Commit
•
15aaef5
1
Parent(s):
737d7a2
Model save
Browse files- README.md +99 -0
- adapter_model.safetensors +1 -1
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +1038 -0
README.md
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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-3
|
| 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-3
|
| 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: 0.7407
|
| 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: 8
|
| 46 |
+
- total_train_batch_size: 8
|
| 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 |
+
| 1.0751 | 0.8696 | 5 | 1.0960 |
|
| 57 |
+
| 1.1004 | 1.9130 | 11 | 1.0923 |
|
| 58 |
+
| 1.1552 | 2.9565 | 17 | 1.0845 |
|
| 59 |
+
| 1.0884 | 4.0 | 23 | 1.0731 |
|
| 60 |
+
| 1.0984 | 4.8696 | 28 | 1.0593 |
|
| 61 |
+
| 1.054 | 5.9130 | 34 | 1.0363 |
|
| 62 |
+
| 0.9646 | 6.9565 | 40 | 1.0060 |
|
| 63 |
+
| 0.9982 | 8.0 | 46 | 0.9700 |
|
| 64 |
+
| 0.9649 | 8.8696 | 51 | 0.9380 |
|
| 65 |
+
| 0.9161 | 9.9130 | 57 | 0.9017 |
|
| 66 |
+
| 0.8966 | 10.9565 | 63 | 0.8722 |
|
| 67 |
+
| 0.8314 | 12.0 | 69 | 0.8468 |
|
| 68 |
+
| 0.7747 | 12.8696 | 74 | 0.8286 |
|
| 69 |
+
| 0.8162 | 13.9130 | 80 | 0.8081 |
|
| 70 |
+
| 0.8422 | 14.9565 | 86 | 0.7906 |
|
| 71 |
+
| 0.7802 | 16.0 | 92 | 0.7776 |
|
| 72 |
+
| 0.7179 | 16.8696 | 97 | 0.7692 |
|
| 73 |
+
| 0.7191 | 17.9130 | 103 | 0.7605 |
|
| 74 |
+
| 0.6644 | 18.9565 | 109 | 0.7524 |
|
| 75 |
+
| 0.6898 | 20.0 | 115 | 0.7456 |
|
| 76 |
+
| 0.6776 | 20.8696 | 120 | 0.7404 |
|
| 77 |
+
| 0.6571 | 21.9130 | 126 | 0.7338 |
|
| 78 |
+
| 0.6177 | 22.9565 | 132 | 0.7289 |
|
| 79 |
+
| 0.6361 | 24.0 | 138 | 0.7246 |
|
| 80 |
+
| 0.6357 | 24.8696 | 143 | 0.7214 |
|
| 81 |
+
| 0.6767 | 25.9130 | 149 | 0.7174 |
|
| 82 |
+
| 0.5947 | 26.9565 | 155 | 0.7170 |
|
| 83 |
+
| 0.6182 | 28.0 | 161 | 0.7156 |
|
| 84 |
+
| 0.5899 | 28.8696 | 166 | 0.7157 |
|
| 85 |
+
| 0.5612 | 29.9130 | 172 | 0.7162 |
|
| 86 |
+
| 0.5545 | 30.9565 | 178 | 0.7185 |
|
| 87 |
+
| 0.5574 | 32.0 | 184 | 0.7232 |
|
| 88 |
+
| 0.5316 | 32.8696 | 189 | 0.7254 |
|
| 89 |
+
| 0.5276 | 33.9130 | 195 | 0.7338 |
|
| 90 |
+
| 0.4653 | 34.9565 | 201 | 0.7407 |
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
### Framework versions
|
| 94 |
+
|
| 95 |
+
- PEFT 0.12.0
|
| 96 |
+
- Transformers 4.44.0
|
| 97 |
+
- Pytorch 2.1.2+cu121
|
| 98 |
+
- Datasets 2.20.0
|
| 99 |
+
- 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 sha256:0454573bce531f1d304a4a2bf1d4420974eca333b38cef69c5ec29e0ddd5f11f
|
| 3 |
size 167832240
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 34.95652173913044,
|
| 3 |
+
"total_flos": 1.5560139400124826e+17,
|
| 4 |
+
"train_loss": 0.769242295281804,
|
| 5 |
+
"train_runtime": 5595.4258,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 1.233,
|
| 8 |
+
"train_steps_per_second": 0.134
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 34.95652173913044,
|
| 3 |
+
"total_flos": 1.5560139400124826e+17,
|
| 4 |
+
"train_loss": 0.769242295281804,
|
| 5 |
+
"train_runtime": 5595.4258,
|
| 6 |
+
"train_samples": 46,
|
| 7 |
+
"train_samples_per_second": 1.233,
|
| 8 |
+
"train_steps_per_second": 0.134
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1038 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7156062722206116,
|
| 3 |
+
"best_model_checkpoint": "data/Llama-31-8B_task-2_60-samples_config-3/checkpoint-161",
|
| 4 |
+
"epoch": 34.95652173913044,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 201,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.17391304347826086,
|
| 13 |
+
"grad_norm": 0.7016680836677551,
|
| 14 |
+
"learning_rate": 1.3333333333333336e-07,
|
| 15 |
+
"loss": 1.1058,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.34782608695652173,
|
| 20 |
+
"grad_norm": 0.7510942816734314,
|
| 21 |
+
"learning_rate": 2.666666666666667e-07,
|
| 22 |
+
"loss": 1.1306,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.6956521739130435,
|
| 27 |
+
"grad_norm": 0.7180184125900269,
|
| 28 |
+
"learning_rate": 5.333333333333335e-07,
|
| 29 |
+
"loss": 1.0751,
|
| 30 |
+
"step": 4
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.8695652173913043,
|
| 34 |
+
"eval_loss": 1.0960289239883423,
|
| 35 |
+
"eval_runtime": 12.9777,
|
| 36 |
+
"eval_samples_per_second": 0.925,
|
| 37 |
+
"eval_steps_per_second": 0.925,
|
| 38 |
+
"step": 5
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 1.0434782608695652,
|
| 42 |
+
"grad_norm": 0.696365475654602,
|
| 43 |
+
"learning_rate": 8.000000000000001e-07,
|
| 44 |
+
