Commit
•
92a94c8
1
Parent(s):
4539b83
Model save
Browse files- README.md +121 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- runs/Aug18_04-44-56_9mqd6r3-l/events.out.tfevents.1723949106.9mqd6r3-l.2101535.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +1081 -0
README.md
ADDED
|
@@ -0,0 +1,121 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
license: llama3.1
|
| 5 |
+
tags:
|
| 6 |
+
- trl
|
| 7 |
+
- sft
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: Llama-31-8B_task-2_60-samples_config-4
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# Llama-31-8B_task-2_60-samples_config-4
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on an unknown dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.7192
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- gradient_accumulation_steps: 16
|
| 46 |
+
- total_train_batch_size: 16
|
| 47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 48 |
+
- lr_scheduler_type: cosine
|
| 49 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
+
- num_epochs: 150
|
| 51 |
+
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 56 |
+
| 1.0749 | 0.6957 | 2 | 1.0966 |
|
| 57 |
+
| 1.0739 | 1.7391 | 5 | 1.0942 |
|
| 58 |
+
| 1.0883 | 2.7826 | 8 | 1.0905 |
|
| 59 |
+
| 1.0572 | 3.8261 | 11 | 1.0844 |
|
| 60 |
+
| 1.0814 | 4.8696 | 14 | 1.0741 |
|
| 61 |
+
| 1.0423 | 5.9130 | 17 | 1.0622 |
|
| 62 |
+
| 1.0626 | 6.9565 | 20 | 1.0462 |
|
| 63 |
+
| 1.0118 | 8.0 | 23 | 1.0248 |
|
| 64 |
+
| 1.0176 | 8.6957 | 25 | 1.0099 |
|
| 65 |
+
| 0.9728 | 9.7391 | 28 | 0.9822 |
|
| 66 |
+
| 0.9567 | 10.7826 | 31 | 0.9527 |
|
| 67 |
+
| 0.9202 | 11.8261 | 34 | 0.9259 |
|
| 68 |
+
| 0.9099 | 12.8696 | 37 | 0.9015 |
|
| 69 |
+
| 0.8806 | 13.9130 | 40 | 0.8828 |
|
| 70 |
+
| 0.7975 | 14.9565 | 43 | 0.8661 |
|
| 71 |
+
| 0.8572 | 16.0 | 46 | 0.8533 |
|
| 72 |
+
| 0.8342 | 16.6957 | 48 | 0.8447 |
|
| 73 |
+
| 0.8242 | 17.7391 | 51 | 0.8331 |
|
| 74 |
+
| 0.7954 | 18.7826 | 54 | 0.8223 |
|
| 75 |
+
| 0.8235 | 19.8261 | 57 | 0.8122 |
|
| 76 |
+
| 0.7896 | 20.8696 | 60 | 0.8017 |
|
| 77 |
+
| 0.7775 | 21.9130 | 63 | 0.7933 |
|
| 78 |
+
| 0.7315 | 22.9565 | 66 | 0.7862 |
|
| 79 |
+
| 0.7702 | 24.0 | 69 | 0.7800 |
|
| 80 |
+
| 0.7262 | 24.6957 | 71 | 0.7756 |
|
| 81 |
+
| 0.7683 | 25.7391 | 74 | 0.7715 |
|
| 82 |
+
| 0.7043 | 26.7826 | 77 | 0.7656 |
|
| 83 |
+
| 0.7314 | 27.8261 | 80 | 0.7621 |
|
| 84 |
+
| 0.7093 | 28.8696 | 83 | 0.7586 |
|
| 85 |
+
| 0.7047 | 29.9130 | 86 | 0.7542 |
|
| 86 |
+
| 0.707 | 30.9565 | 89 | 0.7506 |
|
| 87 |
+
| 0.7128 | 32.0 | 92 | 0.7475 |
|
| 88 |
+
| 0.676 | 32.6957 | 94 | 0.7451 |
|
| 89 |
+
| 0.7113 | 33.7391 | 97 | 0.7420 |
|
| 90 |
+
| 0.6733 | 34.7826 | 100 | 0.7396 |
|
| 91 |
+
| 0.698 | 35.8261 | 103 | 0.7370 |
|
| 92 |
+
| 0.6868 | 36.8696 | 106 | 0.7339 |
|
| 93 |
+
| 0.6633 | 37.9130 | 109 | 0.7310 |
|
| 94 |
+
| 0.675 | 38.9565 | 112 | 0.7296 |
|
| 95 |
+
| 0.6563 | 40.0 | 115 | 0.7270 |
|
| 96 |
+
| 0.64 | 40.6957 | 117 | 0.7257 |
|
| 97 |
+
| 0.6314 | 41.7391 | 120 | 0.7242 |
|
| 98 |
+
| 0.619 | 42.7826 | 123 | 0.7225 |
|
| 99 |
+
| 0.6256 | 43.8261 | 126 | 0.7211 |
|
| 100 |
+
| 0.634 | 44.8696 | 129 | 0.7198 |
|
| 101 |
+
| 0.5984 | 45.9130 | 132 | 0.7185 |
|
| 102 |
+
| 0.636 | 46.9565 | 135 | 0.7176 |
|
| 103 |
+
| 0.6084 | 48.0 | 138 | 0.7173 |
|
| 104 |
+
| 0.6068 | 48.6957 | 140 | 0.7168 |
|
| 105 |
+
| 0.5982 | 49.7391 | 143 | 0.7166 |
|
| 106 |
+
| 0.6024 | 50.7826 | 146 | 0.7171 |
|
| 107 |
+
| 0.5876 | 51.8261 | 149 | 0.7170 |
|
| 108 |
+
| 0.5852 | 52.8696 | 152 | 0.7169 |
|
| 109 |
+
| 0.5803 | 53.9130 | 155 | 0.7175 |
|
| 110 |
+
| 0.5794 | 54.9565 | 158 | 0.7172 |
|
| 111 |
+
| 0.5699 | 56.0 | 161 | 0.7188 |
|
| 112 |
+
| 0.5722 | 56.6957 | 163 | 0.7192 |
|
| 113 |
+
|
| 114 |
+
|
| 115 |
+
### Framework versions
|
| 116 |
+
|
| 117 |
+
- PEFT 0.12.0
|
| 118 |
+
- Transformers 4.44.0
|
| 119 |
+
- Pytorch 2.1.2+cu121
|
| 120 |
+
- Datasets 2.20.0
|
| 121 |
+
- Tokenizers 0.19.1
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 167832240
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4cd1f36d2c6f94a8c6a4b04570d48af312f60437c8631a48c36bd38c6e72ec7
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 56.69565217391305,
|
| 3 |
+
"total_flos": 2.5340798505582592e+17,
|
| 4 |
+
"train_loss": 0.767207163243206,
|
| 5 |
+
"train_runtime": 9109.3845,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 0.757,
|
| 8 |
+
"train_steps_per_second": 0.033
|
| 9 |
+
}
|
runs/Aug18_04-44-56_9mqd6r3-l/events.out.tfevents.1723949106.9mqd6r3-l.2101535.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46642c6b55fe7b68193303b0b2e3ffb40c3b40429e4fe2ac63f39b6b5e925acb
|
| 3 |
+
size 39440
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 56.69565217391305,
|
| 3 |
+
"total_flos": 2.5340798505582592e+17,
|
| 4 |
+
"train_loss": 0.767207163243206,
|
| 5 |
+
"train_runtime": 9109.3845,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 0.757,
|
| 8 |
+
"train_steps_per_second": 0.033
