Upload 8 files
Browse filesFirst model version
- checkpoint/.gitattributes +2 -0
- checkpoint/config.json +39 -0
- checkpoint/optimizer.pt +3 -0
- checkpoint/pytorch_model.bin +3 -0
- checkpoint/rng_state.pth +3 -0
- checkpoint/scheduler.pt +3 -0
- checkpoint/trainer_state.json +1121 -0
- checkpoint/training_args.bin +3 -0
checkpoint/.gitattributes
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
checkpoint/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/home/ahf38/palmer_scratch/brainlm/training-runs/2023-07-17-19_00_00/checkpoint-1750",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BrainLMForPretraining"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"conv_kernel_size": 65,
|
| 8 |
+
"decoder_hidden_size": 512,
|
| 9 |
+
"decoder_intermediate_size": 1024,
|
| 10 |
+
"decoder_num_attention_heads": 4,
|
| 11 |
+
"decoder_num_hidden_layers": 2,
|
| 12 |
+
"hidden_act": "gelu",
|
| 13 |
+
"hidden_dropout_prob": 0.0,
|
| 14 |
+
"hidden_size": 512,
|
| 15 |
+
"image_size": 224,
|
| 16 |
+
"initializer_range": 0.02,
|
| 17 |
+
"intermediate_size": 1024,
|
| 18 |
+
"inv_coeff_init_option": false,
|
| 19 |
+
"layer_norm_eps": 1e-12,
|
| 20 |
+
"loss_fn": "mse",
|
| 21 |
+
"mask_ratio": 0.2,
|
| 22 |
+
"max_eval_samples": 800,
|
| 23 |
+
"model_type": "brainlm_mae",
|
| 24 |
+
"norm_pix_loss": false,
|
| 25 |
+
"num_attention_heads": 4,
|
| 26 |
+
"num_brain_voxels": 424,
|
| 27 |
+
"num_channels": 3,
|
| 28 |
+
"num_hidden_layers": 4,
|
| 29 |
+
"num_landmarks": 64,
|
| 30 |
+
"num_timepoints_per_voxel": 200,
|
| 31 |
+
"patch_size": 16,
|
| 32 |
+
"qkv_bias": true,
|
| 33 |
+
"segment_means_seq_len": 64,
|
| 34 |
+
"timepoint_patching_size": 20,
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.30.0.dev0",
|
| 37 |
+
"use_tanh_decoder": false,
|
| 38 |
+
"weight_decay": 1e-05
|
| 39 |
+
}
|
checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4782bce14b3d264eee0a0a1ab7169d19a15a65cbbb828b29cfe1b34479ea0d05
|
| 3 |
+
size 104351649
|
checkpoint/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cd41e52a4c25a7e4c27b91994f9701f56c62ebc498f62576979f8aee4220a94
|
| 3 |
+
size 74237641
|
checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66c42697856b27de62066cce114703542b056aefe0e54d932603929c9bbaab5b
|
| 3 |
+
size 14503
|
checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8635a0bc0753280e659229899e16371eae66a73fe73b2ae4566bf70b33885a8
|
| 3 |
+
size 623
|
checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,1121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.37047404050827026,
|
| 3 |
+
"best_model_checkpoint": "/home/ahf38/palmer_scratch/brainlm/training-runs/2023-07-19-17_00_00/checkpoint-3250",
|
| 4 |
+
"epoch": 13.63040629095675,
|
| 5 |
+
"global_step": 3250,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0,
|
| 12 |
+
"learning_rate": 0.0002100840336134454,
|
| 13 |
+
"loss": 0.3863,
|
| 14 |
+
"step": 50
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0,
|
| 18 |
+
"eval_loss": 0.3854129910469055,
|
| 19 |
+
"eval_mae": 0.4674049913883209,
|
| 20 |
+
"eval_mse": 0.38541293144226074,
|
| 21 |
+
"eval_r2": 0.4410198587613452,
|
| 22 |
+
"eval_runtime": 273.6849,
|
| 23 |
+
"eval_samples_per_second": 2.923,
|
| 24 |
+
"eval_steps_per_second": 0.731,
|
| 25 |
+
"step": 50
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0,
|
| 29 |
+
"learning_rate": 0.0004201680672268908,
|
| 30 |
+
"loss": 0.3852,
|
| 31 |
+
"step": 100
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0,
|
| 35 |
+
"eval_loss": 0.38619935512542725,
|
| 36 |
+
"eval_mae": 0.46789708733558655,
|
| 37 |
+
"eval_mse": 0.386198490858078,
|
| 38 |
+
"eval_r2": 0.4393806237898299,
|
| 39 |
+
"eval_runtime": 280.3385,
|
| 40 |
+
"eval_samples_per_second": 2.854,
|
| 41 |
+
"eval_steps_per_second": 0.713,
|
| 42 |
+
"step": 100
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0,
|
| 46 |
+
"learning_rate": 0.0006302521008403362,
|
| 47 |
+
"loss": 0.3851,
|
| 48 |
+
"step": 150
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0,
|
| 52 |
+
"eval_loss": 0.38692620396614075,
|
| 53 |
+
"eval_mae": 0.4686347544193268,
|
| 54 |
+
"eval_mse": 0.3869261145591736,
|
| 55 |
+
"eval_r2": 0.43769447169001496,
|
| 56 |
+
"eval_runtime": 264.849,
|
| 57 |
+
"eval_samples_per_second": 3.021,
|
| 58 |
+
"eval_steps_per_second": 0.755,
|
| 59 |
+
"step": 150
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0,
|
| 63 |
+
"learning_rate": 0.0008403361344537816,
|
| 64 |
+
"loss": 0.393,
|
| 65 |
+
"step": 200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0,
|
| 69 |
+
"eval_loss": 0.409867525100708,
|
| 70 |
+
"eval_mae": 0.4844866693019867,
|
| 71 |
+
"eval_mse": 0.4098674952983856,
|
| 72 |
+
"eval_r2": 0.4059509929564361,
|
| 73 |
+
"eval_runtime": 264.8497,
|
| 74 |
+
"eval_samples_per_second": 3.021,
|
| 75 |
+