"loss": 1.0591,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.391304347826087,
|
| 49 |
+
"grad_norm": 0.7511110901832581,
|
| 50 |
+
"learning_rate": 1.066666666666667e-06,
|
| 51 |
+
"loss": 1.0881,
|
| 52 |
+
"step": 8
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.7391304347826086,
|
| 56 |
+
"grad_norm": 0.6216956973075867,
|
| 57 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 58 |
+
"loss": 1.1004,
|
| 59 |
+
"step": 10
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.9130434782608696,
|
| 63 |
+
"eval_loss": 1.0923012495040894,
|
| 64 |
+
"eval_runtime": 12.9789,
|
| 65 |
+
"eval_samples_per_second": 0.925,
|
| 66 |
+
"eval_steps_per_second": 0.925,
|
| 67 |
+
"step": 11
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 2.0869565217391304,
|
| 71 |
+
"grad_norm": 0.6951440572738647,
|
| 72 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 73 |
+
"loss": 1.0571,
|
| 74 |
+
"step": 12
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 2.4347826086956523,
|
| 78 |
+
"grad_norm": 0.6762353777885437,
|
| 79 |
+
"learning_rate": 1.8666666666666669e-06,
|
| 80 |
+
"loss": 1.0138,
|
| 81 |
+
"step": 14
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.782608695652174,
|
| 85 |
+
"grad_norm": 0.7078174352645874,
|
| 86 |
+
"learning_rate": 2.133333333333334e-06,
|
| 87 |
+
"loss": 1.1552,
|
| 88 |
+
"step": 16
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.9565217391304346,
|
| 92 |
+
"eval_loss": 1.0845402479171753,
|
| 93 |
+
"eval_runtime": 12.9749,
|
| 94 |
+
"eval_samples_per_second": 0.925,
|
| 95 |
+
"eval_steps_per_second": 0.925,
|
| 96 |
+
"step": 17
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 3.130434782608696,
|
| 100 |
+
"grad_norm": 0.7293493747711182,
|
| 101 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 102 |
+
"loss": 1.0645,
|
| 103 |
+
"step": 18
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 3.4782608695652173,
|
| 107 |
+
"grad_norm": 0.7216983437538147,
|
| 108 |
+
"learning_rate": 2.666666666666667e-06,
|
| 109 |
+
"loss": 1.0369,
|
| 110 |
+
"step": 20
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 3.8260869565217392,
|
| 114 |
+
"grad_norm": 0.6637709140777588,
|
| 115 |
+
"learning_rate": 2.9333333333333338e-06,
|
| 116 |
+
"loss": 1.0884,
|
| 117 |
+
"step": 22
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 4.0,
|
| 121 |
+
"eval_loss": 1.0730719566345215,
|
| 122 |
+
"eval_runtime": 12.9771,
|
| 123 |
+
"eval_samples_per_second": 0.925,
|
| 124 |
+
"eval_steps_per_second": 0.925,
|
| 125 |
+
"step": 23
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 4.173913043478261,
|
| 129 |
+
"grad_norm": 0.7498079538345337,
|
| 130 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 131 |
+
"loss": 1.0667,
|
| 132 |
+
"step": 24
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.521739130434782,
|
| 136 |
+
"grad_norm": 0.741428792476654,
|
| 137 |
+
"learning_rate": 3.4666666666666672e-06,
|
| 138 |
+
"loss": 1.0362,
|
| 139 |
+
"step": 26
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 4.869565217391305,
|
| 143 |
+
"grad_norm": 0.7704049348831177,
|
| 144 |
+
"learning_rate": 3.7333333333333337e-06,
|
| 145 |
+
"loss": 1.0984,
|
| 146 |
+
"step": 28
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 4.869565217391305,
|
| 150 |
+
"eval_loss": 1.0593057870864868,
|
| 151 |
+
"eval_runtime": 12.9818,
|
| 152 |
+
"eval_samples_per_second": 0.924,
|
| 153 |
+
"eval_steps_per_second": 0.924,
|
| 154 |
+
"step": 28
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 5.217391304347826,
|
| 158 |
+
"grad_norm": 0.6860598921775818,
|
| 159 |
+
"learning_rate": 4.000000000000001e-06,
|
| 160 |
+
"loss": 1.022,
|
| 161 |
+
"step": 30
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.565217391304348,
|
| 165 |
+
"grad_norm": 0.7669686079025269,
|
| 166 |
+
"learning_rate": 4.266666666666668e-06,
|
| 167 |
+
"loss": 1.022,
|
| 168 |
+
"step": 32
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 5.913043478260869,
|
| 172 |
+
"grad_norm": 0.6506966948509216,
|
| 173 |
+
"learning_rate": 4.533333333333334e-06,
|
| 174 |
+
"loss": 1.054,
|
| 175 |
+
"step": 34
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.913043478260869,
|
| 179 |
+
"eval_loss": 1.0363248586654663,
|
| 180 |
+
"eval_runtime": 12.9751,
|
| 181 |
+
"eval_samples_per_second": 0.925,
|
| 182 |
+
"eval_steps_per_second": 0.925,
|
| 183 |
+
"step": 34
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.260869565217392,
|
| 187 |
+
"grad_norm": 0.7007432579994202,
|
| 188 |
+
