Commit
•
c41972f
1
Parent(s):
656b701
Model save
Browse files- README.md +112 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +925 -0
README.md
ADDED
|
@@ -0,0 +1,112 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-3_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-3_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: 0.4797
|
| 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 |
+
| 2.4485 | 0.6957 | 2 | 2.4786 |
|
| 57 |
+
| 2.4413 | 1.7391 | 5 | 2.4667 |
|
| 58 |
+
| 2.6263 | 2.7826 | 8 | 2.4443 |
|
| 59 |
+
| 2.1438 | 3.8261 | 11 | 2.4112 |
|
| 60 |
+
| 2.3995 | 4.8696 | 14 | 2.3654 |
|
| 61 |
+
| 2.2475 | 5.9130 | 17 | 2.3021 |
|
| 62 |
+
| 2.2194 | 6.9565 | 20 | 2.2092 |
|
| 63 |
+
| 2.2976 | 8.0 | 23 | 2.0988 |
|
| 64 |
+
| 2.0386 | 8.6957 | 25 | 2.0090 |
|
| 65 |
+
| 1.8757 | 9.7391 | 28 | 1.8478 |
|
| 66 |
+
| 1.753 | 10.7826 | 31 | 1.6617 |
|
| 67 |
+
| 1.5394 | 11.8261 | 34 | 1.4736 |
|
| 68 |
+
| 1.4055 | 12.8696 | 37 | 1.2968 |
|
| 69 |
+
| 1.1544 | 13.9130 | 40 | 1.1374 |
|
| 70 |
+
| 1.0965 | 14.9565 | 43 | 0.9952 |
|
| 71 |
+
| 0.8824 | 16.0 | 46 | 0.8632 |
|
| 72 |
+
| 0.8412 | 16.6957 | 48 | 0.7849 |
|
| 73 |
+
| 0.7232 | 17.7391 | 51 | 0.7002 |
|
| 74 |
+
| 0.6275 | 18.7826 | 54 | 0.6459 |
|
| 75 |
+
| 0.6078 | 19.8261 | 57 | 0.6102 |
|
| 76 |
+
| 0.5477 | 20.8696 | 60 | 0.5828 |
|
| 77 |
+
| 0.4369 | 21.9130 | 63 | 0.5587 |
|
| 78 |
+
| 0.5025 | 22.9565 | 66 | 0.5396 |
|
| 79 |
+
| 0.5043 | 24.0 | 69 | 0.5226 |
|
| 80 |
+
| 0.3742 | 24.6957 | 71 | 0.5101 |
|
| 81 |
+
| 0.449 | 25.7391 | 74 | 0.5003 |
|
| 82 |
+
| 0.3276 | 26.7826 | 77 | 0.4925 |
|
| 83 |
+
| 0.4754 | 27.8261 | 80 | 0.4932 |
|
| 84 |
+
| 0.3724 | 28.8696 | 83 | 0.4876 |
|
| 85 |
+
| 0.4679 | 29.9130 | 86 | 0.4861 |
|
| 86 |
+
| 0.3245 | 30.9565 | 89 | 0.4884 |
|
| 87 |
+
| 0.3613 | 32.0 | 92 | 0.4922 |
|
| 88 |
+
| 0.3511 | 32.6957 | 94 | 0.4899 |
|
| 89 |
+
| 0.5275 | 33.7391 | 97 | 0.4931 |
|
| 90 |
+
| 0.3403 | 34.7826 | 100 | 0.4883 |
|
| 91 |
+
| 0.4209 | 35.8261 | 103 | 0.4815 |
|
| 92 |
+
| 0.3543 | 36.8696 | 106 | 0.4805 |
|
| 93 |
+
| 0.4115 | 37.9130 | 109 | 0.4767 |
|
| 94 |
+
| 0.3902 | 38.9565 | 112 | 0.4794 |
|
| 95 |
+
| 0.3735 | 40.0 | 115 | 0.4776 |
|
| 96 |
+
| 0.3227 | 40.6957 | 117 | 0.4733 |
|
| 97 |
+
| 0.2983 | 41.7391 | 120 | 0.4797 |
|
| 98 |
+
| 0.4421 | 42.7826 | 123 | 0.4791 |
|
| 99 |
+
| 0.3819 | 43.8261 | 126 | 0.4739 |
|
| 100 |
+
| 0.2965 | 44.8696 | 129 | 0.4764 |
|
| 101 |
+
| 0.2661 | 45.9130 | 132 | 0.4765 |
|
| 102 |
+
| 0.3827 | 46.9565 | 135 | 0.4778 |
|
| 103 |
+
| 0.3144 | 48.0 | 138 | 0.4797 |
|
| 104 |
+
|
| 105 |
+
|
| 106 |
+
### Framework versions
|
| 107 |
+
|
| 108 |
+
- PEFT 0.12.0
|
| 109 |
+
- Transformers 4.44.0
|
| 110 |
+
- Pytorch 2.1.2+cu121
|
| 111 |
+
- Datasets 2.20.0
|
| 112 |
+
- 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 sha256:65071161616e650f66649eefca1069cd7568cd52945198f4de171346f78a4bf6
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 48.0,
|
| 3 |
+
"total_flos": 1.749470205265838e+17,
|
| 4 |
+
"train_loss": 0.9229606502297996,
|
| 5 |
+
"train_runtime": 6469.2828,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 1.067,
|
| 8 |
+
"train_steps_per_second": 0.046
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 48.0,
|
| 3 |
+
"total_flos": 1.749470205265838e+17,
|
| 4 |
+
"train_loss": 0.9229606502297996,
|
| 5 |
+
"train_runtime": 6469.2828,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 1.067,
|
| 8 |
+
"train_steps_per_second": 0.046
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,925 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.47327545285224915,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-3_60-samples_config-4/checkpoint-117",
|
| 4 |
+
"epoch": 48.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 138,
|
| 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": 2.713942527770996,
|
| 14 |
+
"learning_rate": 3.3333333333333335e-07,
|
| 15 |
+
"loss": 2.4937,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.6956521739130435,
|
| 20 |
+
"grad_norm": 2.5404553413391113,
|
| 21 |
+
"learning_rate": 6.666666666666667e-07,
|
| 22 |
+