"eval_steps_per_second": 0.755,
|
| 76 |
+
"step": 200
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1,
|
| 80 |
+
"learning_rate": 0.0009999826244478293,
|
| 81 |
+
"loss": 0.3975,
|
| 82 |
+
"step": 250
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 1,
|
| 86 |
+
"eval_loss": 0.3888590931892395,
|
| 87 |
+
"eval_mae": 0.46977394819259644,
|
| 88 |
+
"eval_mse": 0.38885924220085144,
|
| 89 |
+
"eval_r2": 0.43532054204855475,
|
| 90 |
+
"eval_runtime": 263.3448,
|
| 91 |
+
"eval_samples_per_second": 3.038,
|
| 92 |
+
"eval_steps_per_second": 0.759,
|
| 93 |
+
"step": 250
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1,
|
| 97 |
+
"learning_rate": 0.0009995362383107963,
|
| 98 |
+
"loss": 0.3883,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1,
|
| 103 |
+
"eval_loss": 0.3876199424266815,
|
| 104 |
+
"eval_mae": 0.46888846158981323,
|
| 105 |
+
"eval_mse": 0.3876205086708069,
|
| 106 |
+
"eval_r2": 0.4391745591771552,
|
| 107 |
+
"eval_runtime": 264.9341,
|
| 108 |
+
"eval_samples_per_second": 3.02,
|
| 109 |
+
"eval_steps_per_second": 0.755,
|
| 110 |
+
"step": 300
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1,
|
| 114 |
+
"learning_rate": 0.000998487151097676,
|
| 115 |
+
"loss": 0.3887,
|
| 116 |
+
"step": 350
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1,
|
| 120 |
+
"eval_loss": 0.3875642418861389,
|
| 121 |
+
"eval_mae": 0.4687305688858032,
|
| 122 |
+
"eval_mse": 0.38756391406059265,
|
| 123 |
+
"eval_r2": 0.4382047783977898,
|
| 124 |
+
"eval_runtime": 272.0994,
|
| 125 |
+
"eval_samples_per_second": 2.94,
|
| 126 |
+
"eval_steps_per_second": 0.735,
|
| 127 |
+
"step": 350
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1,
|
| 131 |
+
"learning_rate": 0.0009968366285544618,
|
| 132 |
+
"loss": 0.386,
|
| 133 |
+
"step": 400
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 1,
|
| 137 |
+
"eval_loss": 0.3863183557987213,
|
| 138 |
+
"eval_mae": 0.4679754078388214,
|
| 139 |
+
"eval_mse": 0.386318176984787,
|
| 140 |
+
"eval_r2": 0.4391650800336171,
|
| 141 |
+
"eval_runtime": 272.2539,
|
| 142 |
+
"eval_samples_per_second": 2.938,
|
| 143 |
+
"eval_steps_per_second": 0.735,
|
| 144 |
+
"step": 400
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1,
|
| 148 |
+
"learning_rate": 0.000994586662071641,
|
| 149 |
+
"loss": 0.3861,
|
| 150 |
+
"step": 450
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1,
|
| 154 |
+
"eval_loss": 0.39024049043655396,
|
| 155 |
+
"eval_mae": 0.47065961360931396,
|
| 156 |
+
"eval_mse": 0.39024049043655396,
|
| 157 |
+
"eval_r2": 0.4331343008067088,
|
| 158 |
+
"eval_runtime": 266.2407,
|
| 159 |
+
"eval_samples_per_second": 3.005,
|
| 160 |
+
"eval_steps_per_second": 0.751,
|
| 161 |
+
"step": 450
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2,
|
| 165 |
+
"learning_rate": 0.000991739966281539,
|
| 166 |
+
"loss": 0.3876,
|
| 167 |
+
"step": 500
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2,
|
| 171 |
+
"eval_loss": 0.3867352604866028,
|
| 172 |
+
"eval_mae": 0.46853551268577576,
|
| 173 |
+
"eval_mse": 0.3867342174053192,
|
| 174 |
+
"eval_r2": 0.43885509094622643,
|
| 175 |
+
"eval_runtime": 265.3966,
|
| 176 |
+
"eval_samples_per_second": 3.014,
|
| 177 |
+
"eval_steps_per_second": 0.754,
|
| 178 |
+
"step": 500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2,
|
| 182 |
+
"learning_rate": 0.0009882999757830587,
|
| 183 |
+
"loss": 0.386,
|
| 184 |
+
"step": 550
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2,
|
| 188 |
+
"eval_loss": 0.38316670060157776,
|
| 189 |
+
"eval_mae": 0.46593964099884033,
|
| 190 |
+
"eval_mse": 0.3831673562526703,
|
| 191 |
+
"eval_r2": 0.44430950413045944,
|
| 192 |
+
"eval_runtime": 262.4987,
|
| 193 |
+
"eval_samples_per_second": 3.048,
|
| 194 |
+
"eval_steps_per_second": 0.762,
|
| 195 |
+
"step": 550
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2,
|
| 199 |
+
"learning_rate": 0.0009842708409977634,
|
| 200 |
+
"loss": 0.3851,
|
| 201 |
+
"step": 600
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2,
|
| 205 |
+
"eval_loss": 0.3835921585559845,
|
| 206 |
+
"eval_mae": 0.4662681818008423,
|
| 207 |
+
"eval_mse": 0.38359254598617554,
|
| 208 |
+
"eval_r2": 0.4431584385649353,
|
| 209 |
+
"eval_runtime": 262.0832,
|
| 210 |
+
"eval_samples_per_second": 3.052,
|
| 211 |
+
"eval_steps_per_second": 0.763,
|
| 212 |
+
"step": 600
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2,
|
| 216 |
+
"learning_rate": 0.0009796574231623054,
|
| 217 |
+
"loss": 0.3828,
|
| 218 |
+
"step": 650
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2,
|
| 222 |
+
"eval_loss": 0.38348111510276794,
|
| 223 |
+
"eval_mae": 0.46614208817481995,
|
| 224 |
+
"eval_mse": 0.3834820091724396,
|
| 225 |
+
"eval_r2": 0.44133966944739267,
|
| 226 |
+
"eval_runtime": 267.1672,
|
| 227 |
+
"eval_samples_per_second": 2.994,