"learning_rate": 4.800000000000001e-06,
|
| 189 |
+
"loss": 0.9417,
|
| 190 |
+
"step": 36
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 6.608695652173913,
|
| 194 |
+
"grad_norm": 0.7524662613868713,
|
| 195 |
+
"learning_rate": 5.0666666666666676e-06,
|
| 196 |
+
"loss": 1.0873,
|
| 197 |
+
"step": 38
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 6.956521739130435,
|
| 201 |
+
"grad_norm": 0.6942258477210999,
|
| 202 |
+
"learning_rate": 5.333333333333334e-06,
|
| 203 |
+
"loss": 0.9646,
|
| 204 |
+
"step": 40
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 6.956521739130435,
|
| 208 |
+
"eval_loss": 1.0060027837753296,
|
| 209 |
+
"eval_runtime": 12.9773,
|
| 210 |
+
"eval_samples_per_second": 0.925,
|
| 211 |
+
"eval_steps_per_second": 0.925,
|
| 212 |
+
"step": 40
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 7.304347826086957,
|
| 216 |
+
"grad_norm": 0.6106516718864441,
|
| 217 |
+
"learning_rate": 5.600000000000001e-06,
|
| 218 |
+
"loss": 0.9713,
|
| 219 |
+
"step": 42
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.6521739130434785,
|
| 223 |
+
"grad_norm": 0.6019290089607239,
|
| 224 |
+
"learning_rate": 5.8666666666666675e-06,
|
| 225 |
+
"loss": 0.9628,
|
| 226 |
+
"step": 44
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 8.0,
|
| 230 |
+
"grad_norm": 0.5895516872406006,
|
| 231 |
+
"learning_rate": 6.133333333333334e-06,
|
| 232 |
+
"loss": 0.9982,
|
| 233 |
+
"step": 46
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 8.0,
|
| 237 |
+
"eval_loss": 0.9700033664703369,
|
| 238 |
+
"eval_runtime": 12.976,
|
| 239 |
+
"eval_samples_per_second": 0.925,
|
| 240 |
+
"eval_steps_per_second": 0.925,
|
| 241 |
+
"step": 46
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 8.347826086956522,
|
| 245 |
+
"grad_norm": 0.6009705066680908,
|
| 246 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 247 |
+
"loss": 0.9219,
|
| 248 |
+
"step": 48
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 8.695652173913043,
|
| 252 |
+
"grad_norm": 0.5637978315353394,
|
| 253 |
+
"learning_rate": 6.666666666666667e-06,
|
| 254 |
+
"loss": 0.9649,
|
| 255 |
+
"step": 50
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.869565217391305,
|
| 259 |
+
"eval_loss": 0.9379908442497253,
|
| 260 |
+
"eval_runtime": 12.9746,
|
| 261 |
+
"eval_samples_per_second": 0.925,
|
| 262 |
+
"eval_steps_per_second": 0.925,
|
| 263 |
+
"step": 51
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 9.043478260869565,
|
| 267 |
+
"grad_norm": 0.552122175693512,
|
| 268 |
+
"learning_rate": 6.9333333333333344e-06,
|
| 269 |
+
"loss": 0.9063,
|
| 270 |
+
"step": 52
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 9.391304347826088,
|
| 274 |
+
"grad_norm": 0.5362454652786255,
|
| 275 |
+
"learning_rate": 7.2000000000000005e-06,
|
| 276 |
+
"loss": 0.8733,
|
| 277 |
+
"step": 54
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 9.73913043478261,
|
| 281 |
+
"grad_norm": 0.4836583137512207,
|
| 282 |
+
"learning_rate": 7.4666666666666675e-06,
|
| 283 |
+
"loss": 0.9161,
|
| 284 |
+
"step": 56
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 9.91304347826087,
|
| 288 |
+
"eval_loss": 0.9016616344451904,
|
| 289 |
+
"eval_runtime": 12.9785,
|
| 290 |
+
"eval_samples_per_second": 0.925,
|
| 291 |
+
"eval_steps_per_second": 0.925,
|
| 292 |
+
"step": 57
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 10.08695652173913,
|
| 296 |
+
"grad_norm": 0.4063497483730316,
|
| 297 |
+
"learning_rate": 7.733333333333334e-06,
|
| 298 |
+
"loss": 0.9077,
|
| 299 |
+
"step": 58
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 10.434782608695652,
|
| 303 |
+
"grad_norm": 0.36825188994407654,
|
| 304 |
+
"learning_rate": 8.000000000000001e-06,
|
| 305 |
+
"loss": 0.8492,
|
| 306 |
+
"step": 60
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 10.782608695652174,
|
| 310 |
+
"grad_norm": 0.42374539375305176,
|
| 311 |
+
"learning_rate": 8.266666666666667e-06,
|
| 312 |
+
"loss": 0.8966,
|
| 313 |
+
"step": 62
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 10.956521739130435,
|
| 317 |
+
"eval_loss": 0.8721893429756165,
|
| 318 |
+
"eval_runtime": 12.9792,
|
| 319 |
+
"eval_samples_per_second": 0.925,
|
| 320 |
+
"eval_steps_per_second": 0.925,
|
| 321 |
+
"step": 63
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.130434782608695,
|
| 325 |
+
"grad_norm": 0.39867985248565674,
|
| 326 |
+
"learning_rate": 8.533333333333335e-06,
|
| 327 |
+
"loss": 0.8529,
|
| 328 |
+
"step": 64
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 11.478260869565217,