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1081 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7166422009468079,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-2_60-samples_config-4/checkpoint-143",
|
| 4 |
+
"epoch": 56.69565217391305,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 163,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.34782608695652173,
|
| 13 |
+
"grad_norm": 0.6984618902206421,
|
| 14 |
+
"learning_rate": 3.3333333333333335e-07,
|
| 15 |
+
"loss": 1.1182,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.6956521739130435,
|
| 20 |
+
"grad_norm": 0.6601165533065796,
|
| 21 |
+
"learning_rate": 6.666666666666667e-07,
|
| 22 |
+
"loss": 1.0749,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6956521739130435,
|
| 27 |
+
"eval_loss": 1.0965907573699951,
|
| 28 |
+
"eval_runtime": 12.9785,
|
| 29 |
+
"eval_samples_per_second": 0.925,
|
| 30 |
+
"eval_steps_per_second": 0.925,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.391304347826087,
|
| 35 |
+
"grad_norm": 0.7221220135688782,
|
| 36 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 37 |
+
"loss": 1.0739,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.7391304347826086,
|
| 42 |
+
"eval_loss": 1.0941747426986694,
|
| 43 |
+
"eval_runtime": 12.9817,
|
| 44 |
+
"eval_samples_per_second": 0.924,
|
| 45 |
+
"eval_steps_per_second": 0.924,
|
| 46 |
+
"step": 5
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.0869565217391304,
|
| 50 |
+
"grad_norm": 0.6844056844711304,
|
| 51 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 52 |
+
"loss": 1.0805,
|
| 53 |
+
"step": 6
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 2.782608695652174,
|
| 57 |
+
"grad_norm": 0.7226310968399048,
|
| 58 |
+
"learning_rate": 2.666666666666667e-06,
|
| 59 |
+
"loss": 1.0883,
|
| 60 |
+
"step": 8
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 2.782608695652174,
|
| 64 |
+
"eval_loss": 1.0905098915100098,
|
| 65 |
+
"eval_runtime": 12.9814,
|
| 66 |
+
"eval_samples_per_second": 0.924,
|
| 67 |
+
"eval_steps_per_second": 0.924,
|
| 68 |
+
"step": 8
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.4782608695652173,
|
| 72 |
+
"grad_norm": 0.6965072751045227,
|
| 73 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 74 |
+
"loss": 1.0572,
|
| 75 |
+
"step": 10
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.8260869565217392,
|
| 79 |
+
"eval_loss": 1.084372878074646,
|
| 80 |
+
"eval_runtime": 12.9774,
|
| 81 |
+
"eval_samples_per_second": 0.925,
|
| 82 |
+
"eval_steps_per_second": 0.925,
|
| 83 |
+
"step": 11
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 4.173913043478261,
|
| 87 |
+
"grad_norm": 0.6885063648223877,
|
| 88 |
+
"learning_rate": 4.000000000000001e-06,
|
| 89 |
+
"loss": 1.0867,
|
| 90 |
+
"step": 12
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 4.869565217391305,
|
| 94 |
+
"grad_norm": 0.7193288803100586,
|
| 95 |
+
"learning_rate": 4.666666666666667e-06,
|
| 96 |
+
"loss": 1.0814,
|
| 97 |
+
"step": 14
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 4.869565217391305,
|
| 101 |
+
"eval_loss": 1.0741270780563354,
|
| 102 |
+
"eval_runtime": 12.9811,
|
| 103 |
+
"eval_samples_per_second": 0.924,
|
| 104 |
+
"eval_steps_per_second": 0.924,
|
| 105 |
+
"step": 14
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 5.565217391304348,
|
| 109 |
+
"grad_norm": 0.6680200099945068,
|
| 110 |
+
"learning_rate": 5.333333333333334e-06,
|
| 111 |
+
"loss": 1.0423,
|
| 112 |
+
"step": 16
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 5.913043478260869,
|
| 116 |
+
"eval_loss": 1.0622462034225464,
|
| 117 |
+
"eval_runtime": 12.9802,
|
| 118 |
+
"eval_samples_per_second": 0.924,
|
| 119 |
+
"eval_steps_per_second": 0.924,
|
| 120 |
+
"step": 17
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 6.260869565217392,
|
| 124 |
+
"grad_norm": 0.669226348400116,
|
| 125 |
+
"learning_rate": 6e-06,
|
| 126 |
+
"loss": 1.0248,
|
| 127 |
+
"step": 18
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 6.956521739130435,
|
| 131 |
+
"grad_norm": 0.6525329947471619,
|
| 132 |
+
"learning_rate": 6.666666666666667e-06,
|
| 133 |
+
"loss": 1.0626,
|
| 134 |
+
"step": 20
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.956521739130435,
|
| 138 |
+
"eval_loss": 1.0461969375610352,
|
| 139 |
+
"eval_runtime": 12.9785,
|
| 140 |
+
"eval_samples_per_second": 0.925,
|
| 141 |
+
"eval_steps_per_second": 0.925,
|
| 142 |
+
"step": 20
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 7.6521739130434785,
|
| 146 |
+
"grad_norm": 0.6599993705749512,
|
| 147 |
+
"learning_rate": 7.333333333333333e-06,
|
| 148 |
+
"loss": 1.0118,
|
| 149 |
+
"step": 22
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_loss": 1.0248109102249146,
|
| 154 |
+
"eval_runtime": 12.9803,
|
| 155 |
+
"eval_samples_per_second": 0.924,
|
| 156 |
+
"eval_steps_per_second": 0.924,
|
| 157 |
+
"step": 23
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 8.347826086956522,