|
| 228 |
+
"eval_steps_per_second": 0.749,
|
| 229 |
+
"step": 650
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2,
|
| 233 |
+
"learning_rate": 0.0009744652884632406,
|
| 234 |
+
"loss": 0.3839,
|
| 235 |
+
"step": 700
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2,
|
| 239 |
+
"eval_loss": 0.38388848304748535,
|
| 240 |
+
"eval_mae": 0.46622949838638306,
|
| 241 |
+
"eval_mse": 0.38388875126838684,
|
| 242 |
+
"eval_r2": 0.44094833637705777,
|
| 243 |
+
"eval_runtime": 264.3781,
|
| 244 |
+
"eval_samples_per_second": 3.026,
|
| 245 |
+
"eval_steps_per_second": 0.756,
|
| 246 |
+
"step": 700
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3,
|
| 250 |
+
"learning_rate": 0.0009687007013213062,
|
| 251 |
+
"loss": 0.3848,
|
| 252 |
+
"step": 750
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 3,
|
| 256 |
+
"eval_loss": 0.3808014392852783,
|
| 257 |
+
"eval_mae": 0.46472200751304626,
|
| 258 |
+
"eval_mse": 0.38080185651779175,
|
| 259 |
+
"eval_r2": 0.44630267861478945,
|
| 260 |
+
"eval_runtime": 265.0946,
|
| 261 |
+
"eval_samples_per_second": 3.018,
|
| 262 |
+
"eval_steps_per_second": 0.754,
|
| 263 |
+
"step": 750
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 3,
|
| 267 |
+
"learning_rate": 0.0009623706168332644,
|
| 268 |
+
"loss": 0.3821,
|
| 269 |
+
"step": 800
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3,
|
| 273 |
+
"eval_loss": 0.3820662200450897,
|
| 274 |
+
"eval_mae": 0.4652169346809387,
|
| 275 |
+
"eval_mse": 0.3820664882659912,
|
| 276 |
+
"eval_r2": 0.4448990871151196,
|
| 277 |
+
"eval_runtime": 267.613,
|
| 278 |
+
"eval_samples_per_second": 2.989,
|
| 279 |
+
"eval_steps_per_second": 0.747,
|
| 280 |
+
"step": 800
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 3,
|
| 284 |
+
"learning_rate": 0.0009554826723804303,
|
| 285 |
+
"loss": 0.3818,
|
| 286 |
+
"step": 850
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 3,
|
| 290 |
+
"eval_loss": 0.3809438645839691,
|
| 291 |
+
"eval_mae": 0.46468687057495117,
|
| 292 |
+
"eval_mse": 0.3809432089328766,
|
| 293 |
+
"eval_r2": 0.4446287307018585,
|
| 294 |
+
"eval_runtime": 264.0042,
|
| 295 |
+
"eval_samples_per_second": 3.03,
|
| 296 |
+
"eval_steps_per_second": 0.758,
|
| 297 |
+
"step": 850
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 3,
|
| 301 |
+
"learning_rate": 0.0009480451784140092,
|
| 302 |
+
"loss": 0.3824,
|
| 303 |
+
"step": 900
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 3,
|
| 307 |
+
"eval_loss": 0.38150742650032043,
|
| 308 |
+
"eval_mae": 0.4647422134876251,
|
| 309 |
+
"eval_mse": 0.3815067708492279,
|
| 310 |
+
"eval_r2": 0.44662126614575437,
|
| 311 |
+
"eval_runtime": 267.3864,
|
| 312 |
+
"eval_samples_per_second": 2.992,
|
| 313 |
+
"eval_steps_per_second": 0.748,
|
| 314 |
+
"step": 900
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3,
|
| 318 |
+
"learning_rate": 0.0009400671084283606,
|
| 319 |
+
"loss": 0.3816,
|
| 320 |
+
"step": 950
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3,
|
| 324 |
+
"eval_loss": 0.3832119107246399,
|
| 325 |
+
"eval_mae": 0.46604394912719727,
|
| 326 |
+
"eval_mse": 0.3832109272480011,
|
| 327 |
+
"eval_r2": 0.4432983612099932,
|
| 328 |
+
"eval_runtime": 284.3156,
|
| 329 |
+
"eval_samples_per_second": 2.814,
|
| 330 |
+
"eval_steps_per_second": 0.703,
|
| 331 |
+
"step": 950
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4,
|
| 335 |
+
"learning_rate": 0.0009315580881342876,
|
| 336 |
+
"loss": 0.3794,
|
| 337 |
+
"step": 1000
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 4,
|
| 341 |
+
"eval_loss": 0.3803976774215698,
|
| 342 |
+
"eval_mae": 0.4641774296760559,
|
| 343 |
+
"eval_mse": 0.380397766828537,
|
| 344 |
+
"eval_r2": 0.4470804443192825,
|
| 345 |
+
"eval_runtime": 265.2618,
|
| 346 |
+
"eval_samples_per_second": 3.016,
|
| 347 |
+
"eval_steps_per_second": 0.754,
|
| 348 |
+
"step": 1000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 4,
|
| 352 |
+
"learning_rate": 0.000922528383845411,
|
| 353 |
+
"loss": 0.3819,
|
| 354 |
+
"step": 1050
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4,
|
| 358 |
+
"eval_loss": 0.38107830286026,
|
| 359 |
+
"eval_mae": 0.4645218849182129,
|
| 360 |
+
"eval_mse": 0.38107892870903015,
|
| 361 |
+
"eval_r2": 0.4483045268109964,
|
| 362 |
+
"eval_runtime": 265.6012,
|
| 363 |
+
"eval_samples_per_second": 3.012,
|
| 364 |
+
"eval_steps_per_second": 0.753,
|
| 365 |
+
"step": 1050
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 4,
|
| 369 |
+
"learning_rate": 0.0009129888900916457,
|
| 370 |
+
"loss": 0.3799,
|
| 371 |
+
"step": 1100
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 4,
|
| 375 |
+
"eval_loss": 0.38090744614601135,
|
| 376 |
+
"eval_mae": 0.46439129114151,
|
| 377 |
+
"eval_mse": 0.38090750575065613,
|
| 378 |
+
"eval_r2": 0.4488611430910662,
|
| 379 |
