eval_loss": 1.9796075820922852,
|
| 66 |
+
"eval_runtime": 36.4437,
|
| 67 |
+
"eval_samples_per_second": 10.784,
|
| 68 |
+
"eval_steps_per_second": 1.372,
|
| 69 |
+
"step": 400
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.564102564102564,
|
| 73 |
+
"grad_norm": 41.900753021240234,
|
| 74 |
+
"learning_rate": 9.9508e-06,
|
| 75 |
+
"loss": 1.9523,
|
| 76 |
+
"step": 500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.564102564102564,
|
| 80 |
+
"eval_loss": 1.936122179031372,
|
| 81 |
+
"eval_runtime": 36.5845,
|
| 82 |
+
"eval_samples_per_second": 10.742,
|
| 83 |
+
"eval_steps_per_second": 1.367,
|
| 84 |
+
"step": 500
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 3.076923076923077,
|
| 88 |
+
"grad_norm": 50.21903991699219,
|
| 89 |
+
"learning_rate": 9.9408e-06,
|
| 90 |
+
"loss": 1.8452,
|
| 91 |
+
"step": 600
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 3.076923076923077,
|
| 95 |
+
"eval_loss": 1.8883634805679321,
|
| 96 |
+
"eval_runtime": 36.6015,
|
| 97 |
+
"eval_samples_per_second": 10.737,
|
| 98 |
+
"eval_steps_per_second": 1.366,
|
| 99 |
+
"step": 600
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.58974358974359,
|
| 103 |
+
"grad_norm": 45.193939208984375,
|
| 104 |
+
"learning_rate": 9.930900000000002e-06,
|
| 105 |
+
"loss": 1.8403,
|
| 106 |
+
"step": 700
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 3.58974358974359,
|
| 110 |
+
"eval_loss": 1.8506474494934082,
|
| 111 |
+
"eval_runtime": 36.454,
|
| 112 |
+
"eval_samples_per_second": 10.781,
|
| 113 |
+
"eval_steps_per_second": 1.372,
|
| 114 |
+
"step": 700
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 4.102564102564102,
|
| 118 |
+
"grad_norm": 27.302494049072266,
|
| 119 |
+
"learning_rate": 9.920900000000002e-06,
|
| 120 |
+
"loss": 1.7976,
|
| 121 |
+
"step": 800
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 4.102564102564102,
|
| 125 |
+
"eval_loss": 1.8370662927627563,
|
| 126 |
+
"eval_runtime": 36.834,
|
| 127 |
+
"eval_samples_per_second": 10.67,
|
| 128 |
+
"eval_steps_per_second": 1.357,
|
| 129 |
+
"step": 800
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.615384615384615,
|
| 133 |
+
"grad_norm": 52.6607666015625,
|
| 134 |
+
"learning_rate": 9.9109e-06,
|
| 135 |
+
"loss": 1.7508,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 4.615384615384615,
|
| 140 |
+
"eval_loss": 1.8037244081497192,
|
| 141 |
+
"eval_runtime": 36.9939,
|
| 142 |
+
"eval_samples_per_second": 10.623,
|
| 143 |
+
"eval_steps_per_second": 1.352,
|
| 144 |
+
"step": 900
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 5.128205128205128,
|
| 148 |
+
"grad_norm": 59.508033752441406,
|
| 149 |
+
"learning_rate": 9.9009e-06,
|
| 150 |
+
"loss": 1.7383,
|
| 151 |
+
"step": 1000
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 5.128205128205128,
|
| 155 |
+
"eval_loss": 1.7986633777618408,
|
| 156 |
+
"eval_runtime": 36.8356,
|
| 157 |
+
"eval_samples_per_second": 10.669,
|
| 158 |
+
"eval_steps_per_second": 1.357,
|
| 159 |
+
"step": 1000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.641025641025641,
|
| 163 |
+
"grad_norm": 71.58872985839844,
|
| 164 |
+
"learning_rate": 9.8909e-06,
|
| 165 |
+
"loss": 1.7361,
|
| 166 |
+
"step": 1100
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 5.641025641025641,
|
| 170 |
+
"eval_loss": 1.7810852527618408,
|
| 171 |
+
"eval_runtime": 37.0957,
|
| 172 |
+
"eval_samples_per_second": 10.594,
|
| 173 |
+
"eval_steps_per_second": 1.348,
|
| 174 |
+
"step": 1100
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 6.153846153846154,
|
| 178 |
+
"grad_norm": 41.782066345214844,
|
| 179 |
+
"learning_rate": 9.8809e-06,
|
| 180 |
+
"loss": 1.682,
|
| 181 |
+
"step": 1200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 6.153846153846154,
|
| 185 |
+
"eval_loss": 1.777554988861084,
|
| 186 |
+
"eval_runtime": 36.9173,
|
| 187 |
+
"eval_samples_per_second": 10.645,
|
| 188 |
+
"eval_steps_per_second": 1.354,
|
| 189 |
+
"step": 1200
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.666666666666667,
|
| 193 |
+
"grad_norm": 40.28728485107422,
|
| 194 |
+
"learning_rate": 9.8709e-06,
|
| 195 |
+
"loss": 1.7216,
|
| 196 |
+
"step": 1300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 6.666666666666667,
|
| 200 |
+
"eval_loss": 1.7382572889328003,
|
| 201 |
+
"eval_runtime": 36.8918,
|
| 202 |
+
"eval_samples_per_second": 10.653,
|
| 203 |
+
"eval_steps_per_second": 1.355,
|
| 204 |
+
"step": 1300
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 7.17948717948718,
|
| 208 |
+
"grad_norm": 104.99211883544922,
|
| 209 |
+
"learning_rate": 9.8609e-06,
|
| 210 |
+
"loss": 1.6534,
|
| 211 |
+
"step": 1400
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 7.17948717948718,
|
| 215 |
+
"eval_loss": 1.76559579372406,
|
| 216 |
+
"eval_runtime": 36.3398,
|
| 217 |
+
"eval_samples_per_second": 10.815,
|
| 218 |
+
"eval_steps_per_second": 1.376,
|
| 219 |
+
"step": 1400
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.6923076923076925,
|
| 223 |
+
"grad_norm": 29.326631546020508,
|
| 224 |
+
"learning_rate": 9.8509e-06,
|
| 225 |
+
"loss": 1.707,
|
| 226 |
+
"step": 1500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 7.6923076923076925,
|
| 230 |
+
"eval_loss": 1.750089406967163,
|
| 231 |
+
"eval_runtime": 36.4098,
|
| 232 |
+
"eval_samples_per_second": 10.794,
|
| 233 |
+
"eval_steps_per_second": 1.373,
|
| 234 |
+
"step": 1500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 8.205128205128204,
|
| 238 |
+
"grad_norm": 37.941261291503906,
|
| 239 |
+
"learning_rate": 9.840900000000001e-06,
|
| 240 |
+
"loss": 1.6554,
|
| 241 |
+
"step": 1600
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.205128205128204,
|
| 245 |
+
"eval_loss": 1.6900651454925537,
|
| 246 |
+
"eval_runtime": 36.3226,
|
| 247 |
+
"eval_samples_per_second": 10.82,
|
| 248 |
+
"eval_steps_per_second": 1.377,
|
| 249 |
+
"step": 1600
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 8.717948717948717,
|
| 253 |
+
"grad_norm": 44.60703659057617,
|
| 254 |
+
"learning_rate": 9.830900000000001e-06,
|
| 255 |
+
"loss": 1.6334,
|
| 256 |
+
"step": 1700
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 8.717948717948717,
|
| 260 |
+
"eval_loss": 1.7162973880767822,
|
| 261 |
+
"eval_runtime": 36.2672,
|
| 262 |
+
"eval_samples_per_second": 10.836,
|
| 263 |
+
"eval_steps_per_second": 1.379,
|
| 264 |
+
"step": 1700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 9.23076923076923,
|
| 268 |
+
"grad_norm": 34.127254486083984,
|
| 269 |
+
"learning_rate": 9.820900000000001e-06,
|
| 270 |
+
"loss": 1.6345,
|
| 271 |
+
"step": 1800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 9.23076923076923,
|
| 275 |
+
"eval_loss": 1.6906001567840576,
|
| 276 |
+
"eval_runtime": 36.2264,
|
| 277 |
+
"eval_samples_per_second": 10.848,
|
| 278 |
+
"eval_steps_per_second": 1.38,
|
| 279 |
+
"step": 1800
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 9.743589743589745,
|
| 283 |
+
"grad_norm": 60.377540588378906,
|
| 284 |
+
"learning_rate": 9.810900000000001e-06,
|
| 285 |
+
"loss": 1.598,
|
| 286 |
+
"step": 1900
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 9.743589743589745,
|
| 290 |
+
"eval_loss": 1.6555503606796265,
|
| 291 |
+
"eval_runtime": 36.3896,
|
| 292 |
+
"eval_samples_per_second": 10.8,
|
| 293 |
+
"eval_steps_per_second": 1.374,
|
| 294 |
+
"step": 1900
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 10.256410256410255,
|
| 298 |
+
"grad_norm": 20.264404296875,
|
| 299 |
+
"learning_rate": 9.800900000000001e-06,
|
| 300 |
+
"loss": 1.5466,
|
| 301 |
+
"step": 2000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 10.256410256410255,
|
| 305 |
+
"eval_loss": 1.648037075996399,
|
| 306 |
+
"eval_runtime": 36.4136,
|
| 307 |
+
"eval_samples_per_second": 10.793,
|
| 308 |
+
"eval_steps_per_second": 1.373,
|
| 309 |
+
"step": 2000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 10.76923076923077,
|
| 313 |
+
"grad_norm": 27.18608856201172,
|
| 314 |
+
"learning_rate": 9.790900000000001e-06,
|
| 315 |
+
"loss": 1.5865,
|
| 316 |
+
"step": 2100
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 10.76923076923077,