|
| 161 |
+
"grad_norm": 0.6169376969337463,
|
| 162 |
+
"learning_rate": 8.000000000000001e-06,
|
| 163 |
+
"loss": 1.0176,
|
| 164 |
+
"step": 24
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 8.695652173913043,
|
| 168 |
+
"eval_loss": 1.0099031925201416,
|
| 169 |
+
"eval_runtime": 12.9784,
|
| 170 |
+
"eval_samples_per_second": 0.925,
|
| 171 |
+
"eval_steps_per_second": 0.925,
|
| 172 |
+
"step": 25
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 9.043478260869565,
|
| 176 |
+
"grad_norm": 0.6581985950469971,
|
| 177 |
+
"learning_rate": 8.666666666666668e-06,
|
| 178 |
+
"loss": 1.0046,
|
| 179 |
+
"step": 26
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 9.73913043478261,
|
| 183 |
+
"grad_norm": 0.5997404456138611,
|
| 184 |
+
"learning_rate": 9.333333333333334e-06,
|
| 185 |
+
"loss": 0.9728,
|
| 186 |
+
"step": 28
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 9.73913043478261,
|
| 190 |
+
"eval_loss": 0.9821717143058777,
|
| 191 |
+
"eval_runtime": 12.9796,
|
| 192 |
+
"eval_samples_per_second": 0.925,
|
| 193 |
+
"eval_steps_per_second": 0.925,
|
| 194 |
+
"step": 28
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 10.434782608695652,
|
| 198 |
+
"grad_norm": 0.5669417977333069,
|
| 199 |
+
"learning_rate": 1e-05,
|
| 200 |
+
"loss": 0.9567,
|
| 201 |
+
"step": 30
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 10.782608695652174,
|
| 205 |
+
"eval_loss": 0.9526691436767578,
|
| 206 |
+
"eval_runtime": 12.98,
|
| 207 |
+
"eval_samples_per_second": 0.924,
|
| 208 |
+
"eval_steps_per_second": 0.924,
|
| 209 |
+
"step": 31
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 11.130434782608695,
|
| 213 |
+
"grad_norm": 0.5114875435829163,
|
| 214 |
+
"learning_rate": 9.99864620589731e-06,
|
| 215 |
+
"loss": 0.9557,
|
| 216 |
+
"step": 32
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.826086956521738,
|
| 220 |
+
"grad_norm": 0.4725043773651123,
|
| 221 |
+
"learning_rate": 9.994585556692624e-06,
|
| 222 |
+
"loss": 0.9202,
|
| 223 |
+
"step": 34
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 11.826086956521738,
|
| 227 |
+
"eval_loss": 0.9259089827537537,
|
| 228 |
+
"eval_runtime": 12.9791,
|
| 229 |
+
"eval_samples_per_second": 0.925,
|
| 230 |
+
"eval_steps_per_second": 0.925,
|
| 231 |
+
"step": 34
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 12.521739130434783,
|
| 235 |
+
"grad_norm": 0.4576855003833771,
|
| 236 |
+
"learning_rate": 9.987820251299121e-06,
|
| 237 |
+
"loss": 0.9099,
|
| 238 |
+
"step": 36
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 12.869565217391305,
|
| 242 |
+
"eval_loss": 0.9014627933502197,
|
| 243 |
+
"eval_runtime": 12.9828,
|
| 244 |
+
"eval_samples_per_second": 0.924,
|
| 245 |
+
"eval_steps_per_second": 0.924,
|
| 246 |
+
"step": 37
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 13.217391304347826,
|
| 250 |
+
"grad_norm": 0.3902890384197235,
|
| 251 |
+
"learning_rate": 9.978353953249023e-06,
|
| 252 |
+
"loss": 0.87,
|
| 253 |
+
"step": 38
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 13.91304347826087,
|
| 257 |
+
"grad_norm": 0.3489598333835602,
|
| 258 |
+
"learning_rate": 9.966191788709716e-06,
|
| 259 |
+
"loss": 0.8806,
|
| 260 |
+
"step": 40
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 13.91304347826087,
|
| 264 |
+
"eval_loss": 0.8827962279319763,
|
| 265 |
+
"eval_runtime": 12.9816,
|
| 266 |
+
"eval_samples_per_second": 0.924,
|
| 267 |
+
"eval_steps_per_second": 0.924,
|
| 268 |
+
"step": 40
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 14.608695652173914,
|
| 272 |
+
"grad_norm": 0.32044491171836853,
|
| 273 |
+
"learning_rate": 9.951340343707852e-06,
|
| 274 |
+
"loss": 0.7975,
|
| 275 |
+
"step": 42
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 14.956521739130435,
|
| 279 |
+
"eval_loss": 0.8661110997200012,
|
| 280 |
+
"eval_runtime": 12.9821,
|
| 281 |
+
"eval_samples_per_second": 0.924,
|
| 282 |
+
"eval_steps_per_second": 0.924,
|
| 283 |
+
"step": 43
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 15.304347826086957,
|
| 287 |
+
"grad_norm": 0.2890640199184418,
|
| 288 |
+
"learning_rate": 9.933807660562898e-06,
|
| 289 |
+
"loss": 0.8663,
|
| 290 |
+
"step": 44
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 16.0,
|
| 294 |
+
"grad_norm": 0.26249009370803833,
|
| 295 |
+
"learning_rate": 9.913603233532067e-06,
|
| 296 |
+
"loss": 0.8572,
|
| 297 |
+
"step": 46
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 16.0,
|
| 301 |
+
"eval_loss": 0.8533071875572205,
|
| 302 |
+
"eval_runtime": 12.9792,
|
| 303 |
+
"eval_samples_per_second": 0.925,
|
| 304 |
+
"eval_steps_per_second": 0.925,
|
| 305 |
+
"step": 46
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 16.695652173913043,
|
| 309 |
+
"grad_norm": 0.3019982874393463,
|
| 310 |
+
"learning_rate": 9.890738003669029e-06,
|
| 311 |
+
"loss": 0.8342,
|
| 312 |
+
"step": 48
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 16.695652173913043,