+
"eval_runtime": 271.1593,
|
| 380 |
+
"eval_samples_per_second": 2.95,
|
| 381 |
+
"eval_steps_per_second": 0.738,
|
| 382 |
+
"step": 1100
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 4,
|
| 386 |
+
"learning_rate": 0.0009029511164747175,
|
| 387 |
+
"loss": 0.383,
|
| 388 |
+
"step": 1150
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 4,
|
| 392 |
+
"eval_loss": 0.3813271224498749,
|
| 393 |
+
"eval_mae": 0.4647519886493683,
|
| 394 |
+
"eval_mse": 0.38132649660110474,
|
| 395 |
+
"eval_r2": 0.44615534251165345,
|
| 396 |
+
"eval_runtime": 272.9035,
|
| 397 |
+
"eval_samples_per_second": 2.931,
|
| 398 |
+
"eval_steps_per_second": 0.733,
|
| 399 |
+
"step": 1150
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 5,
|
| 403 |
+
"learning_rate": 0.0008924271737815855,
|
| 404 |
+
"loss": 0.3809,
|
| 405 |
+
"step": 1200
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 5,
|
| 409 |
+
"eval_loss": 0.37957870960235596,
|
| 410 |
+
"eval_mae": 0.46358469128608704,
|
| 411 |
+
"eval_mse": 0.3795786499977112,
|
| 412 |
+
"eval_r2": 0.4479695425018687,
|
| 413 |
+
"eval_runtime": 265.8282,
|
| 414 |
+
"eval_samples_per_second": 3.009,
|
| 415 |
+
"eval_steps_per_second": 0.752,
|
| 416 |
+
"step": 1200
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 5,
|
| 420 |
+
"learning_rate": 0.0008814297593725199,
|
| 421 |
+
"loss": 0.3805,
|
| 422 |
+
"step": 1250
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5,
|
| 426 |
+
"eval_loss": 0.38085976243019104,
|
| 427 |
+
"eval_mae": 0.46433085203170776,
|
| 428 |
+
"eval_mse": 0.38085973262786865,
|
| 429 |
+
"eval_r2": 0.44749606591539537,
|
| 430 |
+
"eval_runtime": 270.336,
|
| 431 |
+
"eval_samples_per_second": 2.959,
|
| 432 |
+
"eval_steps_per_second": 0.74,
|
| 433 |
+
"step": 1250
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 5,
|
| 437 |
+
"learning_rate": 0.0008699721418614672,
|
| 438 |
+
"loss": 0.3805,
|
| 439 |
+
"step": 1300
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 5,
|
| 443 |
+
"eval_loss": 0.3793216049671173,
|
| 444 |
+
"eval_mae": 0.46346384286880493,
|
| 445 |
+
"eval_mse": 0.3793216049671173,
|
| 446 |
+
"eval_r2": 0.4494445278203605,
|
| 447 |
+
"eval_runtime": 264.9048,
|
| 448 |
+
"eval_samples_per_second": 3.02,
|
| 449 |
+
"eval_steps_per_second": 0.755,
|
| 450 |
+
"step": 1300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 5,
|
| 454 |
+
"learning_rate": 0.0008580681451071866,
|
| 455 |
+
"loss": 0.3794,
|
| 456 |
+
"step": 1350
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 5,
|
| 460 |
+
"eval_loss": 0.37941062450408936,
|
| 461 |
+
"eval_mae": 0.4636057913303375,
|
| 462 |
+
"eval_mse": 0.37941014766693115,
|
| 463 |
+
"eval_r2": 0.4489888493647255,
|
| 464 |
+
"eval_runtime": 279.0513,
|
| 465 |
+
"eval_samples_per_second": 2.867,
|
| 466 |
+
"eval_steps_per_second": 0.717,
|
| 467 |
+
"step": 1350
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 5,
|
| 471 |
+
"learning_rate": 0.0008457321315344694,
|
| 472 |
+
"loss": 0.3806,
|
| 473 |
+
"step": 1400
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 5,
|
| 477 |
+
"eval_loss": 0.37968844175338745,
|
| 478 |
+
"eval_mae": 0.4636916518211365,
|
| 479 |
+
"eval_mse": 0.3796885013580322,
|
| 480 |
+
"eval_r2": 0.4474722627694526,
|
| 481 |
+
"eval_runtime": 268.6996,
|
| 482 |
+
"eval_samples_per_second": 2.977,
|
| 483 |
+
"eval_steps_per_second": 0.744,
|
| 484 |
+
"step": 1400
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 6,
|
| 488 |
+
"learning_rate": 0.0008329789848055705,
|
| 489 |
+
"loss": 0.3764,
|
| 490 |
+
"step": 1450
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 6,
|
| 494 |
+
"eval_loss": 0.3784217834472656,
|
| 495 |
+
"eval_mae": 0.4628964364528656,
|
| 496 |
+
"eval_mse": 0.37842199206352234,
|
| 497 |
+
"eval_r2": 0.45179472514661223,
|
| 498 |
+
"eval_runtime": 275.6704,
|
| 499 |
+
"eval_samples_per_second": 2.902,
|
| 500 |
+
"eval_steps_per_second": 0.726,
|
| 501 |
+
"step": 1450
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 6,
|
| 505 |
+
"learning_rate": 0.0008198240918627525,
|
| 506 |
+
"loss": 0.3802,
|
| 507 |
+
"step": 1500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 6,
|
| 511 |
+
"eval_loss": 0.3779056966304779,
|
| 512 |
+
"eval_mae": 0.4623972177505493,
|
| 513 |
+
"eval_mse": 0.37790581583976746,
|
| 514 |
+
"eval_r2": 0.45185399059020337,
|
| 515 |
+
"eval_runtime": 269.5949,
|
| 516 |
+
"eval_samples_per_second": 2.967,
|
| 517 |
+
"eval_steps_per_second": 0.742,
|
| 518 |
+
"step": 1500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 6,
|
| 522 |
+
"learning_rate": 0.0008062833243636134,
|
| 523 |
+
"loss": 0.3787,
|
| 524 |
+
"step": 1550
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 6,
|
| 528 |
+
"eval_loss": 0.3789410889148712,
|
| 529 |
+
"eval_mae": 0.46288514137268066,