"loss": 2.4485,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6956521739130435,
|
| 27 |
+
"eval_loss": 2.47861909866333,
|
| 28 |
+
"eval_runtime": 11.1868,
|
| 29 |
+
"eval_samples_per_second": 1.073,
|
| 30 |
+
"eval_steps_per_second": 1.073,
|
| 31 |
+
"step": 2
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 1.391304347826087,
|
| 35 |
+
"grad_norm": 2.537482976913452,
|
| 36 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 37 |
+
"loss": 2.4413,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.7391304347826086,
|
| 42 |
+
"eval_loss": 2.4666788578033447,
|
| 43 |
+
"eval_runtime": 11.1876,
|
| 44 |
+
"eval_samples_per_second": 1.073,
|
| 45 |
+
"eval_steps_per_second": 1.073,
|
| 46 |
+
"step": 5
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 2.0869565217391304,
|
| 50 |
+
"grad_norm": 2.515000820159912,
|
| 51 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 52 |
+
"loss": 2.4642,
|
| 53 |
+
"step": 6
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 2.782608695652174,
|
| 57 |
+
"grad_norm": 2.7089920043945312,
|
| 58 |
+
"learning_rate": 2.666666666666667e-06,
|
| 59 |
+
"loss": 2.6263,
|
| 60 |
+
"step": 8
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 2.782608695652174,
|
| 64 |
+
"eval_loss": 2.444336175918579,
|
| 65 |
+
"eval_runtime": 11.1858,
|
| 66 |
+
"eval_samples_per_second": 1.073,
|
| 67 |
+
"eval_steps_per_second": 1.073,
|
| 68 |
+
"step": 8
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 3.4782608695652173,
|
| 72 |
+
"grad_norm": 2.3491318225860596,
|
| 73 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 74 |
+
"loss": 2.1438,
|
| 75 |
+
"step": 10
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 3.8260869565217392,
|
| 79 |
+
"eval_loss": 2.41117262840271,
|
| 80 |
+
"eval_runtime": 11.1873,
|
| 81 |
+
"eval_samples_per_second": 1.073,
|
| 82 |
+
"eval_steps_per_second": 1.073,
|
| 83 |
+
"step": 11
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 4.173913043478261,
|
| 87 |
+
"grad_norm": 2.7485859394073486,
|
| 88 |
+
"learning_rate": 4.000000000000001e-06,
|
| 89 |
+
"loss": 2.5153,
|
| 90 |
+
"step": 12
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 4.869565217391305,
|
| 94 |
+
"grad_norm": 2.9895129203796387,
|
| 95 |
+
"learning_rate": 4.666666666666667e-06,
|
| 96 |
+
"loss": 2.3995,
|
| 97 |
+
"step": 14
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 4.869565217391305,
|
| 101 |
+
"eval_loss": 2.3653676509857178,
|
| 102 |
+
"eval_runtime": 11.1932,
|
| 103 |
+
"eval_samples_per_second": 1.072,
|
| 104 |
+
"eval_steps_per_second": 1.072,
|
| 105 |
+
"step": 14
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 5.565217391304348,
|
| 109 |
+
"grad_norm": 2.5411155223846436,
|
| 110 |
+
"learning_rate": 5.333333333333334e-06,
|
| 111 |
+
"loss": 2.2475,
|
| 112 |
+
"step": 16
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 5.913043478260869,
|
| 116 |
+
"eval_loss": 2.3020589351654053,
|
| 117 |
+
"eval_runtime": 11.1867,
|
| 118 |
+
"eval_samples_per_second": 1.073,
|
| 119 |
+
"eval_steps_per_second": 1.073,
|
| 120 |
+
"step": 17
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 6.260869565217392,
|
| 124 |
+
"grad_norm": 2.7964119911193848,
|
| 125 |
+
"learning_rate": 6e-06,
|
| 126 |
+
"loss": 2.3758,
|
| 127 |
+
"step": 18
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 6.956521739130435,
|
| 131 |
+
"grad_norm": 2.7497153282165527,
|
| 132 |
+
"learning_rate": 6.666666666666667e-06,
|
| 133 |
+
"loss": 2.2194,
|
| 134 |
+
"step": 20
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 6.956521739130435,
|
| 138 |
+
"eval_loss": 2.2091970443725586,
|
| 139 |
+
"eval_runtime": 11.1867,
|
| 140 |
+
"eval_samples_per_second": 1.073,
|
| 141 |
+
"eval_steps_per_second": 1.073,
|
| 142 |
+
"step": 20
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 7.6521739130434785,
|
| 146 |
+
"grad_norm": 2.986889362335205,
|
| 147 |
+
"learning_rate": 7.333333333333333e-06,
|
| 148 |
+
"loss": 2.2976,
|
| 149 |
+
"step": 22
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 8.0,
|
| 153 |
+
"eval_loss": 2.0988080501556396,
|
| 154 |
+
"eval_runtime": 11.191,