|
| 316 |
+
"eval_loss": 0.8447268009185791,
|
| 317 |
+
"eval_runtime": 12.9818,
|
| 318 |
+
"eval_samples_per_second": 0.924,
|
| 319 |
+
"eval_steps_per_second": 0.924,
|
| 320 |
+
"step": 48
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 17.391304347826086,
|
| 324 |
+
"grad_norm": 0.3173466920852661,
|
| 325 |
+
"learning_rate": 9.86522435289912e-06,
|
| 326 |
+
"loss": 0.8242,
|
| 327 |
+
"step": 50
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 17.73913043478261,
|
| 331 |
+
"eval_loss": 0.8330853581428528,
|
| 332 |
+
"eval_runtime": 12.9877,
|
| 333 |
+
"eval_samples_per_second": 0.924,
|
| 334 |
+
"eval_steps_per_second": 0.924,
|
| 335 |
+
"step": 51
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 18.08695652173913,
|
| 339 |
+
"grad_norm": 0.2738870084285736,
|
| 340 |
+
"learning_rate": 9.83707609731432e-06,
|
| 341 |
+
"loss": 0.788,
|
| 342 |
+
"step": 52
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 18.782608695652176,
|
| 346 |
+
"grad_norm": 0.27857592701911926,
|
| 347 |
+
"learning_rate": 9.806308479691595e-06,
|
| 348 |
+
"loss": 0.7954,
|
| 349 |
+
"step": 54
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 18.782608695652176,
|
| 353 |
+
"eval_loss": 0.8223147988319397,
|
| 354 |
+
"eval_runtime": 12.9802,
|
| 355 |
+
"eval_samples_per_second": 0.924,
|
| 356 |
+
"eval_steps_per_second": 0.924,
|
| 357 |
+
"step": 54
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 19.47826086956522,
|
| 361 |
+
"grad_norm": 0.2908647656440735,
|
| 362 |
+
"learning_rate": 9.77293816123866e-06,
|
| 363 |
+
"loss": 0.8235,
|
| 364 |
+
"step": 56
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 19.82608695652174,
|
| 368 |
+
"eval_loss": 0.8121759295463562,
|
| 369 |
+
"eval_runtime": 12.98,
|
| 370 |
+
"eval_samples_per_second": 0.925,
|
| 371 |
+
"eval_steps_per_second": 0.925,
|
| 372 |
+
"step": 57
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 20.17391304347826,
|
| 376 |
+
"grad_norm": 0.26751863956451416,
|
| 377 |
+
"learning_rate": 9.736983212571646e-06,
|
| 378 |
+
"loss": 0.7656,
|
| 379 |
+
"step": 58
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 20.869565217391305,
|
| 383 |
+
"grad_norm": 0.25762423872947693,
|
| 384 |
+
"learning_rate": 9.698463103929542e-06,
|
| 385 |
+
"loss": 0.7896,
|
| 386 |
+
"step": 60
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 20.869565217391305,
|
| 390 |
+
"eval_loss": 0.8017132878303528,
|
| 391 |
+
"eval_runtime": 12.9778,
|
| 392 |
+
"eval_samples_per_second": 0.925,
|
| 393 |
+
"eval_steps_per_second": 0.925,
|
| 394 |
+
"step": 60
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 21.565217391304348,
|
| 398 |
+
"grad_norm": 0.2695617973804474,
|
| 399 |
+
"learning_rate": 9.657398694630713e-06,
|
| 400 |
+
"loss": 0.7775,
|
| 401 |
+
"step": 62
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 21.91304347826087,
|
| 405 |
+
"eval_loss": 0.7932851910591125,
|
| 406 |
+
"eval_runtime": 12.9771,
|
| 407 |
+
"eval_samples_per_second": 0.925,
|
| 408 |
+
"eval_steps_per_second": 0.925,
|
| 409 |
+
"step": 63
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 22.26086956521739,
|
| 413 |
+
"grad_norm": 0.2556411027908325,
|
| 414 |
+
"learning_rate": 9.613812221777212e-06,
|
| 415 |
+
"loss": 0.7745,
|
| 416 |
+
"step": 64
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 22.956521739130434,
|
| 420 |
+
"grad_norm": 0.23346319794654846,
|
| 421 |
+
"learning_rate": 9.567727288213005e-06,
|
| 422 |
+
"loss": 0.7315,
|
| 423 |
+
"step": 66
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 22.956521739130434,
|
| 427 |
+
"eval_loss": 0.7861952185630798,
|
| 428 |
+
"eval_runtime": 12.9804,
|
| 429 |
+
"eval_samples_per_second": 0.924,
|
| 430 |
+
"eval_steps_per_second": 0.924,
|
| 431 |
+
"step": 66
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 23.652173913043477,
|
| 435 |
+
"grad_norm": 0.22954562306404114,
|
| 436 |
+
"learning_rate": 9.519168849742603e-06,
|
| 437 |
+
"loss": 0.7702,
|
| 438 |
+
"step": 68
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 24.0,
|
| 442 |
+
"eval_loss": 0.7799764275550842,
|
| 443 |
+
"eval_runtime": 12.9807,
|
| 444 |
+
"eval_samples_per_second": 0.924,
|
| 445 |
+
"eval_steps_per_second": 0.924,
|
| 446 |
+
"step": 69
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 24.347826086956523,
|
| 450 |
+
"grad_norm": 0.21833382546901703,
|
| 451 |
+
"learning_rate": 9.468163201617063e-06,
|
| 452 |
+
"loss": 0.7262,
|
| 453 |
+
"step": 70
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 24.695652173913043,
|
| 457 |
+
"eval_loss": 0.7756370902061462,
|
| 458 |
+
"eval_runtime": 12.9905,
|
| 459 |
+
"eval_samples_per_second": 0.924,
|
| 460 |
+
"eval_steps_per_second": 0.924,
|
| 461 |
+
"step": 71
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 25.043478260869566,
|
| 465 |
+
"grad_norm": 0.23636947572231293,
|
| 466 |
+
"learning_rate": 9.414737964294636e-06,
|
| 467 |
+
"loss": 0.749,
|