|
| 530 |
+
"eval_mse": 0.37894150614738464,
|
| 531 |
+
"eval_r2": 0.4510378453068221,
|
| 532 |
+
"eval_runtime": 291.6469,
|
| 533 |
+
"eval_samples_per_second": 2.743,
|
| 534 |
+
"eval_steps_per_second": 0.686,
|
| 535 |
+
"step": 1550
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 6,
|
| 539 |
+
"learning_rate": 0.0007923730195315961,
|
| 540 |
+
"loss": 0.379,
|
| 541 |
+
"step": 1600
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 6,
|
| 545 |
+
"eval_loss": 0.3779994249343872,
|
| 546 |
+
"eval_mae": 0.4624533951282501,
|
| 547 |
+
"eval_mse": 0.377999484539032,
|
| 548 |
+
"eval_r2": 0.4508841579385672,
|
| 549 |
+
"eval_runtime": 278.879,
|
| 550 |
+
"eval_samples_per_second": 2.869,
|
| 551 |
+
"eval_steps_per_second": 0.717,
|
| 552 |
+
"step": 1600
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 6,
|
| 556 |
+
"learning_rate": 0.0007781099604447793,
|
| 557 |
+
"loss": 0.3765,
|
| 558 |
+
"step": 1650
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 6,
|
| 562 |
+
"eval_loss": 0.37762123346328735,
|
| 563 |
+
"eval_mae": 0.4622168242931366,
|
| 564 |
+
"eval_mse": 0.37762120366096497,
|
| 565 |
+
"eval_r2": 0.452898354940625,
|
| 566 |
+
"eval_runtime": 278.1979,
|
| 567 |
+
"eval_samples_per_second": 2.876,
|
| 568 |
+
"eval_steps_per_second": 0.719,
|
| 569 |
+
"step": 1650
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 7,
|
| 573 |
+
"learning_rate": 0.0007635113557867395,
|
| 574 |
+
"loss": 0.3797,
|
| 575 |
+
"step": 1700
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 7,
|
| 579 |
+
"eval_loss": 0.37847700715065,
|
| 580 |
+
"eval_mae": 0.4626946747303009,
|
| 581 |
+
"eval_mse": 0.378477543592453,
|
| 582 |
+
"eval_r2": 0.4524606040645045,
|
| 583 |
+
"eval_runtime": 265.647,
|
| 584 |
+
"eval_samples_per_second": 3.012,
|
| 585 |
+
"eval_steps_per_second": 0.753,
|
| 586 |
+
"step": 1700
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 7,
|
| 590 |
+
"learning_rate": 0.0007485948190839076,
|
| 591 |
+
"loss": 0.3772,
|
| 592 |
+
"step": 1750
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 7,
|
| 596 |
+
"eval_loss": 0.3774454891681671,
|
| 597 |
+
"eval_mae": 0.46223533153533936,
|
| 598 |
+
"eval_mse": 0.37744590640068054,
|
| 599 |
+
"eval_r2": 0.45290920313283933,
|
| 600 |
+
"eval_runtime": 268.9714,
|
| 601 |
+
"eval_samples_per_second": 2.974,
|
| 602 |
+
"eval_steps_per_second": 0.744,
|
| 603 |
+
"step": 1750
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 7,
|
| 607 |
+
"learning_rate": 0.0007333783474544757,
|
| 608 |
+
"loss": 0.3792,
|
| 609 |
+
"step": 1800
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 7,
|
| 613 |
+
"eval_loss": 0.37726637721061707,
|
| 614 |
+
"eval_mae": 0.46205469965934753,
|
| 615 |
+
"eval_mse": 0.3772661089897156,
|
| 616 |
+
"eval_r2": 0.45215750792291154,
|
| 617 |
+
"eval_runtime": 270.804,
|
| 618 |
+
"eval_samples_per_second": 2.954,
|
| 619 |
+
"eval_steps_per_second": 0.739,
|
| 620 |
+
"step": 1800
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 7,
|
| 624 |
+
"learning_rate": 0.0007178802998944933,
|
| 625 |
+
"loss": 0.3753,
|
| 626 |
+
"step": 1850
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 7,
|
| 630 |
+
"eval_loss": 0.3767879009246826,
|
| 631 |
+
"eval_mae": 0.4616534411907196,
|
| 632 |
+
"eval_mse": 0.3767889440059662,
|
| 633 |
+
"eval_r2": 0.4520469227666626,
|
| 634 |
+
"eval_runtime": 263.9276,
|
| 635 |
+
"eval_samples_per_second": 3.031,
|
| 636 |
+
"eval_steps_per_second": 0.758,
|
| 637 |
+
"step": 1850
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 7,
|
| 641 |
+
"learning_rate": 0.0007021193751273463,
|
| 642 |
+
"loss": 0.3758,
|
| 643 |
+
"step": 1900
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 7,
|
| 647 |
+
"eval_loss": 0.37764108180999756,
|
| 648 |
+
"eval_mae": 0.4621761739253998,
|
| 649 |
+
"eval_mse": 0.37764135003089905,
|
| 650 |
+
"eval_r2": 0.45377418641465317,
|
| 651 |
+
"eval_runtime": 283.3511,
|
| 652 |
+
"eval_samples_per_second": 2.823,
|
| 653 |
+
"eval_steps_per_second": 0.706,
|
| 654 |
+
"step": 1900
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 8,
|
| 658 |
+
"learning_rate": 0.0006861145890433519,
|
| 659 |
+
"loss": 0.377,
|
| 660 |
+
"step": 1950
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 8,
|
| 664 |
+
"eval_loss": 0.3769887685775757,
|
| 665 |
+
"eval_mae": 0.46189454197883606,
|
| 666 |
+
"eval_mse": 0.37698760628700256,
|
| 667 |
+
"eval_r2": 0.45451653345429155,
|
| 668 |
+
"eval_runtime": 269.8194,
|
| 669 |
+
"eval_samples_per_second": 2.965,
|
| 670 |
+
"eval_steps_per_second": 0.741,
|
| 671 |
+
"step": 1950
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 8,
|
| 675 |
+
"learning_rate": 0.0006698852517566836,
|
| 676 |
+
"loss": 0.3761,
|
| 677 |
+
"step": 2000
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 8,