|
| 155 |
+
"eval_samples_per_second": 1.072,
|
| 156 |
+
"eval_steps_per_second": 1.072,
|
| 157 |
+
"step": 23
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 8.347826086956522,
|
| 161 |
+
"grad_norm": 2.966017961502075,
|
| 162 |
+
"learning_rate": 8.000000000000001e-06,
|
| 163 |
+
"loss": 2.0386,
|
| 164 |
+
"step": 24
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 8.695652173913043,
|
| 168 |
+
"eval_loss": 2.0089728832244873,
|
| 169 |
+
"eval_runtime": 11.1873,
|
| 170 |
+
"eval_samples_per_second": 1.073,
|
| 171 |
+
"eval_steps_per_second": 1.073,
|
| 172 |
+
"step": 25
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 9.043478260869565,
|
| 176 |
+
"grad_norm": 2.240626335144043,
|
| 177 |
+
"learning_rate": 8.666666666666668e-06,
|
| 178 |
+
"loss": 1.9381,
|
| 179 |
+
"step": 26
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 9.73913043478261,
|
| 183 |
+
"grad_norm": 2.0199873447418213,
|
| 184 |
+
"learning_rate": 9.333333333333334e-06,
|
| 185 |
+
"loss": 1.8757,
|
| 186 |
+
"step": 28
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 9.73913043478261,
|
| 190 |
+
"eval_loss": 1.8477638959884644,
|
| 191 |
+
"eval_runtime": 11.1884,
|
| 192 |
+
"eval_samples_per_second": 1.073,
|
| 193 |
+
"eval_steps_per_second": 1.073,
|
| 194 |
+
"step": 28
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 10.434782608695652,
|
| 198 |
+
"grad_norm": 2.3196067810058594,
|
| 199 |
+
"learning_rate": 1e-05,
|
| 200 |
+
"loss": 1.753,
|
| 201 |
+
"step": 30
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 10.782608695652174,
|
| 205 |
+
"eval_loss": 1.661726951599121,
|
| 206 |
+
"eval_runtime": 11.1905,
|
| 207 |
+
"eval_samples_per_second": 1.072,
|
| 208 |
+
"eval_steps_per_second": 1.072,
|
| 209 |
+
"step": 31
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 11.130434782608695,
|
| 213 |
+
"grad_norm": 2.170588970184326,
|
| 214 |
+
"learning_rate": 9.99864620589731e-06,
|
| 215 |
+
"loss": 1.6899,
|
| 216 |
+
"step": 32
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 11.826086956521738,
|
| 220 |
+
"grad_norm": 1.8977363109588623,
|
| 221 |
+
"learning_rate": 9.994585556692624e-06,
|
| 222 |
+
"loss": 1.5394,
|
| 223 |
+
"step": 34
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 11.826086956521738,
|
| 227 |
+
"eval_loss": 1.4736323356628418,
|
| 228 |
+
"eval_runtime": 11.1874,
|
| 229 |
+
"eval_samples_per_second": 1.073,
|
| 230 |
+
"eval_steps_per_second": 1.073,
|
| 231 |
+
"step": 34
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 12.521739130434783,
|
| 235 |
+
"grad_norm": 2.0006208419799805,
|
| 236 |
+
"learning_rate": 9.987820251299121e-06,
|
| 237 |
+
"loss": 1.4055,
|
| 238 |
+
"step": 36
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 12.869565217391305,
|
| 242 |
+
"eval_loss": 1.2967798709869385,
|
| 243 |
+
"eval_runtime": 11.1868,
|
| 244 |
+
"eval_samples_per_second": 1.073,
|
| 245 |
+
"eval_steps_per_second": 1.073,
|
| 246 |
+
"step": 37
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 13.217391304347826,
|
| 250 |
+
"grad_norm": 2.0926783084869385,
|
| 251 |
+
"learning_rate": 9.978353953249023e-06,
|
| 252 |
+
"loss": 1.3167,
|
| 253 |
+
"step": 38
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 13.91304347826087,
|
| 257 |
+
"grad_norm": 2.1667168140411377,
|
| 258 |
+
"learning_rate": 9.966191788709716e-06,
|
| 259 |
+
"loss": 1.1544,
|
| 260 |
+
"step": 40
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 13.91304347826087,
|
| 264 |
+
"eval_loss": 1.1374319791793823,
|
| 265 |
+
"eval_runtime": 11.1869,
|
| 266 |
+
"eval_samples_per_second": 1.073,
|
| 267 |
+
"eval_steps_per_second": 1.073,
|
| 268 |
+
"step": 40
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 14.608695652173914,
|
| 272 |
+
"grad_norm": 1.5720164775848389,
|
| 273 |
+
"learning_rate": 9.951340343707852e-06,
|
| 274 |
+
"loss": 1.0965,
|
| 275 |
+
"step": 42
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 14.956521739130435,
|
| 279 |
+
"eval_loss": 0.9952384829521179,
|
| 280 |
+
"eval_runtime": 11.1859,
|
| 281 |
+
"eval_samples_per_second": 1.073,
|
| 282 |
+