|
| 332 |
+
"grad_norm": 0.3662341833114624,
|
| 333 |
+
"learning_rate": 8.8e-06,
|
| 334 |
+
"loss": 0.8509,
|
| 335 |
+
"step": 66
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 11.826086956521738,
|
| 339 |
+
"grad_norm": 0.31930872797966003,
|
| 340 |
+
"learning_rate": 9.066666666666667e-06,
|
| 341 |
+
"loss": 0.8314,
|
| 342 |
+
"step": 68
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 12.0,
|
| 346 |
+
"eval_loss": 0.8468105792999268,
|
| 347 |
+
"eval_runtime": 12.9771,
|
| 348 |
+
"eval_samples_per_second": 0.925,
|
| 349 |
+
"eval_steps_per_second": 0.925,
|
| 350 |
+
"step": 69
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 12.173913043478262,
|
| 354 |
+
"grad_norm": 0.3196379244327545,
|
| 355 |
+
"learning_rate": 9.333333333333334e-06,
|
| 356 |
+
"loss": 0.7984,
|
| 357 |
+
"step": 70
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.521739130434783,
|
| 361 |
+
"grad_norm": 0.37208741903305054,
|
| 362 |
+
"learning_rate": 9.600000000000001e-06,
|
| 363 |
+
"loss": 0.8613,
|
| 364 |
+
"step": 72
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 12.869565217391305,
|
| 368 |
+
"grad_norm": 0.333916574716568,
|
| 369 |
+
"learning_rate": 9.866666666666668e-06,
|
| 370 |
+
"loss": 0.7747,
|
| 371 |
+
"step": 74
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 12.869565217391305,
|
| 375 |
+
"eval_loss": 0.8285906314849854,
|
| 376 |
+
"eval_runtime": 12.9738,
|
| 377 |
+
"eval_samples_per_second": 0.925,
|
| 378 |
+
"eval_steps_per_second": 0.925,
|
| 379 |
+
"step": 74
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 13.217391304347826,
|
| 383 |
+
"grad_norm": 0.3695715367794037,
|
| 384 |
+
"learning_rate": 9.999945845889795e-06,
|
| 385 |
+
"loss": 0.8164,
|
| 386 |
+
"step": 76
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 13.565217391304348,
|
| 390 |
+
"grad_norm": 0.3073723316192627,
|
| 391 |
+
"learning_rate": 9.999512620046523e-06,
|
| 392 |
+
"loss": 0.786,
|
| 393 |
+
"step": 78
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 13.91304347826087,
|
| 397 |
+
"grad_norm": 0.3305300176143646,
|
| 398 |
+
"learning_rate": 9.99864620589731e-06,
|
| 399 |
+
"loss": 0.8162,
|
| 400 |
+
"step": 80
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 13.91304347826087,
|
| 404 |
+
"eval_loss": 0.8081052899360657,
|
| 405 |
+
"eval_runtime": 12.9758,
|
| 406 |
+
"eval_samples_per_second": 0.925,
|
| 407 |
+
"eval_steps_per_second": 0.925,
|
| 408 |
+
"step": 80
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 14.26086956521739,
|
| 412 |
+
"grad_norm": 0.2998150587081909,
|
| 413 |
+
"learning_rate": 9.99734667851357e-06,
|
| 414 |
+
"loss": 0.697,
|
| 415 |
+
"step": 82
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 14.608695652173914,
|
| 419 |
+
"grad_norm": 0.304190069437027,
|
| 420 |
+
"learning_rate": 9.995614150494293e-06,
|
| 421 |
+
"loss": 0.7373,
|
| 422 |
+
"step": 84
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 14.956521739130435,
|
| 426 |
+
"grad_norm": 0.3205544948577881,
|
| 427 |
+
"learning_rate": 9.993448771956285e-06,
|
| 428 |
+
"loss": 0.8422,
|
| 429 |
+
"step": 86
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 14.956521739130435,
|
| 433 |
+
"eval_loss": 0.7906327843666077,
|
| 434 |
+
"eval_runtime": 12.981,
|
| 435 |
+
"eval_samples_per_second": 0.924,
|
| 436 |
+
"eval_steps_per_second": 0.924,
|
| 437 |
+
"step": 86
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 15.304347826086957,
|
| 441 |
+
"grad_norm": 0.29707759618759155,
|
| 442 |
+
"learning_rate": 9.99085073052117e-06,
|
| 443 |
+
"loss": 0.7246,
|
| 444 |
+
"step": 88
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 15.652173913043478,
|
| 448 |
+
"grad_norm": 0.36958566308021545,
|
| 449 |
+
"learning_rate": 9.987820251299121e-06,
|
| 450 |
+
"loss": 0.7637,
|
| 451 |
+
"step": 90
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 16.0,
|
| 455 |
+
"grad_norm": 0.2745814919471741,
|
| 456 |
+
"learning_rate": 9.984357596869369e-06,
|
| 457 |
+
"loss": 0.7802,
|
| 458 |
+
"step": 92
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 16.0,
|
| 462 |
+
"eval_loss": 0.7775909304618835,
|
| 463 |
+
"eval_runtime": 12.9815,
|
| 464 |
+
"eval_samples_per_second": 0.924,
|
| 465 |
+
"eval_steps_per_second": 0.924,
|
| 466 |
+
"step": 92
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 16.347826086956523,
|
| 470 |
+
"grad_norm": 0.3392060399055481,
|
| 471 |
+
"learning_rate": 9.980463067257437e-06,
|
| 472 |
+
"loss": 0.7707,
|
| 473 |
+