| 468 |
+
"step": 72
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 25.73913043478261,
|
| 472 |
+
"grad_norm": 0.21684788167476654,
|
| 473 |
+
"learning_rate": 9.358922068483813e-06,
|
| 474 |
+
"loss": 0.7683,
|
| 475 |
+
"step": 74
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 25.73913043478261,
|
| 479 |
+
"eval_loss": 0.7715494632720947,
|
| 480 |
+
"eval_runtime": 12.9818,
|
| 481 |
+
"eval_samples_per_second": 0.924,
|
| 482 |
+
"eval_steps_per_second": 0.924,
|
| 483 |
+
"step": 74
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 26.434782608695652,
|
| 487 |
+
"grad_norm": 0.2162179797887802,
|
| 488 |
+
"learning_rate": 9.30074573947683e-06,
|
| 489 |
+
"loss": 0.7043,
|
| 490 |
+
"step": 76
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 26.782608695652176,
|
| 494 |
+
"eval_loss": 0.7655512690544128,
|
| 495 |
+
"eval_runtime": 12.9823,
|
| 496 |
+
"eval_samples_per_second": 0.924,
|
| 497 |
+
"eval_steps_per_second": 0.924,
|
| 498 |
+
"step": 77
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 27.130434782608695,
|
| 502 |
+
"grad_norm": 0.2316512167453766,
|
| 503 |
+
"learning_rate": 9.24024048078213e-06,
|
| 504 |
+
"loss": 0.7234,
|
| 505 |
+
"step": 78
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 27.82608695652174,
|
| 509 |
+
"grad_norm": 0.21031486988067627,
|
| 510 |
+
"learning_rate": 9.177439057064684e-06,
|
| 511 |
+
"loss": 0.7314,
|
| 512 |
+
"step": 80
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 27.82608695652174,
|
| 516 |
+
"eval_loss": 0.7621185779571533,
|
| 517 |
+
"eval_runtime": 12.9789,
|
| 518 |
+
"eval_samples_per_second": 0.925,
|
| 519 |
+
"eval_steps_per_second": 0.925,
|
| 520 |
+
"step": 80
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 28.52173913043478,
|
| 524 |
+
"grad_norm": 0.20802505314350128,
|
| 525 |
+
"learning_rate": 9.112375476403313e-06,
|
| 526 |
+
"loss": 0.7093,
|
| 527 |
+
"step": 82
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 28.869565217391305,
|
| 531 |
+
"eval_loss": 0.7585732936859131,
|
| 532 |
+
"eval_runtime": 12.9843,
|
| 533 |
+
"eval_samples_per_second": 0.924,
|
| 534 |
+
"eval_steps_per_second": 0.924,
|
| 535 |
+
"step": 83
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 29.217391304347824,
|
| 539 |
+
"grad_norm": 0.20854762196540833,
|
| 540 |
+
"learning_rate": 9.045084971874738e-06,
|
| 541 |
+
"loss": 0.7138,
|
| 542 |
+
"step": 84
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 29.91304347826087,
|
| 546 |
+
"grad_norm": 0.21915678679943085,
|
| 547 |
+
"learning_rate": 8.97560398247424e-06,
|
| 548 |
+
"loss": 0.7047,
|
| 549 |
+
"step": 86
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 29.91304347826087,
|
| 553 |
+
"eval_loss": 0.7542468905448914,
|
| 554 |
+
"eval_runtime": 12.9809,
|
| 555 |
+
"eval_samples_per_second": 0.924,
|
| 556 |
+
"eval_steps_per_second": 0.924,
|
| 557 |
+
"step": 86
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 30.608695652173914,
|
| 561 |
+
"grad_norm": 0.20012685656547546,
|
| 562 |
+
"learning_rate": 8.903970133383297e-06,
|
| 563 |
+
"loss": 0.707,
|
| 564 |
+
"step": 88
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 30.956521739130434,
|
| 568 |
+
"eval_loss": 0.7506493926048279,
|
| 569 |
+
"eval_runtime": 12.9843,
|
| 570 |
+
"eval_samples_per_second": 0.924,
|
| 571 |
+
"eval_steps_per_second": 0.924,
|
| 572 |
+
"step": 89
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 31.304347826086957,
|
| 576 |
+
"grad_norm": 0.2392660677433014,
|
| 577 |
+
"learning_rate": 8.83022221559489e-06,
|
| 578 |
+
"loss": 0.6921,
|
| 579 |
+
"step": 90
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 32.0,
|
| 583 |
+
"grad_norm": 0.20580413937568665,
|
| 584 |
+
"learning_rate": 8.754400164907496e-06,
|
| 585 |
+
"loss": 0.7128,
|
| 586 |
+
"step": 92
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 32.0,
|
| 590 |
+
"eval_loss": 0.7475277781486511,
|
| 591 |
+
"eval_runtime": 12.9807,
|
| 592 |
+
"eval_samples_per_second": 0.924,
|
| 593 |
+
"eval_steps_per_second": 0.924,
|
| 594 |
+
"step": 92
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 32.69565217391305,
|
| 598 |
+
"grad_norm": 0.21809720993041992,
|
| 599 |
+
"learning_rate": 8.676545040299145e-06,
|
| 600 |
+
"loss": 0.676,
|
| 601 |
+
"step": 94
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 32.69565217391305,
|
| 605 |
+
"eval_loss": 0.7451496124267578,
|
| 606 |
+
"eval_runtime": 12.9817,
|
| 607 |
+
"eval_samples_per_second": 0.924,
|
| 608 |
+
"eval_steps_per_second": 0.924,
|
| 609 |
+
"step": 94
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 33.391304347826086,
|
| 613 |
+
"grad_norm": 0.22367319464683533,
|
| 614 |
+
"learning_rate": 8.596699001693257e-06,
|
| 615 |
+
"loss": 0.7113,
|
| 616 |
+
"step": 96
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 33.73913043478261,
|
| 620 |
+
"eval_loss": 0.741963803768158,
|
| 621 |
+
"eval_runtime": 12.988,
|
| 622 |
+