"eval_steps_per_second": 1.073,
|
| 283 |
+
"step": 43
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 15.304347826086957,
|
| 287 |
+
"grad_norm": 1.4824587106704712,
|
| 288 |
+
"learning_rate": 9.933807660562898e-06,
|
| 289 |
+
"loss": 0.9479,
|
| 290 |
+
"step": 44
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 16.0,
|
| 294 |
+
"grad_norm": 1.6556437015533447,
|
| 295 |
+
"learning_rate": 9.913603233532067e-06,
|
| 296 |
+
"loss": 0.8824,
|
| 297 |
+
"step": 46
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 16.0,
|
| 301 |
+
"eval_loss": 0.8632068634033203,
|
| 302 |
+
"eval_runtime": 11.1862,
|
| 303 |
+
"eval_samples_per_second": 1.073,
|
| 304 |
+
"eval_steps_per_second": 1.073,
|
| 305 |
+
"step": 46
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 16.695652173913043,
|
| 309 |
+
"grad_norm": 1.2123420238494873,
|
| 310 |
+
"learning_rate": 9.890738003669029e-06,
|
| 311 |
+
"loss": 0.8412,
|
| 312 |
+
"step": 48
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 16.695652173913043,
|
| 316 |
+
"eval_loss": 0.7849404811859131,
|
| 317 |
+
"eval_runtime": 11.1943,
|
| 318 |
+
"eval_samples_per_second": 1.072,
|
| 319 |
+
"eval_steps_per_second": 1.072,
|
| 320 |
+
"step": 48
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 17.391304347826086,
|
| 324 |
+
"grad_norm": 1.1566580533981323,
|
| 325 |
+
"learning_rate": 9.86522435289912e-06,
|
| 326 |
+
"loss": 0.7232,
|
| 327 |
+
"step": 50
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 17.73913043478261,
|
| 331 |
+
"eval_loss": 0.7002378106117249,
|
| 332 |
+
"eval_runtime": 11.1971,
|
| 333 |
+
"eval_samples_per_second": 1.072,
|
| 334 |
+
"eval_steps_per_second": 1.072,
|
| 335 |
+
"step": 51
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 18.08695652173913,
|
| 339 |
+
"grad_norm": 1.167207956314087,
|
| 340 |
+
"learning_rate": 9.83707609731432e-06,
|
| 341 |
+
"loss": 0.5363,
|
| 342 |
+
"step": 52
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 18.782608695652176,
|
| 346 |
+
"grad_norm": 1.0615767240524292,
|
| 347 |
+
"learning_rate": 9.806308479691595e-06,
|
| 348 |
+
"loss": 0.6275,
|
| 349 |
+
"step": 54
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 18.782608695652176,
|
| 353 |
+
"eval_loss": 0.6459404826164246,
|
| 354 |
+
"eval_runtime": 11.191,
|
| 355 |
+
"eval_samples_per_second": 1.072,
|
| 356 |
+
"eval_steps_per_second": 1.072,
|
| 357 |
+
"step": 54
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 19.47826086956522,
|
| 361 |
+
"grad_norm": 0.6826199889183044,
|
| 362 |
+
"learning_rate": 9.77293816123866e-06,
|
| 363 |
+
"loss": 0.6078,
|
| 364 |
+
"step": 56
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 19.82608695652174,
|
| 368 |
+
"eval_loss": 0.6101614832878113,
|
| 369 |
+
"eval_runtime": 11.1924,
|
| 370 |
+
"eval_samples_per_second": 1.072,
|
| 371 |
+
"eval_steps_per_second": 1.072,
|
| 372 |
+
"step": 57
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 20.17391304347826,
|
| 376 |
+
"grad_norm": 0.8720101118087769,
|
| 377 |
+
"learning_rate": 9.736983212571646e-06,
|
| 378 |
+
"loss": 0.6167,
|
| 379 |
+
"step": 58
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 20.869565217391305,
|
| 383 |
+
"grad_norm": 0.6700724959373474,
|
| 384 |
+
"learning_rate": 9.698463103929542e-06,
|
| 385 |
+
"loss": 0.5477,
|
| 386 |
+
"step": 60
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 20.869565217391305,
|
| 390 |
+
"eval_loss": 0.5827677845954895,
|
| 391 |
+
"eval_runtime": 11.192,
|
| 392 |
+
"eval_samples_per_second": 1.072,
|
| 393 |
+
"eval_steps_per_second": 1.072,
|
| 394 |
+
"step": 60
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 21.565217391304348,
|
| 398 |
+
"grad_norm": 0.6034025549888611,
|
| 399 |
+
"learning_rate": 9.657398694630713e-06,
|
| 400 |
+
"loss": 0.4369,
|
| 401 |
+
"step": 62
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 21.91304347826087,
|
| 405 |
+
"eval_loss": 0.5586910843849182,
|
| 406 |
+
"eval_runtime": 11.2081,
|
| 407 |
+
"eval_samples_per_second": 1.071,
|
| 408 |
+
"eval_steps_per_second": 1.071,
|
| 409 |
+
"step": 63
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 22.26086956521739,