|
| 681 |
+
"eval_loss": 0.3763187527656555,
|
| 682 |
+
"eval_mae": 0.4613550901412964,
|
| 683 |
+
"eval_mse": 0.3763185143470764,
|
| 684 |
+
"eval_r2": 0.45283548813003005,
|
| 685 |
+
"eval_runtime": 272.1057,
|
| 686 |
+
"eval_samples_per_second": 2.94,
|
| 687 |
+
"eval_steps_per_second": 0.735,
|
| 688 |
+
"step": 2000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 8,
|
| 692 |
+
"learning_rate": 0.0006534509443073072,
|
| 693 |
+
"loss": 0.3764,
|
| 694 |
+
"step": 2050
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 8,
|
| 698 |
+
"eval_loss": 0.3749840557575226,
|
| 699 |
+
"eval_mae": 0.46052685379981995,
|
| 700 |
+
"eval_mse": 0.37498345971107483,
|
| 701 |
+
"eval_r2": 0.45454628406748754,
|
| 702 |
+
"eval_runtime": 277.2032,
|
| 703 |
+
"eval_samples_per_second": 2.886,
|
| 704 |
+
"eval_steps_per_second": 0.721,
|
| 705 |
+
"step": 2050
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 8,
|
| 709 |
+
"learning_rate": 0.0006368314950360416,
|
| 710 |
+
"loss": 0.3747,
|
| 711 |
+
"step": 2100
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 8,
|
| 715 |
+
"eval_loss": 0.37445199489593506,
|
| 716 |
+
"eval_mae": 0.46010997891426086,
|
| 717 |
+
"eval_mse": 0.3744511008262634,
|
| 718 |
+
"eval_r2": 0.4568363191792082,
|
| 719 |
+
"eval_runtime": 276.9731,
|
| 720 |
+
"eval_samples_per_second": 2.888,
|
| 721 |
+
"eval_steps_per_second": 0.722,
|
| 722 |
+
"step": 2100
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 9,
|
| 726 |
+
"learning_rate": 0.0006200469556612435,
|
| 727 |
+
"loss": 0.3754,
|
| 728 |
+
"step": 2150
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 9,
|
| 732 |
+
"eval_loss": 0.3743913769721985,
|
| 733 |
+
"eval_mae": 0.4600675106048584,
|
| 734 |
+
"eval_mse": 0.3743920922279358,
|
| 735 |
+
"eval_r2": 0.45744293340515363,
|
| 736 |
+
"eval_runtime": 281.3782,
|
| 737 |
+
"eval_samples_per_second": 2.843,
|
| 738 |
+
"eval_steps_per_second": 0.711,
|
| 739 |
+
"step": 2150
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 9,
|
| 743 |
+
"learning_rate": 0.0006031175770859848,
|
| 744 |
+
"loss": 0.3736,
|
| 745 |
+
"step": 2200
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 9,
|
| 749 |
+
"eval_loss": 0.3738979399204254,
|
| 750 |
+
"eval_mae": 0.45969095826148987,
|
| 751 |
+
"eval_mse": 0.37389707565307617,
|
| 752 |
+
"eval_r2": 0.4581812073615178,
|
| 753 |
+
"eval_runtime": 270.2281,
|
| 754 |
+
"eval_samples_per_second": 2.96,
|
| 755 |
+
"eval_steps_per_second": 0.74,
|
| 756 |
+
"step": 2200
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 9,
|
| 760 |
+
"learning_rate": 0.0005860637849649073,
|
| 761 |
+
"loss": 0.3743,
|
| 762 |
+
"step": 2250
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 9,
|
| 766 |
+
"eval_loss": 0.3741012513637543,
|
| 767 |
+
"eval_mae": 0.4597731828689575,
|
| 768 |
+
"eval_mse": 0.37410181760787964,
|
| 769 |
+
"eval_r2": 0.4575432685303391,
|
| 770 |
+
"eval_runtime": 278.4971,
|
| 771 |
+
"eval_samples_per_second": 2.873,
|
| 772 |
+
"eval_steps_per_second": 0.718,
|
| 773 |
+
"step": 2250
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 9,
|
| 777 |
+
"learning_rate": 0.000568906155060237,
|
| 778 |
+
"loss": 0.3734,
|
| 779 |
+
"step": 2300
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 9,
|
| 783 |
+
"eval_loss": 0.37282341718673706,
|
| 784 |
+
"eval_mae": 0.4590661823749542,
|
| 785 |
+
"eval_mse": 0.3728235960006714,
|
| 786 |
+
"eval_r2": 0.457423055516365,
|
| 787 |
+
"eval_runtime": 279.5267,
|
| 788 |
+
"eval_samples_per_second": 2.862,
|
| 789 |
+
"eval_steps_per_second": 0.715,
|
| 790 |
+
"step": 2300
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 9,
|
| 794 |
+
"learning_rate": 0.0005516653884166902,
|
| 795 |
+
"loss": 0.371,
|
| 796 |
+
"step": 2350
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 9,
|
| 800 |
+
"eval_loss": 0.3734956681728363,
|
| 801 |
+
"eval_mae": 0.45936986804008484,
|
| 802 |
+
"eval_mse": 0.3734953701496124,
|
| 803 |
+
"eval_r2": 0.4600796269569801,
|
| 804 |
+
"eval_runtime": 274.1528,
|
| 805 |
+
"eval_samples_per_second": 2.918,
|
| 806 |
+
"eval_steps_per_second": 0.73,
|
| 807 |
+
"step": 2350
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 10,
|
| 811 |
+
"learning_rate": 0.0005343622863852232,
|
| 812 |
+
"loss": 0.3754,
|
| 813 |
+
"step": 2400
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 10,
|
| 817 |
+
"eval_loss": 0.3738192021846771,
|
| 818 |
+
"eval_mae": 0.45952871441841125,
|
| 819 |
+
"eval_mse": 0.37381842732429504,
|
| 820 |
+
"eval_r2": 0.4592306947745455,
|
| 821 |
+
"eval_runtime": 277.5843,
|
| 822 |
+
"eval_samples_per_second": 2.882,
|
| 823 |
+
"eval_steps_per_second": 0.721,
|
| 824 |
+
"step": 2400
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 10,
|
| 828 |
+
"learning_rate": 0.0005170177255257618,
|