"eval_samples_per_second": 0.924,
|
| 623 |
+
"eval_steps_per_second": 0.924,
|
| 624 |
+
"step": 97
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 34.08695652173913,
|
| 628 |
+
"grad_norm": 0.22299408912658691,
|
| 629 |
+
"learning_rate": 8.51490528712831e-06,
|
| 630 |
+
"loss": 0.68,
|
| 631 |
+
"step": 98
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 34.78260869565217,
|
| 635 |
+
"grad_norm": 0.23509928584098816,
|
| 636 |
+
"learning_rate": 8.43120818934367e-06,
|
| 637 |
+
"loss": 0.6733,
|
| 638 |
+
"step": 100
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 34.78260869565217,
|
| 642 |
+
"eval_loss": 0.7395928502082825,
|
| 643 |
+
"eval_runtime": 12.9789,
|
| 644 |
+
"eval_samples_per_second": 0.925,
|
| 645 |
+
"eval_steps_per_second": 0.925,
|
| 646 |
+
"step": 100
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 35.47826086956522,
|
| 650 |
+
"grad_norm": 0.22088173031806946,
|
| 651 |
+
"learning_rate": 8.345653031794292e-06,
|
| 652 |
+
"loss": 0.698,
|
| 653 |
+
"step": 102
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 35.82608695652174,
|
| 657 |
+
"eval_loss": 0.7369885444641113,
|
| 658 |
+
"eval_runtime": 12.9801,
|
| 659 |
+
"eval_samples_per_second": 0.924,
|
| 660 |
+
"eval_steps_per_second": 0.924,
|
| 661 |
+
"step": 103
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 36.17391304347826,
|
| 665 |
+
"grad_norm": 0.2378576695919037,
|
| 666 |
+
"learning_rate": 8.258286144107277e-06,
|
| 667 |
+
"loss": 0.6446,
|
| 668 |
+
"step": 104
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 36.869565217391305,
|
| 672 |
+
"grad_norm": 0.22731085121631622,
|
| 673 |
+
"learning_rate": 8.16915483699355e-06,
|
| 674 |
+
"loss": 0.6868,
|
| 675 |
+
"step": 106
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 36.869565217391305,
|
| 679 |
+
"eval_loss": 0.7338590621948242,
|
| 680 |
+
"eval_runtime": 12.9803,
|
| 681 |
+
"eval_samples_per_second": 0.924,
|
| 682 |
+
"eval_steps_per_second": 0.924,
|
| 683 |
+
"step": 106
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 37.56521739130435,
|
| 687 |
+
"grad_norm": 0.21938204765319824,
|
| 688 |
+
"learning_rate": 8.078307376628292e-06,
|
| 689 |
+
"loss": 0.6633,
|
| 690 |
+
"step": 108
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 37.91304347826087,
|
| 694 |
+
"eval_loss": 0.7310268878936768,
|
| 695 |
+
"eval_runtime": 12.9795,
|
| 696 |
+
"eval_samples_per_second": 0.925,
|
| 697 |
+
"eval_steps_per_second": 0.925,
|
| 698 |
+
"step": 109
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 38.26086956521739,
|
| 702 |
+
"grad_norm": 0.21967856585979462,
|
| 703 |
+
"learning_rate": 7.985792958513932e-06,
|
| 704 |
+
"loss": 0.6498,
|
| 705 |
+
"step": 110
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 38.95652173913044,
|
| 709 |
+
"grad_norm": 0.22135666012763977,
|
| 710 |
+
"learning_rate": 7.891661680839932e-06,
|
| 711 |
+
"loss": 0.675,
|
| 712 |
+
"step": 112
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 38.95652173913044,
|
| 716 |
+
"eval_loss": 0.7296469211578369,
|
| 717 |
+
"eval_runtime": 12.9811,
|
| 718 |
+
"eval_samples_per_second": 0.924,
|
| 719 |
+
"eval_steps_per_second": 0.924,
|
| 720 |
+
"step": 112
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 39.65217391304348,
|
| 724 |
+
"grad_norm": 0.2276638001203537,
|
| 725 |
+
"learning_rate": 7.795964517353734e-06,
|
| 726 |
+
"loss": 0.6563,
|
| 727 |
+
"step": 114
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 40.0,
|
| 731 |
+
"eval_loss": 0.7270292639732361,
|
| 732 |
+
"eval_runtime": 12.9804,
|
| 733 |
+
"eval_samples_per_second": 0.924,
|
| 734 |
+
"eval_steps_per_second": 0.924,
|
| 735 |
+
"step": 115
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 40.34782608695652,
|
| 739 |
+
"grad_norm": 0.23463626205921173,
|
| 740 |
+
"learning_rate": 7.698753289757565e-06,
|
| 741 |
+
"loss": 0.64,
|
| 742 |
+
"step": 116
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 40.69565217391305,
|
| 746 |
+
"eval_loss": 0.725705087184906,
|
| 747 |
+
"eval_runtime": 12.9813,
|
| 748 |
+
"eval_samples_per_second": 0.924,
|
| 749 |
+
"eval_steps_per_second": 0.924,
|
| 750 |
+
"step": 117
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 41.04347826086956,
|
| 754 |
+
"grad_norm": 0.22769178450107574,
|
| 755 |
+
"learning_rate": 7.600080639646077e-06,
|
| 756 |
+
"loss": 0.657,
|
| 757 |
+
"step": 118
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 41.73913043478261,
|
| 761 |
+
"grad_norm": 0.22011993825435638,
|
| 762 |
+
"learning_rate": 7.500000000000001e-06,
|
| 763 |
+
"loss": 0.6314,
|
| 764 |
+
"step": 120
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 41.73913043478261,
|
| 768 |
+
"eval_loss": 0.7242138981819153,
|
| 769 |
+
"eval_runtime": 12.9801,
|
| 770 |
+
"eval_samples_per_second": 0.924,
|
| 771 |
+
"eval_steps_per_second": 0.924,
|
| 772 |
+
"step": 120
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 42.43478260869565,
|
| 776 |
+