"step": 94
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 16.695652173913043,
|
| 477 |
+
"grad_norm": 0.2813577651977539,
|
| 478 |
+
"learning_rate": 9.976136999909156e-06,
|
| 479 |
+
"loss": 0.7179,
|
| 480 |
+
"step": 96
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 16.869565217391305,
|
| 484 |
+
"eval_loss": 0.7692317962646484,
|
| 485 |
+
"eval_runtime": 12.9784,
|
| 486 |
+
"eval_samples_per_second": 0.925,
|
| 487 |
+
"eval_steps_per_second": 0.925,
|
| 488 |
+
"step": 97
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 17.043478260869566,
|
| 492 |
+
"grad_norm": 0.29758134484291077,
|
| 493 |
+
"learning_rate": 9.971379769661422e-06,
|
| 494 |
+
"loss": 0.7172,
|
| 495 |
+
"step": 98
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 17.391304347826086,
|
| 499 |
+
"grad_norm": 0.3041021525859833,
|
| 500 |
+
"learning_rate": 9.966191788709716e-06,
|
| 501 |
+
"loss": 0.7507,
|
| 502 |
+
"step": 100
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 17.73913043478261,
|
| 506 |
+
"grad_norm": 0.29003143310546875,
|
| 507 |
+
"learning_rate": 9.960573506572391e-06,
|
| 508 |
+
"loss": 0.7191,
|
| 509 |
+
"step": 102
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 17.91304347826087,
|
| 513 |
+
"eval_loss": 0.7605112195014954,
|
| 514 |
+
"eval_runtime": 12.9797,
|
| 515 |
+
"eval_samples_per_second": 0.925,
|
| 516 |
+
"eval_steps_per_second": 0.925,
|
| 517 |
+
"step": 103
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 18.08695652173913,
|
| 521 |
+
"grad_norm": 0.29067984223365784,
|
| 522 |
+
"learning_rate": 9.95452541005172e-06,
|
| 523 |
+
"loss": 0.7032,
|
| 524 |
+
"step": 104
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 18.434782608695652,
|
| 528 |
+
"grad_norm": 0.26193752884864807,
|
| 529 |
+
"learning_rate": 9.948048023191728e-06,
|
| 530 |
+
"loss": 0.7523,
|
| 531 |
+
"step": 106
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 18.782608695652176,
|
| 535 |
+
"grad_norm": 0.30279889702796936,
|
| 536 |
+
"learning_rate": 9.941141907232766e-06,
|
| 537 |
+
"loss": 0.6644,
|
| 538 |
+
"step": 108
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 18.956521739130434,
|
| 542 |
+
"eval_loss": 0.7523689270019531,
|
| 543 |
+
"eval_runtime": 12.9798,
|
| 544 |
+
"eval_samples_per_second": 0.925,
|
| 545 |
+
"eval_steps_per_second": 0.925,
|
| 546 |
+
"step": 109
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 19.130434782608695,
|
| 550 |
+
"grad_norm": 0.29118812084198,
|
| 551 |
+
"learning_rate": 9.933807660562898e-06,
|
| 552 |
+
"loss": 0.7396,
|
| 553 |
+
"step": 110
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 19.47826086956522,
|
| 557 |
+
"grad_norm": 0.3351486623287201,
|
| 558 |
+
"learning_rate": 9.926045918666045e-06,
|
| 559 |
+
"loss": 0.7189,
|
| 560 |
+
"step": 112
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 19.82608695652174,
|
| 564 |
+
"grad_norm": 0.300157755613327,
|
| 565 |
+
"learning_rate": 9.91785735406693e-06,
|
| 566 |
+
"loss": 0.6898,
|
| 567 |
+
"step": 114
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 20.0,
|
| 571 |
+
"eval_loss": 0.7455799579620361,
|
| 572 |
+
"eval_runtime": 12.9769,
|
| 573 |
+
"eval_samples_per_second": 0.925,
|
| 574 |
+
"eval_steps_per_second": 0.925,
|
| 575 |
+
"step": 115
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 20.17391304347826,
|
| 579 |
+
"grad_norm": 0.28359395265579224,
|
| 580 |
+
"learning_rate": 9.909242676272797e-06,
|
| 581 |
+
"loss": 0.6711,
|
| 582 |
+
"step": 116
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 20.52173913043478,
|
| 586 |
+
"grad_norm": 0.2949537932872772,
|
| 587 |
+
"learning_rate": 9.90020263171194e-06,
|
| 588 |
+
"loss": 0.7176,
|
| 589 |
+
"step": 118
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 20.869565217391305,
|
| 593 |
+
"grad_norm": 0.3114525079727173,
|
| 594 |
+
"learning_rate": 9.890738003669029e-06,
|
| 595 |
+
"loss": 0.6776,
|
| 596 |
+
"step": 120
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 20.869565217391305,
|
| 600 |
+
"eval_loss": 0.740369975566864,
|
| 601 |
+
"eval_runtime": 12.9813,
|
| 602 |
+
"eval_samples_per_second": 0.924,
|
| 603 |
+
"eval_steps_per_second": 0.924,
|
| 604 |
+
"step": 120
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 21.217391304347824,
|
| 608 |
+
"grad_norm": 0.2974396049976349,
|
| 609 |
+
"learning_rate": 9.880849612217238e-06,
|
| 610 |
+
"loss": 0.6606,
|
| 611 |
+
"step": 122
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 21.565217391304348,
|
| 615 |
+