|
| 320 |
+
"eval_loss": 1.6171936988830566,
|
| 321 |
+
"eval_runtime": 36.1051,
|
| 322 |
+
"eval_samples_per_second": 10.885,
|
| 323 |
+
"eval_steps_per_second": 1.385,
|
| 324 |
+
"step": 2100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 11.282051282051283,
|
| 328 |
+
"grad_norm": 32.486331939697266,
|
| 329 |
+
"learning_rate": 9.780900000000002e-06,
|
| 330 |
+
"loss": 1.5284,
|
| 331 |
+
"step": 2200
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 11.282051282051283,
|
| 335 |
+
"eval_loss": 1.5915095806121826,
|
| 336 |
+
"eval_runtime": 36.1781,
|
| 337 |
+
"eval_samples_per_second": 10.863,
|
| 338 |
+
"eval_steps_per_second": 1.382,
|
| 339 |
+
"step": 2200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 11.794871794871796,
|
| 343 |
+
"grad_norm": 65.88719940185547,
|
| 344 |
+
"learning_rate": 9.770900000000002e-06,
|
| 345 |
+
"loss": 1.5514,
|
| 346 |
+
"step": 2300
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 11.794871794871796,
|
| 350 |
+
"eval_loss": 1.5879931449890137,
|
| 351 |
+
"eval_runtime": 36.3934,
|
| 352 |
+
"eval_samples_per_second": 10.799,
|
| 353 |
+
"eval_steps_per_second": 1.374,
|
| 354 |
+
"step": 2300
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 12.307692307692308,
|
| 358 |
+
"grad_norm": 31.737024307250977,
|
| 359 |
+
"learning_rate": 9.760900000000002e-06,
|
| 360 |
+
"loss": 1.4941,
|
| 361 |
+
"step": 2400
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 12.307692307692308,
|
| 365 |
+
"eval_loss": 1.583853006362915,
|
| 366 |
+
"eval_runtime": 36.3797,
|
| 367 |
+
"eval_samples_per_second": 10.803,
|
| 368 |
+
"eval_steps_per_second": 1.374,
|
| 369 |
+
"step": 2400
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 12.820512820512821,
|
| 373 |
+
"grad_norm": 45.48268508911133,
|
| 374 |
+
"learning_rate": 9.7509e-06,
|
| 375 |
+
"loss": 1.5097,
|
| 376 |
+
"step": 2500
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 12.820512820512821,
|
| 380 |
+
"eval_loss": 1.5559026002883911,
|
| 381 |
+
"eval_runtime": 36.1605,
|
| 382 |
+
"eval_samples_per_second": 10.868,
|
| 383 |
+
"eval_steps_per_second": 1.383,
|
| 384 |
+
"step": 2500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 13.333333333333334,
|
| 388 |
+
"grad_norm": 27.500398635864258,
|
| 389 |
+
"learning_rate": 9.7409e-06,
|
| 390 |
+
"loss": 1.5018,
|
| 391 |
+
"step": 2600
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 13.333333333333334,
|
| 395 |
+
"eval_loss": 1.5453521013259888,
|
| 396 |
+
"eval_runtime": 36.2887,
|
| 397 |
+
"eval_samples_per_second": 10.83,
|
| 398 |
+
"eval_steps_per_second": 1.378,
|
| 399 |
+
"step": 2600
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 13.846153846153847,
|
| 403 |
+
"grad_norm": 32.49728775024414,
|
| 404 |
+
"learning_rate": 9.7309e-06,
|
| 405 |
+
"loss": 1.4804,
|
| 406 |
+
"step": 2700
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 13.846153846153847,
|
| 410 |
+
"eval_loss": 1.5424816608428955,
|
| 411 |
+
"eval_runtime": 36.359,
|
| 412 |
+
"eval_samples_per_second": 10.809,
|
| 413 |
+
"eval_steps_per_second": 1.375,
|
| 414 |
+
"step": 2700
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 14.35897435897436,
|
| 418 |
+
"grad_norm": 38.46280288696289,
|
| 419 |
+
"learning_rate": 9.7209e-06,
|
| 420 |
+
"loss": 1.4826,
|
| 421 |
+
"step": 2800
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 14.35897435897436,
|
| 425 |
+
"eval_loss": 1.5317177772521973,
|
| 426 |
+
"eval_runtime": 36.3362,
|
| 427 |
+
"eval_samples_per_second": 10.816,
|
| 428 |
+
"eval_steps_per_second": 1.376,
|
| 429 |
+
"step": 2800
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 14.871794871794872,
|
| 433 |
+
"grad_norm": 16.075960159301758,
|
| 434 |
+
"learning_rate": 9.7109e-06,
|
| 435 |
+
"loss": 1.4568,
|
| 436 |
+
"step": 2900
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 14.871794871794872,
|
| 440 |
+
"eval_loss": 1.5241832733154297,
|
| 441 |
+
"eval_runtime": 36.2025,
|
| 442 |
+
"eval_samples_per_second": 10.856,
|
| 443 |
+
"eval_steps_per_second": 1.381,
|
| 444 |
+
"step": 2900
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 15.384615384615385,
|
| 448 |
+
"grad_norm": 27.334318161010742,
|
| 449 |
+
"learning_rate": 9.7009e-06,
|
| 450 |
+
"loss": 1.4176,
|
| 451 |
+
"step": 3000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 15.384615384615385,
|
| 455 |
+
"eval_loss": 1.520580768585205,
|
| 456 |
+
"eval_runtime": 36.398,
|
| 457 |
+
"eval_samples_per_second": 10.797,
|
| 458 |
+
"eval_steps_per_second": 1.374,
|
| 459 |
+
"step": 3000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 15.897435897435898,
|
| 463 |
+
"grad_norm": 94.90784454345703,
|
| 464 |
+
"learning_rate": 9.6909e-06,
|
| 465 |
+
"loss": 1.4681,
|
| 466 |
+
"step": 3100
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 15.897435897435898,
|
| 470 |
+
"eval_loss": 1.5268648862838745,
|
| 471 |
+
"eval_runtime": 36.0541,
|
| 472 |
+
"eval_samples_per_second": 10.9,
|
| 473 |
+
"eval_steps_per_second": 1.387,
|
| 474 |
+
"step": 3100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 16.41025641025641,
|
| 478 |
+
"grad_norm": 16.697856903076172,
|
| 479 |
+
"learning_rate": 9.6809e-06,
|
| 480 |
+
"loss": 1.454,
|
| 481 |
+
"step": 3200
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 16.41025641025641,
|
| 485 |
+
"eval_loss": 1.5157753229141235,
|
| 486 |
+
"eval_runtime": 36.3172,
|
| 487 |
+
"eval_samples_per_second": 10.821,
|
| 488 |
+
"eval_steps_per_second": 1.377,
|
| 489 |
+
"step": 3200
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 16.923076923076923,
|
| 493 |
+
"grad_norm": 54.05553436279297,
|
| 494 |
+
"learning_rate": 9.670900000000001e-06,
|
| 495 |
+
"loss": 1.4309,
|
| 496 |
+
"step": 3300
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 16.923076923076923,
|
| 500 |
+
"eval_loss": 1.516249179840088,
|
| 501 |
+
"eval_runtime": 36.2632,
|
| 502 |
+
"eval_samples_per_second": 10.837,
|
| 503 |
+
"eval_steps_per_second": 1.379,
|
| 504 |
+
"step": 3300
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 17.435897435897434,
|
| 508 |
+
"grad_norm": 47.010475158691406,
|
| 509 |
+
"learning_rate": 9.660900000000001e-06,
|
| 510 |
+
"loss": 1.4571,
|
| 511 |
+
"step": 3400
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 17.435897435897434,
|
| 515 |
+
"eval_loss": 1.5018247365951538,
|
| 516 |
+
"eval_runtime": 36.2118,
|
| 517 |
+
"eval_samples_per_second": 10.853,
|
| 518 |
+
"eval_steps_per_second": 1.381,
|
| 519 |
+
"step": 3400
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 17.94871794871795,
|
| 523 |
+
"grad_norm": 52.865718841552734,
|
| 524 |
+
"learning_rate": 9.650900000000001e-06,
|
| 525 |
+
"loss": 1.4168,
|
| 526 |
+
"step": 3500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 17.94871794871795,
|
| 530 |
+
"eval_loss": 1.4993616342544556,
|
| 531 |
+
"eval_runtime": 36.2572,
|
| 532 |
+
"eval_samples_per_second": 10.839,
|
| 533 |
+
"eval_steps_per_second": 1.379,
|
| 534 |
+
"step": 3500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 18.46153846153846,
|
| 538 |
+
"grad_norm": 30.117380142211914,
|
| 539 |
+
"learning_rate": 9.640900000000001e-06,
|
| 540 |
+
"loss": 1.4275,
|
| 541 |
+
"step": 3600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 18.46153846153846,
|
| 545 |
+
"eval_loss": 1.4899998903274536,
|
| 546 |
+
"eval_runtime": 36.4696,
|
| 547 |
+
"eval_samples_per_second": 10.776,
|
| 548 |
+
"eval_steps_per_second": 1.371,
|
| 549 |
+
"step": 3600
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 18.974358974358974,
|
| 553 |
+
"grad_norm": 31.10028076171875,
|
| 554 |
+
"learning_rate": 9.630900000000001e-06,
|
| 555 |
+
"loss": 1.4148,
|
| 556 |
+
"step": 3700
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 18.974358974358974,
|
| 560 |
+
"eval_loss": 1.5231629610061646,
|
| 561 |
+
"eval_runtime": 36.4604,
|
| 562 |
+
"eval_samples_per_second": 10.779,
|
| 563 |
+
"eval_steps_per_second": 1.371,
|
| 564 |
+
"step": 3700
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 19.487179487179485,
|
| 568 |
+
"grad_norm": 44.06697082519531,
|
| 569 |
+
"learning_rate": 9.620900000000001e-06,