"grad_norm": 0.2390049695968628,
|
| 777 |
+
"learning_rate": 7.398565566251232e-06,
|
| 778 |
+
"loss": 0.619,
|
| 779 |
+
"step": 122
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 42.78260869565217,
|
| 783 |
+
"eval_loss": 0.7225276827812195,
|
| 784 |
+
"eval_runtime": 12.9807,
|
| 785 |
+
"eval_samples_per_second": 0.924,
|
| 786 |
+
"eval_steps_per_second": 0.924,
|
| 787 |
+
"step": 123
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 43.130434782608695,
|
| 791 |
+
"grad_norm": 0.2800259292125702,
|
| 792 |
+
"learning_rate": 7.295832266935059e-06,
|
| 793 |
+
"loss": 0.6532,
|
| 794 |
+
"step": 124
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 43.82608695652174,
|
| 798 |
+
"grad_norm": 0.22223666310310364,
|
| 799 |
+
"learning_rate": 7.191855733945388e-06,
|
| 800 |
+
"loss": 0.6256,
|
| 801 |
+
"step": 126
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 43.82608695652174,
|
| 805 |
+
"eval_loss": 0.7211093902587891,
|
| 806 |
+
"eval_runtime": 12.9815,
|
| 807 |
+
"eval_samples_per_second": 0.924,
|
| 808 |
+
"eval_steps_per_second": 0.924,
|
| 809 |
+
"step": 126
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 44.52173913043478,
|
| 813 |
+
"grad_norm": 0.2679072320461273,
|
| 814 |
+
"learning_rate": 7.08669227240909e-06,
|
| 815 |
+
"loss": 0.634,
|
| 816 |
+
"step": 128
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 44.869565217391305,
|
| 820 |
+
"eval_loss": 0.7197514176368713,
|
| 821 |
+
"eval_runtime": 12.9829,
|
| 822 |
+
"eval_samples_per_second": 0.924,
|
| 823 |
+
"eval_steps_per_second": 0.924,
|
| 824 |
+
"step": 129
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 45.21739130434783,
|
| 828 |
+
"grad_norm": 0.2466752678155899,
|
| 829 |
+
"learning_rate": 6.980398830195785e-06,
|
| 830 |
+
"loss": 0.6245,
|
| 831 |
+
"step": 130
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 45.91304347826087,
|
| 835 |
+
"grad_norm": 0.2207140475511551,
|
| 836 |
+
"learning_rate": 6.873032967079562e-06,
|
| 837 |
+
"loss": 0.5984,
|
| 838 |
+
"step": 132
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 45.91304347826087,
|
| 842 |
+
"eval_loss": 0.7184772491455078,
|
| 843 |
+
"eval_runtime": 12.9845,
|
| 844 |
+
"eval_samples_per_second": 0.924,
|
| 845 |
+
"eval_steps_per_second": 0.924,
|
| 846 |
+
"step": 132
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 46.608695652173914,
|
| 850 |
+
"grad_norm": 0.24495841562747955,
|
| 851 |
+
"learning_rate": 6.7646528235693445e-06,
|
| 852 |
+
"loss": 0.636,
|
| 853 |
+
"step": 134
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 46.95652173913044,
|
| 857 |
+
"eval_loss": 0.7176054120063782,
|
| 858 |
+
"eval_runtime": 12.9825,
|
| 859 |
+
"eval_samples_per_second": 0.924,
|
| 860 |
+
"eval_steps_per_second": 0.924,
|
| 861 |
+
"step": 135
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 47.30434782608695,
|
| 865 |
+
"grad_norm": 0.24388910830020905,
|
| 866 |
+
"learning_rate": 6.655317089424791e-06,
|
| 867 |
+
"loss": 0.6088,
|
| 868 |
+
"step": 136
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 48.0,
|
| 872 |
+
"grad_norm": 0.2629048824310303,
|
| 873 |
+
"learning_rate": 6.545084971874738e-06,
|
| 874 |
+
"loss": 0.6084,
|
| 875 |
+
"step": 138
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 48.0,
|
| 879 |
+
"eval_loss": 0.7173163890838623,
|
| 880 |
+
"eval_runtime": 12.9805,
|
| 881 |
+
"eval_samples_per_second": 0.924,
|
| 882 |
+
"eval_steps_per_second": 0.924,
|
| 883 |
+
"step": 138
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 48.69565217391305,
|
| 887 |
+
"grad_norm": 0.23480680584907532,
|
| 888 |
+
"learning_rate": 6.434016163555452e-06,
|
| 889 |
+
"loss": 0.6068,
|
| 890 |
+
"step": 140
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 48.69565217391305,
|
| 894 |
+
"eval_loss": 0.716775119304657,
|
| 895 |
+
"eval_runtime": 12.9805,
|
| 896 |
+
"eval_samples_per_second": 0.924,
|
| 897 |
+
"eval_steps_per_second": 0.924,
|
| 898 |
+
"step": 140
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 49.391304347826086,
|
| 902 |
+
"grad_norm": 0.24330304563045502,
|
| 903 |
+
"learning_rate": 6.322170810186013e-06,
|
| 904 |
+
"loss": 0.5982,
|
| 905 |
+
"step": 142
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 49.73913043478261,
|
| 909 |
+
"eval_loss": 0.7166422009468079,
|
| 910 |
+
"eval_runtime": 12.9831,
|
| 911 |
+
"eval_samples_per_second": 0.924,
|
| 912 |
+
"eval_steps_per_second": 0.924,
|
| 913 |
+
"step": 143
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 50.08695652173913,
|
| 917 |
+
"grad_norm": 0.2731475234031677,
|
| 918 |
+
"learning_rate": 6.209609477998339e-06,
|
| 919 |
+
"loss": 0.5933,
|
| 920 |
+
"step": 144
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 50.78260869565217,
|
| 924 |
+
"grad_norm": 0.28438258171081543,
|
| 925 |
+
"learning_rate": 6.0963931209395165e-06,
|
| 926 |
+
"loss": 0.6024,
|
| 927 |
+
"step": 146
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 50.78260869565217,