"grad_norm": 0.3048945963382721,
|
| 616 |
+
"learning_rate": 9.870538314147194e-06,
|
| 617 |
+
"loss": 0.7063,
|
| 618 |
+
"step": 124
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 21.91304347826087,
|
| 622 |
+
"grad_norm": 0.32696473598480225,
|
| 623 |
+
"learning_rate": 9.859805002892733e-06,
|
| 624 |
+
"loss": 0.6571,
|
| 625 |
+
"step": 126
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 21.91304347826087,
|
| 629 |
+
"eval_loss": 0.7337734699249268,
|
| 630 |
+
"eval_runtime": 12.9777,
|
| 631 |
+
"eval_samples_per_second": 0.925,
|
| 632 |
+
"eval_steps_per_second": 0.925,
|
| 633 |
+
"step": 126
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 22.26086956521739,
|
| 637 |
+
"grad_norm": 0.31726372241973877,
|
| 638 |
+
"learning_rate": 9.84865060845349e-06,
|
| 639 |
+
"loss": 0.7094,
|
| 640 |
+
"step": 128
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 22.608695652173914,
|
| 644 |
+
"grad_norm": 0.31174156069755554,
|
| 645 |
+
"learning_rate": 9.83707609731432e-06,
|
| 646 |
+
"loss": 0.6608,
|
| 647 |
+
"step": 130
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 22.956521739130434,
|
| 651 |
+
"grad_norm": 0.31973257660865784,
|
| 652 |
+
"learning_rate": 9.825082472361558e-06,
|
| 653 |
+
"loss": 0.6177,
|
| 654 |
+
"step": 132
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 22.956521739130434,
|
| 658 |
+
"eval_loss": 0.7288563847541809,
|
| 659 |
+
"eval_runtime": 12.9756,
|
| 660 |
+
"eval_samples_per_second": 0.925,
|
| 661 |
+
"eval_steps_per_second": 0.925,
|
| 662 |
+
"step": 132
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 23.304347826086957,
|
| 666 |
+
"grad_norm": 0.36018624901771545,
|
| 667 |
+
"learning_rate": 9.812670772796113e-06,
|
| 668 |
+
"loss": 0.6802,
|
| 669 |
+
"step": 134
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 23.652173913043477,
|
| 673 |
+
"grad_norm": 0.30724474787712097,
|
| 674 |
+
"learning_rate": 9.799842074043438e-06,
|
| 675 |
+
"loss": 0.6582,
|
| 676 |
+
"step": 136
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 24.0,
|
| 680 |
+
"grad_norm": 0.3061894178390503,
|
| 681 |
+
"learning_rate": 9.786597487660336e-06,
|
| 682 |
+
"loss": 0.6361,
|
| 683 |
+
"step": 138
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 24.0,
|
| 687 |
+
"eval_loss": 0.724605143070221,
|
| 688 |
+
"eval_runtime": 12.9779,
|
| 689 |
+
"eval_samples_per_second": 0.925,
|
| 690 |
+
"eval_steps_per_second": 0.925,
|
| 691 |
+
"step": 138
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 24.347826086956523,
|
| 695 |
+
"grad_norm": 0.3347689211368561,
|
| 696 |
+
"learning_rate": 9.77293816123866e-06,
|
| 697 |
+
"loss": 0.6304,
|
| 698 |
+
"step": 140
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 24.695652173913043,
|
| 702 |
+
"grad_norm": 0.3372015058994293,
|
| 703 |
+
"learning_rate": 9.75886527830587e-06,
|
| 704 |
+
"loss": 0.6357,
|
| 705 |
+
"step": 142
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 24.869565217391305,
|
| 709 |
+
"eval_loss": 0.7214323878288269,
|
| 710 |
+
"eval_runtime": 12.9829,
|
| 711 |
+
"eval_samples_per_second": 0.924,
|
| 712 |
+
"eval_steps_per_second": 0.924,
|
| 713 |
+
"step": 143
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 25.043478260869566,
|
| 717 |
+
"grad_norm": 0.3627227544784546,
|
| 718 |
+
"learning_rate": 9.744380058222483e-06,
|
| 719 |
+
"loss": 0.6527,
|
| 720 |
+
"step": 144
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 25.391304347826086,
|
| 724 |
+
"grad_norm": 0.32768282294273376,
|
| 725 |
+
"learning_rate": 9.729483756076436e-06,
|
| 726 |
+
"loss": 0.6396,
|
| 727 |
+
"step": 146
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 25.73913043478261,
|
| 731 |
+
"grad_norm": 0.3657958209514618,
|
| 732 |
+
"learning_rate": 9.714177662574316e-06,
|
| 733 |
+
"loss": 0.6767,
|
| 734 |
+
"step": 148
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 25.91304347826087,
|
| 738 |
+
"eval_loss": 0.7174214720726013,
|
| 739 |
+
"eval_runtime": 12.9804,
|
| 740 |
+
"eval_samples_per_second": 0.924,
|
| 741 |
+
"eval_steps_per_second": 0.924,
|
| 742 |
+
"step": 149
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 26.08695652173913,
|
| 746 |
+
"grad_norm": 0.38097909092903137,
|
| 747 |
+
"learning_rate": 9.698463103929542e-06,
|
| 748 |
+
"loss": 0.5935,
|
| 749 |
+
"step": 150
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 26.434782608695652,
|
| 753 |
+
"grad_norm": 0.3344641327857971,
|
| 754 |
+
"learning_rate": 9.682341441747446e-06,
|
| 755 |
+
"loss": 0.6088,