| 829 |
+
"loss": 0.373,
|
| 830 |
+
"step": 2450
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 10,
|
| 834 |
+
"eval_loss": 0.3726402521133423,
|
| 835 |
+
"eval_mae": 0.4587893486022949,
|
| 836 |
+
"eval_mse": 0.3726405203342438,
|
| 837 |
+
"eval_r2": 0.45936278859727786,
|
| 838 |
+
"eval_runtime": 281.2863,
|
| 839 |
+
"eval_samples_per_second": 2.844,
|
| 840 |
+
"eval_steps_per_second": 0.711,
|
| 841 |
+
"step": 2450
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 10,
|
| 845 |
+
"learning_rate": 0.0004996526324191872,
|
| 846 |
+
"loss": 0.3717,
|
| 847 |
+
"step": 2500
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 10,
|
| 851 |
+
"eval_loss": 0.37096771597862244,
|
| 852 |
+
"eval_mae": 0.45787444710731506,
|
| 853 |
+
"eval_mse": 0.3709667921066284,
|
| 854 |
+
"eval_r2": 0.4609350988985167,
|
| 855 |
+
"eval_runtime": 270.5778,
|
| 856 |
+
"eval_samples_per_second": 2.957,
|
| 857 |
+
"eval_steps_per_second": 0.739,
|
| 858 |
+
"step": 2500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 10,
|
| 862 |
+
"learning_rate": 0.0004822879584189731,
|
| 863 |
+
"loss": 0.3727,
|
| 864 |
+
"step": 2550
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 10,
|
| 868 |
+
"eval_loss": 0.3726476728916168,
|
| 869 |
+
"eval_mae": 0.4586939215660095,
|
| 870 |
+
"eval_mse": 0.37264758348464966,
|
| 871 |
+
"eval_r2": 0.4587349241462606,
|
| 872 |
+
"eval_runtime": 273.9493,
|
| 873 |
+
"eval_samples_per_second": 2.92,
|
| 874 |
+
"eval_steps_per_second": 0.73,
|
| 875 |
+
"step": 2550
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 10,
|
| 879 |
+
"learning_rate": 0.0004649446543729322,
|
| 880 |
+
"loss": 0.372,
|
| 881 |
+
"step": 2600
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 10,
|
| 885 |
+
"eval_loss": 0.37159234285354614,
|
| 886 |
+
"eval_mae": 0.4583428204059601,
|
| 887 |
+
"eval_mse": 0.3715912401676178,
|
| 888 |
+
"eval_r2": 0.4603821208241091,
|
| 889 |
+
"eval_runtime": 278.26,
|
| 890 |
+
"eval_samples_per_second": 2.875,
|
| 891 |
+
"eval_steps_per_second": 0.719,
|
| 892 |
+
"step": 2600
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 11,
|
| 896 |
+
"learning_rate": 0.0004476436453455742,
|
| 897 |
+
"loss": 0.3715,
|
| 898 |
+
"step": 2650
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 11,
|
| 902 |
+
"eval_loss": 0.3717365562915802,
|
| 903 |
+
"eval_mae": 0.4582462012767792,
|
| 904 |
+
"eval_mse": 0.3717361092567444,
|
| 905 |
+
"eval_r2": 0.45976387138394437,
|
| 906 |
+
"eval_runtime": 292.146,
|
| 907 |
+
"eval_samples_per_second": 2.738,
|
| 908 |
+
"eval_steps_per_second": 0.685,
|
| 909 |
+
"step": 2650
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 11,
|
| 913 |
+
"learning_rate": 0.0004304058053715702,
|
| 914 |
+
"loss": 0.3717,
|
| 915 |
+
"step": 2700
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 11,
|
| 919 |
+
"eval_loss": 0.3717900216579437,
|
| 920 |
+
"eval_mae": 0.45822903513908386,
|
| 921 |
+
"eval_mse": 0.37178927659988403,
|
| 922 |
+
"eval_r2": 0.45998171303819835,
|
| 923 |
+
"eval_runtime": 269.82,
|
| 924 |
+
"eval_samples_per_second": 2.965,
|
| 925 |
+
"eval_steps_per_second": 0.741,
|
| 926 |
+
"step": 2700
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 11,
|
| 930 |
+
"learning_rate": 0.0004132519322707882,
|
| 931 |
+
"loss": 0.3707,
|
| 932 |
+
"step": 2750
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 11,
|
| 936 |
+
"eval_loss": 0.3708600699901581,
|
| 937 |
+
"eval_mae": 0.45766767859458923,
|
| 938 |
+
"eval_mse": 0.3708597719669342,
|
| 939 |
+
"eval_r2": 0.4603013858171726,
|
| 940 |
+
"eval_runtime": 269.9605,
|
| 941 |
+
"eval_samples_per_second": 2.963,
|
| 942 |
+
"eval_steps_per_second": 0.741,
|
| 943 |
+
"step": 2750
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 11,
|
| 947 |
+
"learning_rate": 0.00039620272255528065,
|
| 948 |
+
"loss": 0.3739,
|
| 949 |
+
"step": 2800
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 11,
|
| 953 |
+
"eval_loss": 0.3721630573272705,
|
| 954 |
+
"eval_mae": 0.4584360122680664,
|
| 955 |
+
"eval_mse": 0.37216344475746155,
|
| 956 |
+
"eval_r2": 0.459010225690355,
|
| 957 |
+
"eval_runtime": 268.3335,
|
| 958 |
+
"eval_samples_per_second": 2.981,
|
| 959 |
+
"eval_steps_per_second": 0.745,
|
| 960 |
+
"step": 2800
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 11,
|
| 964 |
+
"learning_rate": 0.000379278746458504,
|
| 965 |
+
"loss": 0.3702,
|
| 966 |
+
"step": 2850
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 11,
|
| 970 |
+
"eval_loss": 0.37071841955184937,
|
| 971 |
+
"eval_mae": 0.4574899673461914,
|
| 972 |
+
"eval_mse": 0.3707171678543091,
|
| 973 |
+
"eval_r2": 0.4613746011063965,
|
| 974 |
+
"eval_runtime": 279.1852,
|
| 975 |
+
"eval_samples_per_second": 2.865,
|
| 976 |
+
"eval_steps_per_second": 0.716,
|
| 977 |
+
"step": 2850