|
| 931 |
+
"eval_loss": 0.7170538306236267,
|
| 932 |
+
"eval_runtime": 12.9821,
|
| 933 |
+
"eval_samples_per_second": 0.924,
|
| 934 |
+
"eval_steps_per_second": 0.924,
|
| 935 |
+
"step": 146
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 51.47826086956522,
|
| 939 |
+
"grad_norm": 0.26069560647010803,
|
| 940 |
+
"learning_rate": 5.982583047664151e-06,
|
| 941 |
+
"loss": 0.5876,
|
| 942 |
+
"step": 148
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 51.82608695652174,
|
| 946 |
+
"eval_loss": 0.7170079350471497,
|
| 947 |
+
"eval_runtime": 12.9793,
|
| 948 |
+
"eval_samples_per_second": 0.925,
|
| 949 |
+
"eval_steps_per_second": 0.925,
|
| 950 |
+
"step": 149
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 52.17391304347826,
|
| 954 |
+
"grad_norm": 0.30849406123161316,
|
| 955 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 956 |
+
"loss": 0.5845,
|
| 957 |
+
"step": 150
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 52.869565217391305,
|
| 961 |
+
"grad_norm": 0.2836209833621979,
|
| 962 |
+
"learning_rate": 5.753428561247416e-06,
|
| 963 |
+
"loss": 0.5852,
|
| 964 |
+
"step": 152
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 52.869565217391305,
|
| 968 |
+
"eval_loss": 0.7168818116188049,
|
| 969 |
+
"eval_runtime": 12.9839,
|
| 970 |
+
"eval_samples_per_second": 0.924,
|
| 971 |
+
"eval_steps_per_second": 0.924,
|
| 972 |
+
"step": 152
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 53.56521739130435,
|
| 976 |
+
"grad_norm": 0.2691332995891571,
|
| 977 |
+
"learning_rate": 5.638208239302975e-06,
|
| 978 |
+
"loss": 0.5803,
|
| 979 |
+
"step": 154
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 53.91304347826087,
|
| 983 |
+
"eval_loss": 0.7174960970878601,
|
| 984 |
+
"eval_runtime": 12.9787,
|
| 985 |
+
"eval_samples_per_second": 0.925,
|
| 986 |
+
"eval_steps_per_second": 0.925,
|
| 987 |
+
"step": 155
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 54.26086956521739,
|
| 991 |
+
"grad_norm": 0.2947712242603302,
|
| 992 |
+
"learning_rate": 5.522642316338268e-06,
|
| 993 |
+
"loss": 0.5606,
|
| 994 |
+
"step": 156
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 54.95652173913044,
|
| 998 |
+
"grad_norm": 0.28288403153419495,
|
| 999 |
+
"learning_rate": 5.406793373339292e-06,
|
| 1000 |
+
"loss": 0.5794,
|
| 1001 |
+
"step": 158
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 54.95652173913044,
|
| 1005 |
+
"eval_loss": 0.717235803604126,
|
| 1006 |
+
"eval_runtime": 12.9824,
|
| 1007 |
+
"eval_samples_per_second": 0.924,
|
| 1008 |
+
"eval_steps_per_second": 0.924,
|
| 1009 |
+
"step": 158
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 55.65217391304348,
|
| 1013 |
+
"grad_norm": 0.2836114168167114,
|
| 1014 |
+
"learning_rate": 5.290724144552379e-06,
|
| 1015 |
+
"loss": 0.5699,
|
| 1016 |
+
"step": 160
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 56.0,
|
| 1020 |
+
"eval_loss": 0.7187849879264832,
|
| 1021 |
+
"eval_runtime": 12.9808,
|
| 1022 |
+
"eval_samples_per_second": 0.924,
|
| 1023 |
+
"eval_steps_per_second": 0.924,
|
| 1024 |
+
"step": 161
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 56.34782608695652,
|
| 1028 |
+
"grad_norm": 0.30464258790016174,
|
| 1029 |
+
"learning_rate": 5.174497483512506e-06,
|
| 1030 |
+
"loss": 0.5722,
|
| 1031 |
+
"step": 162
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 56.69565217391305,
|
| 1035 |
+
"eval_loss": 0.719237744808197,
|
| 1036 |
+
"eval_runtime": 12.9776,
|
| 1037 |
+
"eval_samples_per_second": 0.925,
|
| 1038 |
+
"eval_steps_per_second": 0.925,
|
| 1039 |
+
"step": 163
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 56.69565217391305,
|
| 1043 |
+
"step": 163,
|
| 1044 |
+
"total_flos": 2.5340798505582592e+17,
|
| 1045 |
+
"train_loss": 0.767207163243206,
|
| 1046 |
+
"train_runtime": 9109.3845,
|
| 1047 |
+
"train_samples_per_second": 0.757,
|
| 1048 |
+
"train_steps_per_second": 0.033
|
| 1049 |
+
}
|
| 1050 |
+
],
|
| 1051 |
+
"logging_steps": 2,
|
| 1052 |
+
"max_steps": 300,
|
| 1053 |
+
"num_input_tokens_seen": 0,
|
| 1054 |
+
"num_train_epochs": 150,
|
| 1055 |
+
"save_steps": 25,
|
| 1056 |
+
"stateful_callbacks": {
|
| 1057 |
+
"EarlyStoppingCallback": {
|
| 1058 |
+
"args": {
|
| 1059 |
+
"early_stopping_patience": 7,
|
| 1060 |
+
"early_stopping_threshold": 0.0
|
| 1061 |
+
},
|
| 1062 |
+
"attributes": {
|
| 1063 |
+
"early_stopping_patience_counter": 0
|
| 1064 |
+
}
|
| 1065 |
+
},
|
| 1066 |
+
"TrainerControl": {
|
| 1067 |
+
"args": {
|
| 1068 |
+
"should_epoch_stop": false,
|
| 1069 |
+
"should_evaluate": false,
|
| 1070 |
+
"should_log": false,
|
| 1071 |
+
"should_save": true,
|
| 1072 |
+
"should_training_stop": true
|
| 1073 |
+
},
|
| 1074 |
+
"attributes": {}
|
| 1075 |
+
}
|
| 1076 |
+
},
|
| 1077 |
+
"total_flos": 2.5340798505582592e+17,
|
| 1078 |
+
"train_batch_size": 1,
|
| 1079 |
+
"trial_name": null,
|
| 1080 |
+
"trial_params": null
|
| 1081 |
+
}
|