|
| 756 |
+
"step": 152
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 26.782608695652176,
|
| 760 |
+
"grad_norm": 0.35751739144325256,
|
| 761 |
+
"learning_rate": 9.665814072907293e-06,
|
| 762 |
+
"loss": 0.5947,
|
| 763 |
+
"step": 154
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 26.956521739130434,
|
| 767 |
+
"eval_loss": 0.7170318961143494,
|
| 768 |
+
"eval_runtime": 12.9784,
|
| 769 |
+
"eval_samples_per_second": 0.925,
|
| 770 |
+
"eval_steps_per_second": 0.925,
|
| 771 |
+
"step": 155
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 27.130434782608695,
|
| 775 |
+
"grad_norm": 0.3365950584411621,
|
| 776 |
+
"learning_rate": 9.648882429441258e-06,
|
| 777 |
+
"loss": 0.6198,
|
| 778 |
+
"step": 156
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 27.47826086956522,
|
| 782 |
+
"grad_norm": 0.419979989528656,
|
| 783 |
+
"learning_rate": 9.63154797841033e-06,
|
| 784 |
+
"loss": 0.5974,
|
| 785 |
+
"step": 158
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 27.82608695652174,
|
| 789 |
+
"grad_norm": 0.3486815392971039,
|
| 790 |
+
"learning_rate": 9.613812221777212e-06,
|
| 791 |
+
"loss": 0.6182,
|
| 792 |
+
"step": 160
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 28.0,
|
| 796 |
+
"eval_loss": 0.7156062722206116,
|
| 797 |
+
"eval_runtime": 12.977,
|
| 798 |
+
"eval_samples_per_second": 0.925,
|
| 799 |
+
"eval_steps_per_second": 0.925,
|
| 800 |
+
"step": 161
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 28.17391304347826,
|
| 804 |
+
"grad_norm": 0.37861475348472595,
|
| 805 |
+
"learning_rate": 9.595676696276173e-06,
|
| 806 |
+
"loss": 0.5702,
|
| 807 |
+
"step": 162
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 28.52173913043478,
|
| 811 |
+
"grad_norm": 0.3779279589653015,
|
| 812 |
+
"learning_rate": 9.577142973279896e-06,
|
| 813 |
+
"loss": 0.5992,
|
| 814 |
+
"step": 164
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 28.869565217391305,
|
| 818 |
+
"grad_norm": 0.4336070418357849,
|
| 819 |
+
"learning_rate": 9.55821265866333e-06,
|
| 820 |
+
"loss": 0.5899,
|
| 821 |
+
"step": 166
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 28.869565217391305,
|
| 825 |
+
"eval_loss": 0.7157405018806458,
|
| 826 |
+
"eval_runtime": 12.9775,
|
| 827 |
+
"eval_samples_per_second": 0.925,
|
| 828 |
+
"eval_steps_per_second": 0.925,
|
| 829 |
+
"step": 166
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 29.217391304347824,
|
| 833 |
+
"grad_norm": 0.37057119607925415,
|
| 834 |
+
"learning_rate": 9.538887392664544e-06,
|
| 835 |
+
"loss": 0.588,
|
| 836 |
+
"step": 168
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 29.565217391304348,
|
| 840 |
+
"grad_norm": 0.4328691065311432,
|
| 841 |
+
"learning_rate": 9.519168849742603e-06,
|
| 842 |
+
"loss": 0.5622,
|
| 843 |
+
"step": 170
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 29.91304347826087,
|
| 847 |
+
"grad_norm": 0.4100225567817688,
|
| 848 |
+
"learning_rate": 9.499058738432492e-06,
|
| 849 |
+
"loss": 0.5612,
|
| 850 |
+
"step": 172
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 29.91304347826087,
|
| 854 |
+
"eval_loss": 0.7161919474601746,
|
| 855 |
+
"eval_runtime": 12.9765,
|
| 856 |
+
"eval_samples_per_second": 0.925,
|
| 857 |
+
"eval_steps_per_second": 0.925,
|
| 858 |
+
"step": 172
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 30.26086956521739,
|
| 862 |
+
"grad_norm": 0.4240186810493469,
|
| 863 |
+
"learning_rate": 9.478558801197065e-06,
|
| 864 |
+
"loss": 0.5735,
|
| 865 |
+
"step": 174
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 30.608695652173914,
|
| 869 |
+
"grad_norm": 0.43012985587120056,
|
| 870 |
+
"learning_rate": 9.457670814276083e-06,
|
| 871 |
+
"loss": 0.5602,
|
| 872 |
+
"step": 176
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 30.956521739130434,
|
| 876 |
+
"grad_norm": 0.4227677881717682,
|
| 877 |
+
"learning_rate": 9.436396587532297e-06,
|
| 878 |
+
"loss": 0.5545,
|
| 879 |
+
"step": 178
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 30.956521739130434,
|
| 883 |
+
"eval_loss": 0.7185451984405518,
|
| 884 |
+
"eval_runtime": 12.9819,
|
| 885 |
+
"eval_samples_per_second": 0.924,
|
| 886 |
+
"eval_steps_per_second": 0.924,
|
| 887 |
+
"step": 178
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 31.304347826086957,
|
| 891 |
+
"grad_norm": 0.45781397819519043,
|
| 892 |
+
"learning_rate": 9.414737964294636e-06,
|
| 893 |
+
"loss": 0.519,
|
| 894 |
+
"step": 180
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 31.652173913043477,