|
| 570 |
+
"loss": 1.4057,
|
| 571 |
+
"step": 3800
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 19.487179487179485,
|
| 575 |
+
"eval_loss": 1.4841217994689941,
|
| 576 |
+
"eval_runtime": 36.3382,
|
| 577 |
+
"eval_samples_per_second": 10.815,
|
| 578 |
+
"eval_steps_per_second": 1.376,
|
| 579 |
+
"step": 3800
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 20.0,
|
| 583 |
+
"grad_norm": 53.86429214477539,
|
| 584 |
+
"learning_rate": 9.610900000000001e-06,
|
| 585 |
+
"loss": 1.4302,
|
| 586 |
+
"step": 3900
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 20.0,
|
| 590 |
+
"eval_loss": 1.477772831916809,
|
| 591 |
+
"eval_runtime": 36.1794,
|
| 592 |
+
"eval_samples_per_second": 10.863,
|
| 593 |
+
"eval_steps_per_second": 1.382,
|
| 594 |
+
"step": 3900
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 20.51282051282051,
|
| 598 |
+
"grad_norm": 80.95457458496094,
|
| 599 |
+
"learning_rate": 9.600900000000002e-06,
|
| 600 |
+
"loss": 1.4076,
|
| 601 |
+
"step": 4000
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 20.51282051282051,
|
| 605 |
+
"eval_loss": 1.4769134521484375,
|
| 606 |
+
"eval_runtime": 36.4725,
|
| 607 |
+
"eval_samples_per_second": 10.775,
|
| 608 |
+
"eval_steps_per_second": 1.371,
|
| 609 |
+
"step": 4000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 21.025641025641026,
|
| 613 |
+
"grad_norm": 32.276214599609375,
|
| 614 |
+
"learning_rate": 9.5909e-06,
|
| 615 |
+
"loss": 1.3868,
|
| 616 |
+
"step": 4100
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 21.025641025641026,
|
| 620 |
+
"eval_loss": 1.463292121887207,
|
| 621 |
+
"eval_runtime": 36.5192,
|
| 622 |
+
"eval_samples_per_second": 10.761,
|
| 623 |
+
"eval_steps_per_second": 1.369,
|
| 624 |
+
"step": 4100
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 21.53846153846154,
|
| 628 |
+
"grad_norm": 54.65959167480469,
|
| 629 |
+
"learning_rate": 9.5809e-06,
|
| 630 |
+
"loss": 1.3795,
|
| 631 |
+
"step": 4200
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 21.53846153846154,
|
| 635 |
+
"eval_loss": 1.4630039930343628,
|
| 636 |
+
"eval_runtime": 36.5288,
|
| 637 |
+
"eval_samples_per_second": 10.759,
|
| 638 |
+
"eval_steps_per_second": 1.369,
|
| 639 |
+
"step": 4200
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 22.05128205128205,
|
| 643 |
+
"grad_norm": 42.31818389892578,
|
| 644 |
+
"learning_rate": 9.5709e-06,
|
| 645 |
+
"loss": 1.3787,
|
| 646 |
+
"step": 4300
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 22.05128205128205,
|
| 650 |
+
"eval_loss": 1.4471133947372437,
|
| 651 |
+
"eval_runtime": 36.2949,
|
| 652 |
+
"eval_samples_per_second": 10.828,
|
| 653 |
+
"eval_steps_per_second": 1.378,
|
| 654 |
+
"step": 4300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 22.564102564102566,
|
| 658 |
+
"grad_norm": 34.44257736206055,
|
| 659 |
+
"learning_rate": 9.5609e-06,
|
| 660 |
+
"loss": 1.4027,
|
| 661 |
+
"step": 4400
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 22.564102564102566,
|
| 665 |
+
"eval_loss": 1.4606964588165283,
|
| 666 |
+
"eval_runtime": 36.5672,
|
| 667 |
+
"eval_samples_per_second": 10.747,
|
| 668 |
+
"eval_steps_per_second": 1.367,
|
| 669 |
+
"step": 4400
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 23.076923076923077,
|
| 673 |
+
"grad_norm": 42.65989303588867,
|
| 674 |
+
"learning_rate": 9.5509e-06,
|
| 675 |
+
"loss": 1.3459,
|
| 676 |
+
"step": 4500
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 23.076923076923077,
|
| 680 |
+
"eval_loss": 1.454709768295288,
|
| 681 |
+
"eval_runtime": 37.2024,
|
| 682 |
+
"eval_samples_per_second": 10.564,
|
| 683 |
+
"eval_steps_per_second": 1.344,
|
| 684 |
+
"step": 4500
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 23.58974358974359,
|
| 688 |
+
"grad_norm": 35.11396789550781,
|
| 689 |
+
"learning_rate": 9.5409e-06,
|
| 690 |
+
"loss": 1.3367,
|
| 691 |
+
"step": 4600
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 23.58974358974359,
|
| 695 |
+
"eval_loss": 1.4562979936599731,
|
| 696 |
+
"eval_runtime": 36.4579,
|
| 697 |
+
"eval_samples_per_second": 10.78,
|
| 698 |
+
"eval_steps_per_second": 1.371,
|
| 699 |
+
"step": 4600
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 24.102564102564102,
|
| 703 |
+
"grad_norm": 32.71805953979492,
|
| 704 |
+
"learning_rate": 9.5309e-06,
|
| 705 |
+
"loss": 1.3575,
|
| 706 |
+
"step": 4700
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 24.102564102564102,
|
| 710 |
+
"eval_loss": 1.4620144367218018,
|
| 711 |
+
"eval_runtime": 36.4055,
|
| 712 |
+
"eval_samples_per_second": 10.795,
|
| 713 |
+
"eval_steps_per_second": 1.373,
|
| 714 |
+
"step": 4700
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 24.615384615384617,
|
| 718 |
+
"grad_norm": 28.839757919311523,
|
| 719 |
+
"learning_rate": 9.5209e-06,
|
| 720 |
+
"loss": 1.3549,
|
| 721 |
+
"step": 4800
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 24.615384615384617,
|
| 725 |
+
"eval_loss": 1.4431304931640625,
|
| 726 |
+
"eval_runtime": 36.5027,
|
| 727 |
+
"eval_samples_per_second": 10.766,
|
| 728 |
+
"eval_steps_per_second": 1.37,
|
| 729 |
+
"step": 4800
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 25.128205128205128,
|
| 733 |
+
"grad_norm": 45.3994140625,
|
| 734 |
+
"learning_rate": 9.5109e-06,
|
| 735 |
+
"loss": 1.3885,
|
| 736 |
+
"step": 4900
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 25.128205128205128,
|
| 740 |
+
"eval_loss": 1.4312200546264648,
|
| 741 |
+
"eval_runtime": 36.3039,
|
| 742 |
+
"eval_samples_per_second": 10.825,
|
| 743 |
+
"eval_steps_per_second": 1.377,
|
| 744 |
+
"step": 4900
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 25.641025641025642,
|
| 748 |
+
"grad_norm": 22.972829818725586,
|
| 749 |
+
"learning_rate": 9.5009e-06,
|
| 750 |
+
"loss": 1.3469,
|
| 751 |
+
"step": 5000
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 25.641025641025642,
|
| 755 |
+
"eval_loss": 1.416171669960022,
|
| 756 |
+
"eval_runtime": 36.6695,
|
| 757 |
+
"eval_samples_per_second": 10.717,
|
| 758 |
+
"eval_steps_per_second": 1.364,
|
| 759 |
+
"step": 5000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 26.153846153846153,
|
| 763 |
+
"grad_norm": 77.40106964111328,
|
| 764 |
+
"learning_rate": 9.490900000000001e-06,
|
| 765 |
+
"loss": 1.3363,
|
| 766 |
+
"step": 5100
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 26.153846153846153,
|
| 770 |
+
"eval_loss": 1.4090278148651123,
|
| 771 |
+
"eval_runtime": 36.2573,
|
| 772 |
+
"eval_samples_per_second": 10.839,
|
| 773 |
+
"eval_steps_per_second": 1.379,
|
| 774 |
+
"step": 5100
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 26.666666666666668,
|
| 778 |
+
"grad_norm": 29.757932662963867,
|
| 779 |
+
"learning_rate": 9.480900000000001e-06,
|
| 780 |
+
"loss": 1.3183,
|
| 781 |
+
"step": 5200
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 26.666666666666668,
|
| 785 |
+
"eval_loss": 1.4073749780654907,
|
| 786 |
+
"eval_runtime": 36.2439,
|
| 787 |
+
"eval_samples_per_second": 10.843,
|
| 788 |
+
"eval_steps_per_second": 1.38,
|
| 789 |
+
"step": 5200
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 27.17948717948718,
|
| 793 |
+
"grad_norm": 56.78797149658203,
|
| 794 |
+
"learning_rate": 9.470900000000001e-06,
|
| 795 |
+
"loss": 1.3568,
|
| 796 |
+
"step": 5300
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 27.17948717948718,
|
| 800 |
+
"eval_loss": 1.4153741598129272,
|
| 801 |
+
"eval_runtime": 36.2756,
|
| 802 |
+
"eval_samples_per_second": 10.834,
|
| 803 |
+
"eval_steps_per_second": 1.378,
|
| 804 |
+
"step": 5300
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 27.692307692307693,
|
| 808 |
+
"grad_norm": 62.353477478027344,
|
| 809 |
+
"learning_rate": 9.460900000000001e-06,
|
| 810 |
+
"loss": 1.3304,
|
| 811 |
+
"step": 5400
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 27.692307692307693,
|
| 815 |
+
"eval_loss": 1.4334921836853027,
|
| 816 |
+
"eval_runtime": 36.2626,
|
| 817 |
+
"eval_samples_per_second": 10.838,
|
| 818 |
+
"eval_steps_per_second": 1.379,
|
| 819 |
+
"step": 5400
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 28.205128205128204,
|