|
| 413 |
+
"grad_norm": 0.627003014087677,
|
| 414 |
+
"learning_rate": 9.613812221777212e-06,
|
| 415 |
+
"loss": 0.5656,
|
| 416 |
+
"step": 64
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 22.956521739130434,
|
| 420 |
+
"grad_norm": 0.5275210738182068,
|
| 421 |
+
"learning_rate": 9.567727288213005e-06,
|
| 422 |
+
"loss": 0.5025,
|
| 423 |
+
"step": 66
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 22.956521739130434,
|
| 427 |
+
"eval_loss": 0.5395612716674805,
|
| 428 |
+
"eval_runtime": 11.1941,
|
| 429 |
+
"eval_samples_per_second": 1.072,
|
| 430 |
+
"eval_steps_per_second": 1.072,
|
| 431 |
+
"step": 66
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 23.652173913043477,
|
| 435 |
+
"grad_norm": 0.600711464881897,
|
| 436 |
+
"learning_rate": 9.519168849742603e-06,
|
| 437 |
+
"loss": 0.5043,
|
| 438 |
+
"step": 68
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 24.0,
|
| 442 |
+
"eval_loss": 0.5226072072982788,
|
| 443 |
+
"eval_runtime": 11.193,
|
| 444 |
+
"eval_samples_per_second": 1.072,
|
| 445 |
+
"eval_steps_per_second": 1.072,
|
| 446 |
+
"step": 69
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 24.347826086956523,
|
| 450 |
+
"grad_norm": 0.4522433876991272,
|
| 451 |
+
"learning_rate": 9.468163201617063e-06,
|
| 452 |
+
"loss": 0.3742,
|
| 453 |
+
"step": 70
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 24.695652173913043,
|
| 457 |
+
"eval_loss": 0.5101320743560791,
|
| 458 |
+
"eval_runtime": 11.1941,
|
| 459 |
+
"eval_samples_per_second": 1.072,
|
| 460 |
+
"eval_steps_per_second": 1.072,
|
| 461 |
+
"step": 71
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 25.043478260869566,
|
| 465 |
+
"grad_norm": 0.5010709166526794,
|
| 466 |
+
"learning_rate": 9.414737964294636e-06,
|
| 467 |
+
"loss": 0.5107,
|
| 468 |
+
"step": 72
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 25.73913043478261,
|
| 472 |
+
"grad_norm": 0.4562795162200928,
|
| 473 |
+
"learning_rate": 9.358922068483813e-06,
|
| 474 |
+
"loss": 0.449,
|
| 475 |
+
"step": 74
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 25.73913043478261,
|
| 479 |
+
"eval_loss": 0.5002694725990295,
|
| 480 |
+
"eval_runtime": 11.1989,
|
| 481 |
+
"eval_samples_per_second": 1.072,
|
| 482 |
+
"eval_steps_per_second": 1.072,
|
| 483 |
+
"step": 74
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 26.434782608695652,
|
| 487 |
+
"grad_norm": 0.38633814454078674,
|
| 488 |
+
"learning_rate": 9.30074573947683e-06,
|
| 489 |
+
"loss": 0.3276,
|
| 490 |
+
"step": 76
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 26.782608695652176,
|
| 494 |
+
"eval_loss": 0.4924570322036743,
|
| 495 |
+
"eval_runtime": 11.1968,
|
| 496 |
+
"eval_samples_per_second": 1.072,
|
| 497 |
+
"eval_steps_per_second": 1.072,
|
| 498 |
+
"step": 77
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 27.130434782608695,
|
| 502 |
+
"grad_norm": 0.46364274621009827,
|
| 503 |
+
"learning_rate": 9.24024048078213e-06,
|
| 504 |
+
"loss": 0.5073,
|
| 505 |
+
"step": 78
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 27.82608695652174,
|
| 509 |
+
"grad_norm": 0.4898723363876343,
|
| 510 |
+
"learning_rate": 9.177439057064684e-06,
|
| 511 |
+
"loss": 0.4754,
|
| 512 |
+
"step": 80
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 27.82608695652174,
|
| 516 |
+
"eval_loss": 0.493239164352417,
|
| 517 |
+
"eval_runtime": 11.1957,
|
| 518 |
+
"eval_samples_per_second": 1.072,
|
| 519 |
+
"eval_steps_per_second": 1.072,
|
| 520 |
+
"step": 80
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 28.52173913043478,
|
| 524 |
+
"grad_norm": 0.5032973885536194,
|
| 525 |
+
"learning_rate": 9.112375476403313e-06,
|
| 526 |
+
"loss": 0.3724,
|
| 527 |
+
"step": 82
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 28.869565217391305,
|
| 531 |
+
"eval_loss": 0.48757660388946533,
|
| 532 |
+
"eval_runtime": 11.1963,
|
| 533 |
+
"eval_samples_per_second": 1.072,
|
| 534 |
+
"eval_steps_per_second": 1.072,
|
| 535 |
+
"step": 83
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 29.217391304347824,
|
| 539 |
+
"grad_norm": 0.2735467553138733,