|
| 898 |
+
"grad_norm": 0.4655354619026184,
|
| 899 |
+
"learning_rate": 9.392696821198488e-06,
|
| 900 |
+
"loss": 0.5702,
|
| 901 |
+
"step": 182
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 32.0,
|
| 905 |
+
"grad_norm": 0.5229057669639587,
|
| 906 |
+
"learning_rate": 9.370275068023097e-06,
|
| 907 |
+
"loss": 0.5574,
|
| 908 |
+
"step": 184
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 32.0,
|
| 912 |
+
"eval_loss": 0.7232272624969482,
|
| 913 |
+
"eval_runtime": 12.9824,
|
| 914 |
+
"eval_samples_per_second": 0.924,
|
| 915 |
+
"eval_steps_per_second": 0.924,
|
| 916 |
+
"step": 184
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 32.34782608695652,
|
| 920 |
+
"grad_norm": 0.4893576204776764,
|
| 921 |
+
"learning_rate": 9.347474647526095e-06,
|
| 922 |
+
"loss": 0.5103,
|
| 923 |
+
"step": 186
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 32.69565217391305,
|
| 927 |
+
"grad_norm": 0.5043169260025024,
|
| 928 |
+
"learning_rate": 9.324297535275156e-06,
|
| 929 |
+
"loss": 0.5316,
|
| 930 |
+
"step": 188
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 32.869565217391305,
|
| 934 |
+
"eval_loss": 0.725393533706665,
|
| 935 |
+
"eval_runtime": 12.9763,
|
| 936 |
+
"eval_samples_per_second": 0.925,
|
| 937 |
+
"eval_steps_per_second": 0.925,
|
| 938 |
+
"step": 189
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 33.04347826086956,
|
| 942 |
+
"grad_norm": 0.6029254198074341,
|
| 943 |
+
"learning_rate": 9.30074573947683e-06,
|
| 944 |
+
"loss": 0.5299,
|
| 945 |
+
"step": 190
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 33.391304347826086,
|
| 949 |
+
"grad_norm": 0.4804014265537262,
|
| 950 |
+
"learning_rate": 9.276821300802535e-06,
|
| 951 |
+
"loss": 0.5041,
|
| 952 |
+
"step": 192
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 33.73913043478261,
|
| 956 |
+
"grad_norm": 0.5214328169822693,
|
| 957 |
+
"learning_rate": 9.25252629221175e-06,
|
| 958 |
+
"loss": 0.5276,
|
| 959 |
+
"step": 194
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 33.91304347826087,
|
| 963 |
+
"eval_loss": 0.7338247299194336,
|
| 964 |
+
"eval_runtime": 12.98,
|
| 965 |
+
"eval_samples_per_second": 0.924,
|
| 966 |
+
"eval_steps_per_second": 0.924,
|
| 967 |
+
"step": 195
|
| 968 |
+
},
|
| 969 |
+
{
|
| 970 |
+
"epoch": 34.08695652173913,
|
| 971 |
+
"grad_norm": 0.5305810570716858,
|
| 972 |
+
"learning_rate": 9.227862818772392e-06,
|
| 973 |
+
"loss": 0.4906,
|
| 974 |
+
"step": 196
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 34.43478260869565,
|
| 978 |
+
"grad_norm": 0.5043832659721375,
|
| 979 |
+
"learning_rate": 9.202833017478421e-06,
|
| 980 |
+
"loss": 0.5014,
|
| 981 |
+
"step": 198
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 34.78260869565217,
|
| 985 |
+
"grad_norm": 0.7232289910316467,
|
| 986 |
+
"learning_rate": 9.177439057064684e-06,
|
| 987 |
+
"loss": 0.4653,
|
| 988 |
+
"step": 200
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 34.95652173913044,
|
| 992 |
+
"eval_loss": 0.7406532764434814,
|
| 993 |
+
"eval_runtime": 12.9783,
|
| 994 |
+
"eval_samples_per_second": 0.925,
|
| 995 |
+
"eval_steps_per_second": 0.925,
|
| 996 |
+
"step": 201
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 34.95652173913044,
|
| 1000 |
+
"step": 201,
|
| 1001 |
+
"total_flos": 1.5560139400124826e+17,
|
| 1002 |
+
"train_loss": 0.769242295281804,
|
| 1003 |
+
"train_runtime": 5595.4258,
|
| 1004 |
+
"train_samples_per_second": 1.233,
|
| 1005 |
+
"train_steps_per_second": 0.134
|
| 1006 |
+
}
|
| 1007 |
+
],
|
| 1008 |
+
"logging_steps": 2,
|
| 1009 |
+
"max_steps": 750,
|
| 1010 |
+
"num_input_tokens_seen": 0,
|
| 1011 |
+
"num_train_epochs": 150,
|
| 1012 |
+
"save_steps": 25,
|
| 1013 |
+
"stateful_callbacks": {
|
| 1014 |
+
"EarlyStoppingCallback": {
|
| 1015 |
+
"args": {
|
| 1016 |
+
"early_stopping_patience": 7,
|
| 1017 |
+
"early_stopping_threshold": 0.0
|
| 1018 |
+
},
|
| 1019 |
+
"attributes": {
|
| 1020 |
+
"early_stopping_patience_counter": 0
|
| 1021 |
+
}
|
| 1022 |
+
},
|
| 1023 |
+
"TrainerControl": {
|
| 1024 |
+
"args": {
|
| 1025 |
+
"should_epoch_stop": false,
|
| 1026 |
+
"should_evaluate": false,
|
| 1027 |
+
"should_log": false,
|
| 1028 |
+
"should_save": true,
|
| 1029 |
+
"should_training_stop": true
|
| 1030 |
+
},
|
| 1031 |
+
"attributes": {}
|
| 1032 |
+
}
|
| 1033 |
+
},
|
| 1034 |
+
"total_flos": 1.5560139400124826e+17,
|
| 1035 |
+
"train_batch_size": 1,
|
| 1036 |
+
"trial_name": null,
|
| 1037 |
+
"trial_params": null
|
| 1038 |
+
}
|