| 823 |
+
"grad_norm": 100.7852554321289,
|
| 824 |
+
"learning_rate": 9.450900000000001e-06,
|
| 825 |
+
"loss": 1.2897,
|
| 826 |
+
"step": 5500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 28.205128205128204,
|
| 830 |
+
"eval_loss": 1.4160270690917969,
|
| 831 |
+
"eval_runtime": 36.6139,
|
| 832 |
+
"eval_samples_per_second": 10.734,
|
| 833 |
+
"eval_steps_per_second": 1.366,
|
| 834 |
+
"step": 5500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 28.71794871794872,
|
| 838 |
+
"grad_norm": 62.06657409667969,
|
| 839 |
+
"learning_rate": 9.440900000000001e-06,
|
| 840 |
+
"loss": 1.3233,
|
| 841 |
+
"step": 5600
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 28.71794871794872,
|
| 845 |
+
"eval_loss": 1.431317687034607,
|
| 846 |
+
"eval_runtime": 36.5341,
|
| 847 |
+
"eval_samples_per_second": 10.757,
|
| 848 |
+
"eval_steps_per_second": 1.369,
|
| 849 |
+
"step": 5600
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 29.23076923076923,
|
| 853 |
+
"grad_norm": 32.661346435546875,
|
| 854 |
+
"learning_rate": 9.4309e-06,
|
| 855 |
+
"loss": 1.305,
|
| 856 |
+
"step": 5700
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 29.23076923076923,
|
| 860 |
+
"eval_loss": 1.3954827785491943,
|
| 861 |
+
"eval_runtime": 36.5903,
|
| 862 |
+
"eval_samples_per_second": 10.741,
|
| 863 |
+
"eval_steps_per_second": 1.366,
|
| 864 |
+
"step": 5700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 29.743589743589745,
|
| 868 |
+
"grad_norm": 25.690454483032227,
|
| 869 |
+
"learning_rate": 9.421000000000002e-06,
|
| 870 |
+
"loss": 1.2961,
|
| 871 |
+
"step": 5800
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 29.743589743589745,
|
| 875 |
+
"eval_loss": 1.4036046266555786,
|
| 876 |
+
"eval_runtime": 36.5935,
|
| 877 |
+
"eval_samples_per_second": 10.74,
|
| 878 |
+
"eval_steps_per_second": 1.366,
|
| 879 |
+
"step": 5800
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 30.256410256410255,
|
| 883 |
+
"grad_norm": 45.45426940917969,
|
| 884 |
+
"learning_rate": 9.411000000000002e-06,
|
| 885 |
+
"loss": 1.3175,
|
| 886 |
+
"step": 5900
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 30.256410256410255,
|
| 890 |
+
"eval_loss": 1.3845292329788208,
|
| 891 |
+
"eval_runtime": 36.5594,
|
| 892 |
+
"eval_samples_per_second": 10.75,
|
| 893 |
+
"eval_steps_per_second": 1.368,
|
| 894 |
+
"step": 5900
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 30.76923076923077,
|
| 898 |
+
"grad_norm": 41.62439727783203,
|
| 899 |
+
"learning_rate": 9.401000000000002e-06,
|
| 900 |
+
"loss": 1.3242,
|
| 901 |
+
"step": 6000
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 30.76923076923077,
|
| 905 |
+
"eval_loss": 1.3939634561538696,
|
| 906 |
+
"eval_runtime": 36.4895,
|
| 907 |
+
"eval_samples_per_second": 10.77,
|
| 908 |
+
"eval_steps_per_second": 1.37,
|
| 909 |
+
"step": 6000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 31.28205128205128,
|
| 913 |
+
"grad_norm": 26.999319076538086,
|
| 914 |
+
"learning_rate": 9.391e-06,
|
| 915 |
+
"loss": 1.2886,
|
| 916 |
+
"step": 6100
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 31.28205128205128,
|
| 920 |
+
"eval_loss": 1.3804558515548706,
|
| 921 |
+
"eval_runtime": 36.2599,
|
| 922 |
+
"eval_samples_per_second": 10.838,
|
| 923 |
+
"eval_steps_per_second": 1.379,
|
| 924 |
+
"step": 6100
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 31.794871794871796,
|
| 928 |
+
"grad_norm": 24.70287322998047,
|
| 929 |
+
"learning_rate": 9.381e-06,
|
| 930 |
+
"loss": 1.2893,
|
| 931 |
+
"step": 6200
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 31.794871794871796,
|
| 935 |
+
"eval_loss": 1.3821990489959717,
|
| 936 |
+
"eval_runtime": 36.2613,
|
| 937 |
+
"eval_samples_per_second": 10.838,
|
| 938 |
+
"eval_steps_per_second": 1.379,
|
| 939 |
+
"step": 6200
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 32.30769230769231,
|
| 943 |
+
"grad_norm": 41.910606384277344,
|
| 944 |
+
"learning_rate": 9.371e-06,
|
| 945 |
+
"loss": 1.3093,
|
| 946 |
+
"step": 6300
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 32.30769230769231,
|
| 950 |
+
"eval_loss": 1.3875064849853516,
|
| 951 |
+
"eval_runtime": 36.4998,
|
| 952 |
+
"eval_samples_per_second": 10.767,
|
| 953 |
+
"eval_steps_per_second": 1.37,
|
| 954 |
+
"step": 6300
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 32.82051282051282,
|
| 958 |
+
"grad_norm": 82.20216369628906,
|
| 959 |
+
"learning_rate": 9.361e-06,
|
| 960 |
+
"loss": 1.3184,
|
| 961 |
+
"step": 6400
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 32.82051282051282,
|
| 965 |
+
"eval_loss": 1.3840612173080444,
|
| 966 |
+
"eval_runtime": 36.4787,
|
| 967 |
+
"eval_samples_per_second": 10.773,
|
| 968 |
+
"eval_steps_per_second": 1.371,
|
| 969 |
+
"step": 6400
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 33.333333333333336,
|
| 973 |
+
"grad_norm": 797.53271484375,
|
| 974 |
+
"learning_rate": 9.351e-06,
|
| 975 |
+
"loss": 1.2939,
|
| 976 |
+
"step": 6500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 33.333333333333336,
|
| 980 |
+
"eval_loss": 1.3881950378417969,
|
| 981 |
+
"eval_runtime": 36.4166,
|
| 982 |
+
"eval_samples_per_second": 10.792,
|
| 983 |
+
"eval_steps_per_second": 1.373,
|
| 984 |
+
"step": 6500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 33.84615384615385,
|
| 988 |
+
"grad_norm": 35.14693069458008,
|
| 989 |
+
"learning_rate": 9.341000000000001e-06,
|
| 990 |
+
"loss": 1.2881,
|
| 991 |
+
"step": 6600
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 33.84615384615385,
|
| 995 |
+
"eval_loss": 1.4039666652679443,
|
| 996 |
+
"eval_runtime": 36.4141,
|
| 997 |
+
"eval_samples_per_second": 10.793,
|
| 998 |
+
"eval_steps_per_second": 1.373,
|
| 999 |
+
"step": 6600
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 34.35897435897436,
|
| 1003 |
+
"grad_norm": 38.676666259765625,
|
| 1004 |
+
"learning_rate": 9.331000000000001e-06,
|
| 1005 |
+
"loss": 1.2699,
|
| 1006 |
+
"step": 6700
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 34.35897435897436,
|
| 1010 |
+
"eval_loss": 1.3800386190414429,
|
| 1011 |
+
"eval_runtime": 36.2367,
|
| 1012 |
+
"eval_samples_per_second": 10.845,
|
| 1013 |
+
"eval_steps_per_second": 1.38,
|
| 1014 |
+
"step": 6700
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 34.87179487179487,
|
| 1018 |
+
"grad_norm": 26.051170349121094,
|
| 1019 |
+
"learning_rate": 9.321000000000001e-06,
|
| 1020 |
+
"loss": 1.3079,
|
| 1021 |
+
"step": 6800
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 34.87179487179487,
|
| 1025 |
+
"eval_loss": 1.3784704208374023,
|
| 1026 |
+
"eval_runtime": 36.3119,
|
| 1027 |
+
"eval_samples_per_second": 10.823,
|
| 1028 |
+
"eval_steps_per_second": 1.377,
|
| 1029 |
+
"step": 6800
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 35.38461538461539,
|
| 1033 |
+
"grad_norm": 42.667236328125,
|
| 1034 |
+
"learning_rate": 9.311000000000001e-06,
|
| 1035 |
+
"loss": 1.2622,
|
| 1036 |
+
"step": 6900
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 35.38461538461539,
|
| 1040 |
+
"eval_loss": 1.3637058734893799,
|
| 1041 |
+
"eval_runtime": 36.1116,
|
| 1042 |
+
"eval_samples_per_second": 10.883,
|
| 1043 |
+
"eval_steps_per_second": 1.385,
|
| 1044 |
+
"step": 6900
|
| 1045 |
+
},
|
| 1046 |
+
{
|
| 1047 |
+
"epoch": 35.8974358974359,
|
| 1048 |
+
"grad_norm": 38.78388977050781,
|
| 1049 |
+
"learning_rate": 9.301000000000001e-06,
|
| 1050 |
+
"loss": 1.2652,
|
| 1051 |
+
"step": 7000
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 35.8974358974359,
|
| 1055 |
+
"eval_loss": 1.3452589511871338,
|
| 1056 |
+
"eval_runtime": 36.2593,
|
| 1057 |
+
"eval_samples_per_second": 10.839,
|
| 1058 |
+
"eval_steps_per_second": 1.379,
|
| 1059 |
+
"step": 7000
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 36.41025641025641,
|
| 1063 |
+
"grad_norm": 44.43967056274414,
|
| 1064 |
+
"learning_rate": 9.291000000000001e-06,
|
| 1065 |
+
"loss": 1.2378,
|
| 1066 |
+
"step": 7100
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 36.41025641025641,
|
| 1070 |
+
"eval_loss": 1.3494073152542114,
|
| 1071 |
+
"eval_runtime": 35.4402,
|
| 1072 |
+