|
| 540 |
+
"learning_rate": 9.045084971874738e-06,
|
| 541 |
+
"loss": 0.338,
|
| 542 |
+
"step": 84
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 29.91304347826087,
|
| 546 |
+
"grad_norm": 0.4709406793117523,
|
| 547 |
+
"learning_rate": 8.97560398247424e-06,
|
| 548 |
+
"loss": 0.4679,
|
| 549 |
+
"step": 86
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 29.91304347826087,
|
| 553 |
+
"eval_loss": 0.48609817028045654,
|
| 554 |
+
"eval_runtime": 11.1994,
|
| 555 |
+
"eval_samples_per_second": 1.071,
|
| 556 |
+
"eval_steps_per_second": 1.071,
|
| 557 |
+
"step": 86
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 30.608695652173914,
|
| 561 |
+
"grad_norm": 0.25528159737586975,
|
| 562 |
+
"learning_rate": 8.903970133383297e-06,
|
| 563 |
+
"loss": 0.3245,
|
| 564 |
+
"step": 88
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 30.956521739130434,
|
| 568 |
+
"eval_loss": 0.4883822202682495,
|
| 569 |
+
"eval_runtime": 11.1995,
|
| 570 |
+
"eval_samples_per_second": 1.071,
|
| 571 |
+
"eval_steps_per_second": 1.071,
|
| 572 |
+
"step": 89
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 31.304347826086957,
|
| 576 |
+
"grad_norm": 0.36503228545188904,
|
| 577 |
+
"learning_rate": 8.83022221559489e-06,
|
| 578 |
+
"loss": 0.4829,
|
| 579 |
+
"step": 90
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 32.0,
|
| 583 |
+
"grad_norm": 0.3194330930709839,
|
| 584 |
+
"learning_rate": 8.754400164907496e-06,
|
| 585 |
+
"loss": 0.3613,
|
| 586 |
+
"step": 92
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 32.0,
|
| 590 |
+
"eval_loss": 0.4921656847000122,
|
| 591 |
+
"eval_runtime": 11.193,
|
| 592 |
+
"eval_samples_per_second": 1.072,
|
| 593 |
+
"eval_steps_per_second": 1.072,
|
| 594 |
+
"step": 92
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 32.69565217391305,
|
| 598 |
+
"grad_norm": 0.24091415107250214,
|
| 599 |
+
"learning_rate": 8.676545040299145e-06,
|
| 600 |
+
"loss": 0.3511,
|
| 601 |
+
"step": 94
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 32.69565217391305,
|
| 605 |
+
"eval_loss": 0.48988497257232666,
|
| 606 |
+
"eval_runtime": 11.1916,
|
| 607 |
+
"eval_samples_per_second": 1.072,
|
| 608 |
+
"eval_steps_per_second": 1.072,
|
| 609 |
+
"step": 94
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 33.391304347826086,
|
| 613 |
+
"grad_norm": 0.32847926020622253,
|
| 614 |
+
"learning_rate": 8.596699001693257e-06,
|
| 615 |
+
"loss": 0.5275,
|
| 616 |
+
"step": 96
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 33.73913043478261,
|
| 620 |
+
"eval_loss": 0.4931323528289795,
|
| 621 |
+
"eval_runtime": 11.1917,
|
| 622 |
+
"eval_samples_per_second": 1.072,
|
| 623 |
+
"eval_steps_per_second": 1.072,
|
| 624 |
+
"step": 97
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 34.08695652173913,
|
| 628 |
+
"grad_norm": 0.229437455534935,
|
| 629 |
+
"learning_rate": 8.51490528712831e-06,
|
| 630 |
+
"loss": 0.2909,
|
| 631 |
+
"step": 98
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 34.78260869565217,
|
| 635 |
+
"grad_norm": 0.2619946002960205,
|
| 636 |
+
"learning_rate": 8.43120818934367e-06,
|
| 637 |
+
"loss": 0.3403,
|
| 638 |
+
"step": 100
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 34.78260869565217,
|
| 642 |
+
"eval_loss": 0.488254576921463,
|
| 643 |
+
"eval_runtime": 11.2025,
|
| 644 |
+
"eval_samples_per_second": 1.071,
|
| 645 |
+
"eval_steps_per_second": 1.071,
|
| 646 |
+
"step": 100
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 35.47826086956522,
|
| 650 |
+
"grad_norm": 0.2497745305299759,
|
| 651 |
+
"learning_rate": 8.345653031794292e-06,
|
| 652 |
+
"loss": 0.4209,
|
| 653 |
+
"step": 102
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 35.82608695652174,
|
| 657 |
+
"eval_loss": 0.4814887046813965,
|
| 658 |
+
"eval_runtime": 11.195,
|
| 659 |
+
"eval_samples_per_second": 1.072,
|
| 660 |
+
"eval_steps_per_second": 1.072,
|
| 661 |
+
"step": 103
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 36.17391304347826,
|
| 665 |
+
"grad_norm": 0.2717205882072449,
|
| 666 |
+
"learning_rate": 8.258286144107277e-06,
|
| 667 |
+
"loss": 0.3889,
|