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 12,
|
| 981 |
+
"learning_rate": 0.000362500423116895,
|
| 982 |
+
"loss": 0.3712,
|
| 983 |
+
"step": 2900
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 12,
|
| 987 |
+
"eval_loss": 0.37087440490722656,
|
| 988 |
+
"eval_mae": 0.45766788721084595,
|
| 989 |
+
"eval_mse": 0.37087327241897583,
|
| 990 |
+
"eval_r2": 0.4618904862700307,
|
| 991 |
+
"eval_runtime": 292.1987,
|
| 992 |
+
"eval_samples_per_second": 2.738,
|
| 993 |
+
"eval_steps_per_second": 0.684,
|
| 994 |
+
"step": 2900
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 12,
|
| 998 |
+
"learning_rate": 0.0003458879959337494,
|
| 999 |
+
"loss": 0.3693,
|
| 1000 |
+
"step": 2950
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 12,
|
| 1004 |
+
"eval_loss": 0.3699745535850525,
|
| 1005 |
+
"eval_mae": 0.4571460485458374,
|
| 1006 |
+
"eval_mse": 0.36997491121292114,
|
| 1007 |
+
"eval_r2": 0.4619671878026411,
|
| 1008 |
+
"eval_runtime": 273.9573,
|
| 1009 |
+
"eval_samples_per_second": 2.92,
|
| 1010 |
+
"eval_steps_per_second": 0.73,
|
| 1011 |
+
"step": 2950
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 12,
|
| 1015 |
+
"learning_rate": 0.00032946150815512586,
|
| 1016 |
+
"loss": 0.3719,
|
| 1017 |
+
"step": 3000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 12,
|
| 1021 |
+
"eval_loss": 0.3705122470855713,
|
| 1022 |
+
"eval_mae": 0.45748522877693176,
|
| 1023 |
+
"eval_mse": 0.37051278352737427,
|
| 1024 |
+
"eval_r2": 0.46142887892760176,
|
| 1025 |
+
"eval_runtime": 268.3928,
|
| 1026 |
+
"eval_samples_per_second": 2.981,
|
| 1027 |
+
"eval_steps_per_second": 0.745,
|
| 1028 |
+
"step": 3000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 12,
|
| 1032 |
+
"learning_rate": 0.0003132407786872442,
|
| 1033 |
+
"loss": 0.3716,
|
| 1034 |
+
"step": 3050
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 12,
|
| 1038 |
+
"eval_loss": 0.3708195388317108,
|
| 1039 |
+
"eval_mae": 0.45740067958831787,
|
| 1040 |
+
"eval_mse": 0.3708195090293884,
|
| 1041 |
+
"eval_r2": 0.4616999176965736,
|
| 1042 |
+
"eval_runtime": 273.3209,
|
| 1043 |
+
"eval_samples_per_second": 2.927,
|
| 1044 |
+
"eval_steps_per_second": 0.732,
|
| 1045 |
+
"step": 3050
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 13,
|
| 1049 |
+
"learning_rate": 0.00029724537818455465,
|
| 1050 |
+
"loss": 0.3693,
|
| 1051 |
+
"step": 3100
|
| 1052 |
+
},
|
| 1053 |
+
{
|
| 1054 |
+
"epoch": 13,
|
| 1055 |
+
"eval_loss": 0.3704887628555298,
|
| 1056 |
+
"eval_mae": 0.45740318298339844,
|
| 1057 |
+
"eval_mse": 0.37048864364624023,
|
| 1058 |
+
"eval_r2": 0.4616717003785853,
|
| 1059 |
+
"eval_runtime": 273.739,
|
| 1060 |
+
"eval_samples_per_second": 2.922,
|
| 1061 |
+
"eval_steps_per_second": 0.731,
|
| 1062 |
+
"step": 3100
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 13,
|
| 1066 |
+
"learning_rate": 0.00028149460543732666,
|
| 1067 |
+
"loss": 0.3706,
|
| 1068 |
+
"step": 3150
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 13,
|
| 1072 |
+
"eval_loss": 0.37004169821739197,
|
| 1073 |
+
"eval_mae": 0.45711666345596313,
|
| 1074 |
+
"eval_mse": 0.37004172801971436,
|
| 1075 |
+
"eval_r2": 0.46274949898335205,
|
| 1076 |
+
"eval_runtime": 265.1017,
|
| 1077 |
+
"eval_samples_per_second": 3.018,
|
| 1078 |
+
"eval_steps_per_second": 0.754,
|
| 1079 |
+
"step": 3150
|
| 1080 |
+
},
|
| 1081 |
+
{
|
| 1082 |
+
"epoch": 13,
|
| 1083 |
+
"learning_rate": 0.00026600746408725063,
|
| 1084 |
+
"loss": 0.3703,
|
| 1085 |
+
"step": 3200
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 13,
|
| 1089 |
+
"eval_loss": 0.3703955113887787,
|
| 1090 |
+
"eval_mae": 0.45735496282577515,
|
| 1091 |
+
"eval_mse": 0.37039563059806824,
|
| 1092 |
+
"eval_r2": 0.4622188399376109,
|
| 1093 |
+
"eval_runtime": 287.415,
|
| 1094 |
+
"eval_samples_per_second": 2.783,
|
| 1095 |
+
"eval_steps_per_second": 0.696,
|
| 1096 |
+
"step": 3200
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 13,
|
| 1100 |
+
"learning_rate": 0.000250802639699139,
|
| 1101 |
+
"loss": 0.3693,
|
| 1102 |
+
"step": 3250
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 13,
|
| 1106 |
+
"eval_loss": 0.37047404050827026,
|
| 1107 |
+
"eval_mae": 0.45720237493515015,
|
| 1108 |
+
"eval_mse": 0.37047335505485535,
|
| 1109 |
+
"eval_r2": 0.46234450920301984,
|
| 1110 |
+
"eval_runtime": 265.936,
|
| 1111 |
+
"eval_samples_per_second": 3.008,
|
| 1112 |
+
"eval_steps_per_second": 0.752,
|
| 1113 |
+
"step": 3250
|
| 1114 |
+
}
|
| 1115 |
+
],
|
| 1116 |
+
"max_steps": 4760,
|
| 1117 |
+
"num_train_epochs": 20,
|
| 1118 |
+
"total_flos": 0.0,
|
| 1119 |
+
"trial_name": null,
|
| 1120 |
+
"trial_params": null
|
| 1121 |
+
}
|
checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a0ea0e252e14911a2d3e2e2b236a6871913290ad9a3dc525b758414542a2e479
|
| 3 |
+
size 4143
|