"eval_samples_per_second": 11.089,
|
| 1073 |
+
"eval_steps_per_second": 1.411,
|
| 1074 |
+
"step": 7100
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 36.92307692307692,
|
| 1078 |
+
"grad_norm": 49.02131271362305,
|
| 1079 |
+
"learning_rate": 9.281000000000001e-06,
|
| 1080 |
+
"loss": 1.2932,
|
| 1081 |
+
"step": 7200
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 36.92307692307692,
|
| 1085 |
+
"eval_loss": 1.3460158109664917,
|
| 1086 |
+
"eval_runtime": 35.9361,
|
| 1087 |
+
"eval_samples_per_second": 10.936,
|
| 1088 |
+
"eval_steps_per_second": 1.391,
|
| 1089 |
+
"step": 7200
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 37.43589743589744,
|
| 1093 |
+
"grad_norm": 28.279098510742188,
|
| 1094 |
+
"learning_rate": 9.271000000000002e-06,
|
| 1095 |
+
"loss": 1.2598,
|
| 1096 |
+
"step": 7300
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 37.43589743589744,
|
| 1100 |
+
"eval_loss": 1.36253023147583,
|
| 1101 |
+
"eval_runtime": 36.2944,
|
| 1102 |
+
"eval_samples_per_second": 10.828,
|
| 1103 |
+
"eval_steps_per_second": 1.378,
|
| 1104 |
+
"step": 7300
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 37.94871794871795,
|
| 1108 |
+
"grad_norm": 35.21017074584961,
|
| 1109 |
+
"learning_rate": 9.261000000000002e-06,
|
| 1110 |
+
"loss": 1.2703,
|
| 1111 |
+
"step": 7400
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 37.94871794871795,
|
| 1115 |
+
"eval_loss": 1.3509865999221802,
|
| 1116 |
+
"eval_runtime": 36.2661,
|
| 1117 |
+
"eval_samples_per_second": 10.837,
|
| 1118 |
+
"eval_steps_per_second": 1.379,
|
| 1119 |
+
"step": 7400
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 38.46153846153846,
|
| 1123 |
+
"grad_norm": 51.673316955566406,
|
| 1124 |
+
"learning_rate": 9.251000000000002e-06,
|
| 1125 |
+
"loss": 1.2393,
|
| 1126 |
+
"step": 7500
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 38.46153846153846,
|
| 1130 |
+
"eval_loss": 1.3402855396270752,
|
| 1131 |
+
"eval_runtime": 36.392,
|
| 1132 |
+
"eval_samples_per_second": 10.799,
|
| 1133 |
+
"eval_steps_per_second": 1.374,
|
| 1134 |
+
"step": 7500
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 38.97435897435897,
|
| 1138 |
+
"grad_norm": 53.73936462402344,
|
| 1139 |
+
"learning_rate": 9.241000000000002e-06,
|
| 1140 |
+
"loss": 1.2577,
|
| 1141 |
+
"step": 7600
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 38.97435897435897,
|
| 1145 |
+
"eval_loss": 1.3487578630447388,
|
| 1146 |
+
"eval_runtime": 36.2119,
|
| 1147 |
+
"eval_samples_per_second": 10.853,
|
| 1148 |
+
"eval_steps_per_second": 1.381,
|
| 1149 |
+
"step": 7600
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 39.48717948717949,
|
| 1153 |
+
"grad_norm": 55.994686126708984,
|
| 1154 |
+
"learning_rate": 9.231000000000002e-06,
|
| 1155 |
+
"loss": 1.229,
|
| 1156 |
+
"step": 7700
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 39.48717948717949,
|
| 1160 |
+
"eval_loss": 1.340031623840332,
|
| 1161 |
+
"eval_runtime": 36.2063,
|
| 1162 |
+
"eval_samples_per_second": 10.854,
|
| 1163 |
+
"eval_steps_per_second": 1.381,
|
| 1164 |
+
"step": 7700
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 40.0,
|
| 1168 |
+
"grad_norm": 86.7531509399414,
|
| 1169 |
+
"learning_rate": 9.221e-06,
|
| 1170 |
+
"loss": 1.2941,
|
| 1171 |
+
"step": 7800
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 40.0,
|
| 1175 |
+
"eval_loss": 1.3422337770462036,
|
| 1176 |
+
"eval_runtime": 36.7462,
|
| 1177 |
+
"eval_samples_per_second": 10.695,
|
| 1178 |
+
"eval_steps_per_second": 1.361,
|
| 1179 |
+
"step": 7800
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 40.51282051282051,
|
| 1183 |
+
"grad_norm": 60.86371612548828,
|
| 1184 |
+
"learning_rate": 9.211e-06,
|
| 1185 |
+
"loss": 1.2423,
|
| 1186 |
+
"step": 7900
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 40.51282051282051,
|
| 1190 |
+
"eval_loss": 1.3336257934570312,
|
| 1191 |
+
"eval_runtime": 36.2441,
|
| 1192 |
+
"eval_samples_per_second": 10.843,
|
| 1193 |
+
"eval_steps_per_second": 1.38,
|
| 1194 |
+
"step": 7900
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 41.02564102564103,
|
| 1198 |
+
"grad_norm": 28.535411834716797,
|
| 1199 |
+
"learning_rate": 9.2011e-06,
|
| 1200 |
+
"loss": 1.2676,
|
| 1201 |
+
"step": 8000
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 41.02564102564103,
|
| 1205 |
+
"eval_loss": 1.338461995124817,
|
| 1206 |
+
"eval_runtime": 36.2212,
|
| 1207 |
+
"eval_samples_per_second": 10.85,
|
| 1208 |
+
"eval_steps_per_second": 1.38,
|
| 1209 |
+
"step": 8000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 41.53846153846154,
|
| 1213 |
+
"grad_norm": 35.707183837890625,
|
| 1214 |
+
"learning_rate": 9.1911e-06,
|
| 1215 |
+
"loss": 1.2428,
|
| 1216 |
+
"step": 8100
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 41.53846153846154,
|
| 1220 |
+
"eval_loss": 1.3225666284561157,
|
| 1221 |
+
"eval_runtime": 36.2043,
|
| 1222 |
+
"eval_samples_per_second": 10.855,
|
| 1223 |
+
"eval_steps_per_second": 1.381,
|
| 1224 |
+
"step": 8100
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 42.05128205128205,
|
| 1228 |
+
"grad_norm": 29.23111343383789,
|
| 1229 |
+
"learning_rate": 9.181100000000001e-06,
|
| 1230 |
+
"loss": 1.2269,
|
| 1231 |
+
"step": 8200
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 42.05128205128205,
|
| 1235 |
+
"eval_loss": 1.3405094146728516,
|
| 1236 |
+
"eval_runtime": 36.2498,
|
| 1237 |
+
"eval_samples_per_second": 10.841,
|
| 1238 |
+
"eval_steps_per_second": 1.379,
|
| 1239 |
+
"step": 8200
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 42.56410256410256,
|
| 1243 |
+
"grad_norm": 20.379304885864258,
|
| 1244 |
+
"learning_rate": 9.171100000000001e-06,
|
| 1245 |
+
"loss": 1.2187,
|
| 1246 |
+
"step": 8300
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 42.56410256410256,
|
| 1250 |
+
"eval_loss": 1.3247309923171997,
|
| 1251 |
+
"eval_runtime": 36.3237,
|
| 1252 |
+
"eval_samples_per_second": 10.819,
|
| 1253 |
+
"eval_steps_per_second": 1.377,
|
| 1254 |
+
"step": 8300
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 43.07692307692308,
|
| 1258 |
+
"grad_norm": 44.43791198730469,
|
| 1259 |
+
"learning_rate": 9.161100000000001e-06,
|
| 1260 |
+
"loss": 1.2321,
|
| 1261 |
+
"step": 8400
|
| 1262 |
+
},
|
| 1263 |
+
{
|
| 1264 |
+
"epoch": 43.07692307692308,
|
| 1265 |
+
"eval_loss": 1.334086298942566,
|
| 1266 |
+
"eval_runtime": 36.2039,
|
| 1267 |
+
"eval_samples_per_second": 10.855,
|
| 1268 |
+
"eval_steps_per_second": 1.381,
|
| 1269 |
+
"step": 8400
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 43.58974358974359,
|
| 1273 |
+
"grad_norm": 30.97890853881836,
|
| 1274 |
+
"learning_rate": 9.151100000000001e-06,
|
| 1275 |
+
"loss": 1.2071,
|
| 1276 |
+
"step": 8500
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 43.58974358974359,
|
| 1280 |
+
"eval_loss": 1.3306576013565063,
|
| 1281 |
+
"eval_runtime": 36.3547,
|
| 1282 |
+
"eval_samples_per_second": 10.81,
|
| 1283 |
+
"eval_steps_per_second": 1.375,
|
| 1284 |
+
"step": 8500
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 44.1025641025641,
|
| 1288 |
+
"grad_norm": 40.07706832885742,
|
| 1289 |
+
"learning_rate": 9.141100000000001e-06,
|
| 1290 |
+
"loss": 1.25,
|
| 1291 |
+
"step": 8600
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 44.1025641025641,
|
| 1295 |
+
"eval_loss": 1.3270679712295532,
|
| 1296 |
+
"eval_runtime": 36.1754,
|
| 1297 |
+
"eval_samples_per_second": 10.864,
|
| 1298 |
+
"eval_steps_per_second": 1.382,
|
| 1299 |
+
"step": 8600
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 44.61538461538461,
|
| 1303 |
+
"grad_norm": 27.011186599731445,
|
| 1304 |
+
"learning_rate": 9.1311e-06,
|
| 1305 |
+
"loss": 1.1968,
|
| 1306 |
+
"step": 8700
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 44.61538461538461,
|
| 1310 |
+
"eval_loss": 1.3117327690124512,
|
| 1311 |
+
"eval_runtime": 36.1727,
|
| 1312 |
+
"eval_samples_per_second": 10.865,
|
| 1313 |
+
"eval_steps_per_second": 1.382,
|
| 1314 |
+
"step": 8700
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 45.12820512820513,
|
| 1318 |
+
"grad_norm": 25.976228713989258,
|
| 1319 |
+