| 668 |
+
"step": 104
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 36.869565217391305,
|
| 672 |
+
"grad_norm": 0.2658683955669403,
|
| 673 |
+
"learning_rate": 8.16915483699355e-06,
|
| 674 |
+
"loss": 0.3543,
|
| 675 |
+
"step": 106
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 36.869565217391305,
|
| 679 |
+
"eval_loss": 0.48049914836883545,
|
| 680 |
+
"eval_runtime": 11.1957,
|
| 681 |
+
"eval_samples_per_second": 1.072,
|
| 682 |
+
"eval_steps_per_second": 1.072,
|
| 683 |
+
"step": 106
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 37.56521739130435,
|
| 687 |
+
"grad_norm": 0.24305017292499542,
|
| 688 |
+
"learning_rate": 8.078307376628292e-06,
|
| 689 |
+
"loss": 0.4115,
|
| 690 |
+
"step": 108
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 37.91304347826087,
|
| 694 |
+
"eval_loss": 0.47674474120140076,
|
| 695 |
+
"eval_runtime": 11.1929,
|
| 696 |
+
"eval_samples_per_second": 1.072,
|
| 697 |
+
"eval_steps_per_second": 1.072,
|
| 698 |
+
"step": 109
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 38.26086956521739,
|
| 702 |
+
"grad_norm": 0.27400490641593933,
|
| 703 |
+
"learning_rate": 7.985792958513932e-06,
|
| 704 |
+
"loss": 0.3339,
|
| 705 |
+
"step": 110
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 38.95652173913044,
|
| 709 |
+
"grad_norm": 0.26753950119018555,
|
| 710 |
+
"learning_rate": 7.891661680839932e-06,
|
| 711 |
+
"loss": 0.3902,
|
| 712 |
+
"step": 112
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 38.95652173913044,
|
| 716 |
+
"eval_loss": 0.47939857840538025,
|
| 717 |
+
"eval_runtime": 11.1926,
|
| 718 |
+
"eval_samples_per_second": 1.072,
|
| 719 |
+
"eval_steps_per_second": 1.072,
|
| 720 |
+
"step": 112
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 39.65217391304348,
|
| 724 |
+
"grad_norm": 0.25980764627456665,
|
| 725 |
+
"learning_rate": 7.795964517353734e-06,
|
| 726 |
+
"loss": 0.3735,
|
| 727 |
+
"step": 114
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 40.0,
|
| 731 |
+
"eval_loss": 0.4776058495044708,
|
| 732 |
+
"eval_runtime": 11.1942,
|
| 733 |
+
"eval_samples_per_second": 1.072,
|
| 734 |
+
"eval_steps_per_second": 1.072,
|
| 735 |
+
"step": 115
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 40.34782608695652,
|
| 739 |
+
"grad_norm": 0.2467641979455948,
|
| 740 |
+
"learning_rate": 7.698753289757565e-06,
|
| 741 |
+
"loss": 0.3227,
|
| 742 |
+
"step": 116
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 40.69565217391305,
|
| 746 |
+
"eval_loss": 0.47327545285224915,
|
| 747 |
+
"eval_runtime": 11.1958,
|
| 748 |
+
"eval_samples_per_second": 1.072,
|
| 749 |
+
"eval_steps_per_second": 1.072,
|
| 750 |
+
"step": 117
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 41.04347826086956,
|
| 754 |
+
"grad_norm": 0.28041788935661316,
|
| 755 |
+
"learning_rate": 7.600080639646077e-06,
|
| 756 |
+
"loss": 0.385,
|
| 757 |
+
"step": 118
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 41.73913043478261,
|
| 761 |
+
"grad_norm": 0.21985159814357758,
|
| 762 |
+
"learning_rate": 7.500000000000001e-06,
|
| 763 |
+
"loss": 0.2983,
|
| 764 |
+
"step": 120
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 41.73913043478261,
|
| 768 |
+
"eval_loss": 0.47965100407600403,
|
| 769 |
+
"eval_runtime": 11.1988,
|
| 770 |
+
"eval_samples_per_second": 1.072,
|
| 771 |
+
"eval_steps_per_second": 1.072,
|
| 772 |
+
"step": 120
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 42.43478260869565,
|
| 776 |
+
"grad_norm": 0.30970826745033264,
|
| 777 |
+
"learning_rate": 7.398565566251232e-06,
|
| 778 |
+
"loss": 0.4421,
|
| 779 |
+
"step": 122
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 42.78260869565217,
|
| 783 |
+
"eval_loss": 0.47911468148231506,
|
| 784 |
+
"eval_runtime": 11.2003,
|
| 785 |
+
"eval_samples_per_second": 1.071,
|
| 786 |
+
"eval_steps_per_second": 1.071,
|
| 787 |
+
"step": 123
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 43.130434782608695,
|
| 791 |
+
"grad_norm": 0.320541650056839,
|
| 792 |
+
"learning_rate": 7.295832266935059e-06,
|
| 793 |
+
"loss": 0.3315,
|
| 794 |
+
"step": 124