"learning_rate": 9.1211e-06,
|
| 1320 |
+
"loss": 1.2492,
|
| 1321 |
+
"step": 8800
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 45.12820512820513,
|
| 1325 |
+
"eval_loss": 1.3281300067901611,
|
| 1326 |
+
"eval_runtime": 36.2531,
|
| 1327 |
+
"eval_samples_per_second": 10.84,
|
| 1328 |
+
"eval_steps_per_second": 1.379,
|
| 1329 |
+
"step": 8800
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 45.64102564102564,
|
| 1333 |
+
"grad_norm": 21.215715408325195,
|
| 1334 |
+
"learning_rate": 9.1111e-06,
|
| 1335 |
+
"loss": 1.221,
|
| 1336 |
+
"step": 8900
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 45.64102564102564,
|
| 1340 |
+
"eval_loss": 1.3373734951019287,
|
| 1341 |
+
"eval_runtime": 36.2242,
|
| 1342 |
+
"eval_samples_per_second": 10.849,
|
| 1343 |
+
"eval_steps_per_second": 1.38,
|
| 1344 |
+
"step": 8900
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 46.15384615384615,
|
| 1348 |
+
"grad_norm": 48.8258171081543,
|
| 1349 |
+
"learning_rate": 9.1011e-06,
|
| 1350 |
+
"loss": 1.2123,
|
| 1351 |
+
"step": 9000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 46.15384615384615,
|
| 1355 |
+
"eval_loss": 1.3303853273391724,
|
| 1356 |
+
"eval_runtime": 36.4019,
|
| 1357 |
+
"eval_samples_per_second": 10.796,
|
| 1358 |
+
"eval_steps_per_second": 1.374,
|
| 1359 |
+
"step": 9000
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 46.666666666666664,
|
| 1363 |
+
"grad_norm": 36.76605224609375,
|
| 1364 |
+
"learning_rate": 9.0911e-06,
|
| 1365 |
+
"loss": 1.1951,
|
| 1366 |
+
"step": 9100
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 46.666666666666664,
|
| 1370 |
+
"eval_loss": 1.3182373046875,
|
| 1371 |
+
"eval_runtime": 36.387,
|
| 1372 |
+
"eval_samples_per_second": 10.801,
|
| 1373 |
+
"eval_steps_per_second": 1.374,
|
| 1374 |
+
"step": 9100
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 47.17948717948718,
|
| 1378 |
+
"grad_norm": 40.79771423339844,
|
| 1379 |
+
"learning_rate": 9.0811e-06,
|
| 1380 |
+
"loss": 1.2155,
|
| 1381 |
+
"step": 9200
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 47.17948717948718,
|
| 1385 |
+
"eval_loss": 1.3303160667419434,
|
| 1386 |
+
"eval_runtime": 36.2265,
|
| 1387 |
+
"eval_samples_per_second": 10.848,
|
| 1388 |
+
"eval_steps_per_second": 1.38,
|
| 1389 |
+
"step": 9200
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 47.69230769230769,
|
| 1393 |
+
"grad_norm": 48.06431579589844,
|
| 1394 |
+
"learning_rate": 9.0711e-06,
|
| 1395 |
+
"loss": 1.2236,
|
| 1396 |
+
"step": 9300
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 47.69230769230769,
|
| 1400 |
+
"eval_loss": 1.3128286600112915,
|
| 1401 |
+
"eval_runtime": 36.3665,
|
| 1402 |
+
"eval_samples_per_second": 10.807,
|
| 1403 |
+
"eval_steps_per_second": 1.375,
|
| 1404 |
+
"step": 9300
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 48.205128205128204,
|
| 1408 |
+
"grad_norm": 31.19647216796875,
|
| 1409 |
+
"learning_rate": 9.0611e-06,
|
| 1410 |
+
"loss": 1.2033,
|
| 1411 |
+
"step": 9400
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 48.205128205128204,
|
| 1415 |
+
"eval_loss": 1.3134888410568237,
|
| 1416 |
+
"eval_runtime": 36.5129,
|
| 1417 |
+
"eval_samples_per_second": 10.763,
|
| 1418 |
+
"eval_steps_per_second": 1.369,
|
| 1419 |
+
"step": 9400
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 48.717948717948715,
|
| 1423 |
+
"grad_norm": 20.11866569519043,
|
| 1424 |
+
"learning_rate": 9.0511e-06,
|
| 1425 |
+
"loss": 1.1955,
|
| 1426 |
+
"step": 9500
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 48.717948717948715,
|
| 1430 |
+
"eval_loss": 1.3154560327529907,
|
| 1431 |
+
"eval_runtime": 36.6023,
|
| 1432 |
+
"eval_samples_per_second": 10.737,
|
| 1433 |
+
"eval_steps_per_second": 1.366,
|
| 1434 |
+
"step": 9500
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 49.23076923076923,
|
| 1438 |
+
"grad_norm": 36.3143424987793,
|
| 1439 |
+
"learning_rate": 9.0411e-06,
|
| 1440 |
+
"loss": 1.2067,
|
| 1441 |
+
"step": 9600
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 49.23076923076923,
|
| 1445 |
+
"eval_loss": 1.3158589601516724,
|
| 1446 |
+
"eval_runtime": 36.4851,
|
| 1447 |
+
"eval_samples_per_second": 10.772,
|
| 1448 |
+
"eval_steps_per_second": 1.37,
|
| 1449 |
+
"step": 9600
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 49.743589743589745,
|
| 1453 |
+
"grad_norm": 48.41688537597656,
|
| 1454 |
+
"learning_rate": 9.0311e-06,
|
| 1455 |
+
"loss": 1.2295,
|
| 1456 |
+
"step": 9700
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 49.743589743589745,
|
| 1460 |
+
"eval_loss": 1.306788682937622,
|
| 1461 |
+
"eval_runtime": 36.291,
|
| 1462 |
+
"eval_samples_per_second": 10.829,
|
| 1463 |
+
"eval_steps_per_second": 1.378,
|
| 1464 |
+
"step": 9700
|
| 1465 |
+
},
|
| 1466 |
+
{
|
| 1467 |
+
"epoch": 50.256410256410255,
|
| 1468 |
+
"grad_norm": 26.129995346069336,
|
| 1469 |
+
"learning_rate": 9.0211e-06,
|
| 1470 |
+
"loss": 1.1809,
|
| 1471 |
+
"step": 9800
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 50.256410256410255,
|
| 1475 |
+
"eval_loss": 1.3299375772476196,
|
| 1476 |
+
"eval_runtime": 36.4651,
|
| 1477 |
+
"eval_samples_per_second": 10.777,
|
| 1478 |
+
"eval_steps_per_second": 1.371,
|
| 1479 |
+
"step": 9800
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 50.76923076923077,
|
| 1483 |
+
"grad_norm": 19.543821334838867,
|
| 1484 |
+
"learning_rate": 9.011100000000001e-06,
|
| 1485 |
+
"loss": 1.2179,
|
| 1486 |
+
"step": 9900
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 50.76923076923077,
|
| 1490 |
+
"eval_loss": 1.317457675933838,
|
| 1491 |
+
"eval_runtime": 36.2864,
|
| 1492 |
+
"eval_samples_per_second": 10.831,
|
| 1493 |
+
"eval_steps_per_second": 1.378,
|
| 1494 |
+
"step": 9900
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 51.282051282051285,
|
| 1498 |
+
"grad_norm": 25.619775772094727,
|
| 1499 |
+
"learning_rate": 9.001100000000001e-06,
|
| 1500 |
+
"loss": 1.1653,
|
| 1501 |
+
"step": 10000
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 51.282051282051285,
|
| 1505 |
+
"eval_loss": 1.31196928024292,
|
| 1506 |
+
"eval_runtime": 36.3263,
|
| 1507 |
+
"eval_samples_per_second": 10.819,
|
| 1508 |
+
"eval_steps_per_second": 1.376,
|
| 1509 |
+
"step": 10000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 51.794871794871796,
|
| 1513 |
+
"grad_norm": 45.30315017700195,
|
| 1514 |
+
"learning_rate": 8.991100000000001e-06,
|
| 1515 |
+
"loss": 1.2391,
|
| 1516 |
+
"step": 10100
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 51.794871794871796,
|
| 1520 |
+
"eval_loss": 1.305709719657898,
|
| 1521 |
+
"eval_runtime": 36.2103,
|
| 1522 |
+
"eval_samples_per_second": 10.853,
|
| 1523 |
+
"eval_steps_per_second": 1.381,
|
| 1524 |
+
"step": 10100
|
| 1525 |
+
},
|
| 1526 |
+
{
|
| 1527 |
+
"epoch": 52.30769230769231,
|
| 1528 |
+
"grad_norm": 26.942337036132812,
|
| 1529 |
+
"learning_rate": 8.981100000000001e-06,
|
| 1530 |
+
"loss": 1.2195,
|
| 1531 |
+
"step": 10200
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 52.30769230769231,
|
| 1535 |
+
"eval_loss": 1.3068941831588745,
|
| 1536 |
+
"eval_runtime": 36.2565,
|
| 1537 |
+
"eval_samples_per_second": 10.839,
|
| 1538 |
+
"eval_steps_per_second": 1.379,
|
| 1539 |
+
"step": 10200
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 52.82051282051282,
|
| 1543 |
+
"grad_norm": 26.20073890686035,
|
| 1544 |
+
"learning_rate": 8.9711e-06,
|
| 1545 |
+
"loss": 1.1639,
|
| 1546 |
+
"step": 10300
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 52.82051282051282,
|
| 1550 |
+
"eval_loss": 1.3013452291488647,
|
| 1551 |
+
"eval_runtime": 36.2146,
|
| 1552 |
+
"eval_samples_per_second": 10.852,
|
| 1553 |
+
"eval_steps_per_second": 1.381,
|
| 1554 |
+
"step": 10300
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 53.333333333333336,
|
| 1558 |
+
"grad_norm": 41.40350341796875,
|
| 1559 |
+
"learning_rate": 8.9611e-06,
|
| 1560 |
+
"loss": 1.2033,
|
| 1561 |
+
"step": 10400
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 53.333333333333336,
|
| 1565 |
+
"eval_loss": 1.305737853050232,
|
| 1566 |
+
"eval_runtime": 36.4865,
|
| 1567 |
+
"eval_samples_per_second": 10.771,
|
| 1568 |
+
"eval_steps_per_second": 1.37,
|
| 1569 |
+
"step": 10400
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 53.84615384615385,
|
| 1573 |
+
"grad_norm": 28.133567810058594,
|
| 1574 |
+
"learning_rate": 8.9511e-06,
|
| 1575 |
+
"loss": 1.1906,
|
| 1576 |
+
"step": 10500
|
| 1577 |
+
},
|
| 1578 |
+
{
|
| 1579 |
+
"epoch": 53.84615384615385,
|
| 1580 |
+
"eval_loss": 1.2961195707321167,
|
| 1581 |
+
"eval_runtime": 36.2734,
|
| 1582 |
+
"eval_samples_per_second": 10.834,
|
| 1583 |
+
"eval_steps_per_second": 1.378,
|
| 1584 |
+
"step": 10500
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 54.35897435897436,
|
| 1588 |
+
"grad_norm": 44.07390213012695,
|
| 1589 |
+
"learning_rate": 8.9411e-06,
|
| 1590 |
+
"loss": 1.1899,
|
| 1591 |
+
"step": 10600
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 54.35897435897436,
|
| 1595 |
+
"eval_loss": 1.3024916648864746,
|
| 1596 |
+
"eval_runtime": 36.4774,
|
| 1597 |
+
"eval_samples_per_second": 10.774,
|
| 1598 |
+
"eval_steps_per_second": 1.371,
|
| 1599 |
+
"step": 10600
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 54.87179487179487,
|
| 1603 |
+
"grad_norm": 19.120830535888672,
|
| 1604 |
+
"learning_rate": 8.9311e-06,
|
| 1605 |
+
"loss": 1.1697,
|
| 1606 |
+
"step": 10700
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 54.87179487179487,
|
| 1610 |
+
"eval_loss": 1.3056432008743286,
|
| 1611 |
+
"eval_runtime": 36.2367,
|
| 1612 |
+
"eval_samples_per_second": 10.845,
|
| 1613 |
+
"eval_steps_per_second": 1.38,
|
| 1614 |
+
"step": 10700
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 55.38461538461539,
|
| 1618 |
+
"grad_norm": 52.376529693603516,
|
| 1619 |
+
"learning_rate": 8.9211e-06,
|
| 1620 |
+
"loss": 1.1759,
|
| 1621 |
+
"step": 10800
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 55.38461538461539,
|
| 1625 |
+
"eval_loss": 1.3018929958343506,
|
| 1626 |
+
"eval_runtime": 36.1478,
|
| 1627 |
+
"eval_samples_per_second": 10.872,
|
| 1628 |
+
"eval_steps_per_second": 1.383,
|
| 1629 |
+
"step": 10800
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 55.8974358974359,
|
| 1633 |
+
"grad_norm": 41.84946060180664,
|
| 1634 |
+
"learning_rate": 8.9112e-06,
|
| 1635 |
+
"loss": 1.1973,
|
| 1636 |
+
"step": 10900
|
| 1637 |
+
},
|
| 1638 |
+
{
|
| 1639 |
+
"epoch": 55.8974358974359,
|
| 1640 |
+
"eval_loss": 1.3166084289550781,
|
| 1641 |
+
"eval_runtime": 36.4967,
|
| 1642 |
+
"eval_samples_per_second": 10.768,
|
| 1643 |
+
"eval_steps_per_second": 1.37,
|
| 1644 |
+
"step": 10900
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 56.41025641025641,
|
| 1648 |
+
"grad_norm": 48.97800064086914,
|
| 1649 |
+
"learning_rate": 8.9012e-06,
|
| 1650 |
+
"loss": 1.1942,
|
| 1651 |
+
"step": 11000
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 56.41025641025641,
|
| 1655 |
+
"eval_loss": 1.3040730953216553,
|
| 1656 |
+
"eval_runtime": 36.3391,
|
| 1657 |
+
"eval_samples_per_second": 10.815,
|
| 1658 |
+
"eval_steps_per_second": 1.376,
|
| 1659 |
+
"step": 11000
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 56.92307692307692,
|
| 1663 |
+
"grad_norm": 24.18547821044922,
|
| 1664 |
+
"learning_rate": 8.8912e-06,
|
| 1665 |
+
"loss": 1.1544,
|
| 1666 |
+
"step": 11100
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 56.92307692307692,
|
| 1670 |
+
"eval_loss": 1.2837135791778564,
|
| 1671 |
+
"eval_runtime": 36.2839,
|
| 1672 |
+
"eval_samples_per_second": 10.831,
|
| 1673 |
+
"eval_steps_per_second": 1.378,
|
| 1674 |
+
"step": 11100
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 57.43589743589744,
|
| 1678 |
+
"grad_norm": 34.69540023803711,
|
| 1679 |
+
"learning_rate": 8.8812e-06,
|
| 1680 |
+
"loss": 1.1998,
|
| 1681 |
+
"step": 11200
|
| 1682 |
+
},
|
| 1683 |
+
{
|
| 1684 |
+
"epoch": 57.43589743589744,
|
| 1685 |
+
"eval_loss": 1.2983756065368652,
|
| 1686 |
+
"eval_runtime": 36.2024,
|
| 1687 |
+
"eval_samples_per_second": 10.856,
|
| 1688 |
+
"eval_steps_per_second": 1.381,
|
| 1689 |
+
"step": 11200
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 57.94871794871795,
|
| 1693 |
+
"grad_norm": 30.074583053588867,
|
| 1694 |
+
"learning_rate": 8.8712e-06,
|
| 1695 |
+
"loss": 1.1352,
|
| 1696 |
+
"step": 11300
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 57.94871794871795,
|
| 1700 |
+
"eval_loss": 1.2913649082183838,
|
| 1701 |
+
"eval_runtime": 36.0977,
|
| 1702 |
+
"eval_samples_per_second": 10.887,
|
| 1703 |
+
"eval_steps_per_second": 1.385,
|
| 1704 |
+
"step": 11300
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 58.46153846153846,
|
| 1708 |
+
"grad_norm": 26.75031852722168,
|
| 1709 |
+
"learning_rate": 8.8612e-06,
|
| 1710 |
+
"loss": 1.1728,
|
| 1711 |
+
"step": 11400
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 58.46153846153846,
|
| 1715 |
+
"eval_loss": 1.288116216659546,
|
| 1716 |
+
"eval_runtime": 36.2588,
|
| 1717 |
+
"eval_samples_per_second": 10.839,
|
| 1718 |
+
"eval_steps_per_second": 1.379,
|
| 1719 |
+
"step": 11400
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 58.97435897435897,
|
| 1723 |
+
"grad_norm": 49.548213958740234,
|
| 1724 |
+
"learning_rate": 8.851200000000001e-06,
|
| 1725 |
+
"loss": 1.1738,
|
| 1726 |
+
"step": 11500
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 58.97435897435897,
|
| 1730 |
+
"eval_loss": 1.2846206426620483,
|
| 1731 |
+
"eval_runtime": 36.5245,
|
| 1732 |
+
"eval_samples_per_second": 10.76,
|
| 1733 |
+
"eval_steps_per_second": 1.369,
|
| 1734 |
+
"step": 11500
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"epoch": 59.48717948717949,
|
| 1738 |
+
"grad_norm": 23.007057189941406,
|
| 1739 |
+
"learning_rate": 8.841200000000001e-06,
|
| 1740 |
+
"loss": 1.1501,
|
| 1741 |
+
"step": 11600
|
| 1742 |
+
},
|
| 1743 |
+
{
|
| 1744 |
+
"epoch": 59.48717948717949,
|
| 1745 |
+
"eval_loss": 1.297021746635437,
|
| 1746 |
+
"eval_runtime": 36.2678,
|
| 1747 |
+
"eval_samples_per_second": 10.836,
|
| 1748 |
+
"eval_steps_per_second": 1.379,
|
| 1749 |
+
"step": 11600
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 60.0,
|
| 1753 |
+
"grad_norm": 39.79067611694336,
|
| 1754 |
+
"learning_rate": 8.831200000000001e-06,
|
| 1755 |
+
"loss": 1.1836,
|
| 1756 |
+
"step": 11700
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 60.0,
|
| 1760 |
+
"eval_loss": 1.2865136861801147,
|
| 1761 |
+
"eval_runtime": 36.1127,
|
| 1762 |
+
"eval_samples_per_second": 10.883,
|
| 1763 |
+
"eval_steps_per_second": 1.385,
|
| 1764 |
+
"step": 11700
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 60.51282051282051,
|
| 1768 |
+
"grad_norm": 24.281373977661133,
|
| 1769 |
+
"learning_rate": 8.821200000000001e-06,
|
| 1770 |
+
"loss": 1.1548,
|
| 1771 |
+
"step": 11800
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 60.51282051282051,
|
| 1775 |
+
"eval_loss": 1.2812024354934692,
|
| 1776 |
+
"eval_runtime": 36.2399,
|
| 1777 |
+
"eval_samples_per_second": 10.844,
|
| 1778 |
+
"eval_steps_per_second": 1.38,
|
| 1779 |
+
"step": 11800
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 61.02564102564103,
|
| 1783 |
+
"grad_norm": 30.851072311401367,
|
| 1784 |
+
"learning_rate": 8.811200000000001e-06,
|
| 1785 |
+
"loss": 1.1794,
|
| 1786 |
+
"step": 11900
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 61.02564102564103,
|
| 1790 |
+
"eval_loss": 1.2902381420135498,
|
| 1791 |
+
"eval_runtime": 36.1264,
|
| 1792 |
+
"eval_samples_per_second": 10.878,
|
| 1793 |
+
"eval_steps_per_second": 1.384,
|
| 1794 |
+
"step": 11900
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 61.53846153846154,
|
| 1798 |
+
"grad_norm": 44.42039108276367,
|
| 1799 |
+
"learning_rate": 8.801200000000001e-06,
|
| 1800 |
+
"loss": 1.1385,
|
| 1801 |
+
"step": 12000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 61.53846153846154,
|
| 1805 |
+
"eval_loss": 1.2793415784835815,
|
| 1806 |
+
"eval_runtime": 36.266,
|
| 1807 |
+
"eval_samples_per_second": 10.837,
|
| 1808 |
+
"eval_steps_per_second": 1.379,
|
| 1809 |
+
"step": 12000
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 62.05128205128205,
|
| 1813 |
+
"grad_norm": 57.410274505615234,
|
| 1814 |
+
"learning_rate": 8.791200000000001e-06,