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 43.82608695652174,
|
| 798 |
+
"grad_norm": 0.3472091853618622,
|
| 799 |
+
"learning_rate": 7.191855733945388e-06,
|
| 800 |
+
"loss": 0.3819,
|
| 801 |
+
"step": 126
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 43.82608695652174,
|
| 805 |
+
"eval_loss": 0.47386252880096436,
|
| 806 |
+
"eval_runtime": 11.1952,
|
| 807 |
+
"eval_samples_per_second": 1.072,
|
| 808 |
+
"eval_steps_per_second": 1.072,
|
| 809 |
+
"step": 126
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 44.52173913043478,
|
| 813 |
+
"grad_norm": 0.24557389318943024,
|
| 814 |
+
"learning_rate": 7.08669227240909e-06,
|
| 815 |
+
"loss": 0.2965,
|
| 816 |
+
"step": 128
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 44.869565217391305,
|
| 820 |
+
"eval_loss": 0.4763611853122711,
|
| 821 |
+
"eval_runtime": 11.1934,
|
| 822 |
+
"eval_samples_per_second": 1.072,
|
| 823 |
+
"eval_steps_per_second": 1.072,
|
| 824 |
+
"step": 129
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 45.21739130434783,
|
| 828 |
+
"grad_norm": 0.39236781001091003,
|
| 829 |
+
"learning_rate": 6.980398830195785e-06,
|
| 830 |
+
"loss": 0.3882,
|
| 831 |
+
"step": 130
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 45.91304347826087,
|
| 835 |
+
"grad_norm": 0.2221372425556183,
|
| 836 |
+
"learning_rate": 6.873032967079562e-06,
|
| 837 |
+
"loss": 0.2661,
|
| 838 |
+
"step": 132
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 45.91304347826087,
|
| 842 |
+
"eval_loss": 0.4764821529388428,
|
| 843 |
+
"eval_runtime": 11.1966,
|
| 844 |
+
"eval_samples_per_second": 1.072,
|
| 845 |
+
"eval_steps_per_second": 1.072,
|
| 846 |
+
"step": 132
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 46.608695652173914,
|
| 850 |
+
"grad_norm": 0.30951645970344543,
|
| 851 |
+
"learning_rate": 6.7646528235693445e-06,
|
| 852 |
+
"loss": 0.3827,
|
| 853 |
+
"step": 134
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"epoch": 46.95652173913044,
|
| 857 |
+
"eval_loss": 0.4778183698654175,
|
| 858 |
+
"eval_runtime": 11.193,
|
| 859 |
+
"eval_samples_per_second": 1.072,
|
| 860 |
+
"eval_steps_per_second": 1.072,
|
| 861 |
+
"step": 135
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 47.30434782608695,
|
| 865 |
+
"grad_norm": 0.3314763903617859,
|
| 866 |
+
"learning_rate": 6.655317089424791e-06,
|
| 867 |
+
"loss": 0.351,
|
| 868 |
+
"step": 136
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 48.0,
|
| 872 |
+
"grad_norm": 0.30320581793785095,
|
| 873 |
+
"learning_rate": 6.545084971874738e-06,
|
| 874 |
+
"loss": 0.3144,
|
| 875 |
+
"step": 138
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 48.0,
|
| 879 |
+
"eval_loss": 0.47970080375671387,
|
| 880 |
+
"eval_runtime": 11.1919,
|
| 881 |
+
"eval_samples_per_second": 1.072,
|
| 882 |
+
"eval_steps_per_second": 1.072,
|
| 883 |
+
"step": 138
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 48.0,
|
| 887 |
+
"step": 138,
|
| 888 |
+
"total_flos": 1.749470205265838e+17,
|
| 889 |
+
"train_loss": 0.9229606502297996,
|
| 890 |
+
"train_runtime": 6469.2828,
|
| 891 |
+
"train_samples_per_second": 1.067,
|
| 892 |
+
"train_steps_per_second": 0.046
|
| 893 |
+
}
|
| 894 |
+
],
|
| 895 |
+
"logging_steps": 2,
|
| 896 |
+
"max_steps": 300,
|
| 897 |
+
"num_input_tokens_seen": 0,
|
| 898 |
+
"num_train_epochs": 150,
|
| 899 |
+
"save_steps": 25,
|
| 900 |
+
"stateful_callbacks": {
|
| 901 |
+
"EarlyStoppingCallback": {
|
| 902 |
+
"args": {
|
| 903 |
+
"early_stopping_patience": 7,
|
| 904 |
+
"early_stopping_threshold": 0.0
|
| 905 |
+
},
|
| 906 |
+
"attributes": {
|
| 907 |
+
"early_stopping_patience_counter": 0
|
| 908 |
+
}
|
| 909 |
+
},
|
| 910 |
+
"TrainerControl": {
|
| 911 |
+
"args": {
|
| 912 |
+
"should_epoch_stop": false,
|
| 913 |
+
"should_evaluate": false,
|
| 914 |
+
"should_log": false,
|
| 915 |
+
"should_save": true,
|
| 916 |
+
"should_training_stop": true
|
| 917 |
+
},
|
| 918 |
+
"attributes": {}
|
| 919 |
+
}
|
| 920 |
+
},
|
| 921 |
+
"total_flos": 1.749470205265838e+17,
|
| 922 |
+
"train_batch_size": 1,
|
| 923 |
+
"trial_name": null,
|
| 924 |
+
"trial_params": null
|
| 925 |
+
}
|