|
| 1815 |
+
"loss": 1.1697,
|
| 1816 |
+
"step": 12100
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 62.05128205128205,
|
| 1820 |
+
"eval_loss": 1.2847199440002441,
|
| 1821 |
+
"eval_runtime": 36.1783,
|
| 1822 |
+
"eval_samples_per_second": 10.863,
|
| 1823 |
+
"eval_steps_per_second": 1.382,
|
| 1824 |
+
"step": 12100
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 62.56410256410256,
|
| 1828 |
+
"grad_norm": 70.70729064941406,
|
| 1829 |
+
"learning_rate": 8.781200000000002e-06,
|
| 1830 |
+
"loss": 1.1518,
|
| 1831 |
+
"step": 12200
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 62.56410256410256,
|
| 1835 |
+
"eval_loss": 1.2760446071624756,
|
| 1836 |
+
"eval_runtime": 36.0527,
|
| 1837 |
+
"eval_samples_per_second": 10.901,
|
| 1838 |
+
"eval_steps_per_second": 1.387,
|
| 1839 |
+
"step": 12200
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 63.07692307692308,
|
| 1843 |
+
"grad_norm": 32.417388916015625,
|
| 1844 |
+
"learning_rate": 8.7712e-06,
|
| 1845 |
+
"loss": 1.1677,
|
| 1846 |
+
"step": 12300
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 63.07692307692308,
|
| 1850 |
+
"eval_loss": 1.2847411632537842,
|
| 1851 |
+
"eval_runtime": 36.3923,
|
| 1852 |
+
"eval_samples_per_second": 10.799,
|
| 1853 |
+
"eval_steps_per_second": 1.374,
|
| 1854 |
+
"step": 12300
|
| 1855 |
+
},
|
| 1856 |
+
{
|
| 1857 |
+
"epoch": 63.58974358974359,
|
| 1858 |
+
"grad_norm": 24.372791290283203,
|
| 1859 |
+
"learning_rate": 8.7612e-06,
|
| 1860 |
+
"loss": 1.1433,
|
| 1861 |
+
"step": 12400
|
| 1862 |
+
},
|
| 1863 |
+
{
|
| 1864 |
+
"epoch": 63.58974358974359,
|
| 1865 |
+
"eval_loss": 1.2779407501220703,
|
| 1866 |
+
"eval_runtime": 36.5015,
|
| 1867 |
+
"eval_samples_per_second": 10.767,
|
| 1868 |
+
"eval_steps_per_second": 1.37,
|
| 1869 |
+
"step": 12400
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 64.1025641025641,
|
| 1873 |
+
"grad_norm": 19.632272720336914,
|
| 1874 |
+
"learning_rate": 8.7512e-06,
|
| 1875 |
+
"loss": 1.1607,
|
| 1876 |
+
"step": 12500
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 64.1025641025641,
|
| 1880 |
+
"eval_loss": 1.2792208194732666,
|
| 1881 |
+
"eval_runtime": 36.4617,
|
| 1882 |
+
"eval_samples_per_second": 10.778,
|
| 1883 |
+
"eval_steps_per_second": 1.371,
|
| 1884 |
+
"step": 12500
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 64.61538461538461,
|
| 1888 |
+
"grad_norm": 34.54841613769531,
|
| 1889 |
+
"learning_rate": 8.7412e-06,
|
| 1890 |
+
"loss": 1.1371,
|
| 1891 |
+
"step": 12600
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 64.61538461538461,
|
| 1895 |
+
"eval_loss": 1.2620294094085693,
|
| 1896 |
+
"eval_runtime": 36.4969,
|
| 1897 |
+
"eval_samples_per_second": 10.768,
|
| 1898 |
+
"eval_steps_per_second": 1.37,
|
| 1899 |
+
"step": 12600
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 65.12820512820512,
|
| 1903 |
+
"grad_norm": 19.67386817932129,
|
| 1904 |
+
"learning_rate": 8.7312e-06,
|
| 1905 |
+
"loss": 1.1332,
|
| 1906 |
+
"step": 12700
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 65.12820512820512,
|
| 1910 |
+
"eval_loss": 1.2682890892028809,
|
| 1911 |
+
"eval_runtime": 36.6309,
|
| 1912 |
+
"eval_samples_per_second": 10.729,
|
| 1913 |
+
"eval_steps_per_second": 1.365,
|
| 1914 |
+
"step": 12700
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 65.64102564102564,
|
| 1918 |
+
"grad_norm": 65.07030487060547,
|
| 1919 |
+
"learning_rate": 8.7212e-06,
|
| 1920 |
+
"loss": 1.1571,
|
| 1921 |
+
"step": 12800
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 65.64102564102564,
|
| 1925 |
+
"eval_loss": 1.2490720748901367,
|
| 1926 |
+
"eval_runtime": 36.3056,
|
| 1927 |
+
"eval_samples_per_second": 10.825,
|
| 1928 |
+
"eval_steps_per_second": 1.377,
|
| 1929 |
+
"step": 12800
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 66.15384615384616,
|
| 1933 |
+
"grad_norm": 20.384132385253906,
|
| 1934 |
+
"learning_rate": 8.7112e-06,
|
| 1935 |
+
"loss": 1.1619,
|
| 1936 |
+
"step": 12900
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 66.15384615384616,
|
| 1940 |
+
"eval_loss": 1.2465028762817383,
|
| 1941 |
+
"eval_runtime": 36.1678,
|
| 1942 |
+
"eval_samples_per_second": 10.866,
|
| 1943 |
+
"eval_steps_per_second": 1.382,
|
| 1944 |
+
"step": 12900
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 66.66666666666667,
|
| 1948 |
+
"grad_norm": 36.320674896240234,
|
| 1949 |
+
"learning_rate": 8.7012e-06,
|
| 1950 |
+
"loss": 1.1176,
|
| 1951 |
+
"step": 13000
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 66.66666666666667,
|
| 1955 |
+
"eval_loss": 1.2594362497329712,
|
| 1956 |
+
"eval_runtime": 36.3117,
|
| 1957 |
+
"eval_samples_per_second": 10.823,
|
| 1958 |
+
"eval_steps_per_second": 1.377,
|
| 1959 |
+
"step": 13000
|
| 1960 |
+
},
|
| 1961 |
+
{
|
| 1962 |
+
"epoch": 67.17948717948718,
|
| 1963 |
+
"grad_norm": 30.79526138305664,
|
| 1964 |
+
"learning_rate": 8.6912e-06,
|
| 1965 |
+
"loss": 1.1311,
|
| 1966 |
+
"step": 13100
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 67.17948717948718,
|
| 1970 |
+
"eval_loss": 1.2553967237472534,
|
| 1971 |
+
"eval_runtime": 36.2667,
|
| 1972 |
+
"eval_samples_per_second": 10.836,
|
| 1973 |
+
"eval_steps_per_second": 1.379,
|
| 1974 |
+
"step": 13100
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 67.6923076923077,
|
| 1978 |
+
"grad_norm": 40.0444450378418,
|
| 1979 |
+
"learning_rate": 8.6812e-06,
|
| 1980 |
+
"loss": 1.165,
|
| 1981 |
+
"step": 13200
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 67.6923076923077,
|
| 1985 |
+
"eval_loss": 1.2607430219650269,
|
| 1986 |
+
"eval_runtime": 36.339,
|
| 1987 |
+
"eval_samples_per_second": 10.815,
|
| 1988 |
+
"eval_steps_per_second": 1.376,
|
| 1989 |
+
"step": 13200
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 68.2051282051282,
|
| 1993 |
+
"grad_norm": 25.53687286376953,
|
| 1994 |
+
"learning_rate": 8.671200000000001e-06,
|
| 1995 |
+
"loss": 1.1334,
|
| 1996 |
+
"step": 13300
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 68.2051282051282,
|
| 2000 |
+
"eval_loss": 1.2592159509658813,
|
| 2001 |
+
"eval_runtime": 36.2847,
|
| 2002 |
+
"eval_samples_per_second": 10.831,
|
| 2003 |
+
"eval_steps_per_second": 1.378,
|
| 2004 |
+
"step": 13300
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 68.71794871794872,
|
| 2008 |
+
"grad_norm": 28.198373794555664,
|
| 2009 |
+
"learning_rate": 8.661200000000001e-06,
|
| 2010 |
+
"loss": 1.1481,
|
| 2011 |
+
"step": 13400
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 68.71794871794872,
|
| 2015 |
+
"eval_loss": 1.2755882740020752,
|
| 2016 |
+
"eval_runtime": 36.6238,
|
| 2017 |
+
"eval_samples_per_second": 10.731,
|
| 2018 |
+
"eval_steps_per_second": 1.365,
|
| 2019 |
+
"step": 13400
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 69.23076923076923,
|
| 2023 |
+
"grad_norm": 44.77776336669922,
|
| 2024 |
+
"learning_rate": 8.651200000000001e-06,
|
| 2025 |
+
"loss": 1.1138,
|
| 2026 |
+
"step": 13500
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 69.23076923076923,
|
| 2030 |
+
"eval_loss": 1.259446144104004,
|
| 2031 |
+
"eval_runtime": 36.4048,
|
| 2032 |
+
"eval_samples_per_second": 10.795,
|
| 2033 |
+
"eval_steps_per_second": 1.373,
|
| 2034 |
+
"step": 13500
|
| 2035 |
+
}
|
| 2036 |
+
],
|
| 2037 |
+
"logging_steps": 100,
|
| 2038 |
+
"max_steps": 100000,
|
| 2039 |
+
"num_input_tokens_seen": 0,
|
| 2040 |
+
"num_train_epochs": 513,
|
| 2041 |
+
"save_steps": 500,
|
| 2042 |
+
"stateful_callbacks": {
|
| 2043 |
+
"TrainerControl": {
|
| 2044 |
+
"args": {
|
| 2045 |
+
"should_epoch_stop": false,
|
| 2046 |
+
"should_evaluate": false,
|
| 2047 |
+
"should_log": false,
|
| 2048 |
+
"should_save": true,
|
| 2049 |
+
"should_training_stop": false
|
| 2050 |
+
},
|
| 2051 |
+
"attributes": {}
|
| 2052 |
+
}
|
| 2053 |
+
},
|
| 2054 |
+
"total_flos": 5.160282743808e+19,
|
| 2055 |
+
"train_batch_size": 8,
|
| 2056 |
+
"trial_name": null,
|
| 2057 |
+
"trial_params": null
|
| 2058 |
+
}
|
checkpoint-13500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8625e14ff679edc4a495930224c1e923adf21894b5ebfeb33e13f511a05ddf66
|
| 3 |
+
size 5304
|