Dynosaur commited on
Commit
06aa597
1 Parent(s): 2311af8

Model save

Browse files
README.md ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3
4
+ base_model: Dynosaur/llama3-8b-math-sft
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: llama3-8b-math-sft-mix-8-1
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
+ # llama3-8b-math-sft-mix-8-1
18
+
19
+ This model is a fine-tuned version of [Dynosaur/llama3-8b-math-sft](https://huggingface.co/Dynosaur/llama3-8b-math-sft) on an unknown dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 2e-05
39
+ - train_batch_size: 2
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - distributed_type: multi-GPU
43
+ - num_devices: 4
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 64
46
+ - total_eval_batch_size: 32
47
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: cosine
49
+ - lr_scheduler_warmup_ratio: 0.1
50
+ - num_epochs: 2
51
+
52
+ ### Training results
53
+
54
+
55
+
56
+ ### Framework versions
57
+
58
+ - Transformers 4.46.3
59
+ - Pytorch 2.5.1+cu124
60
+ - Datasets 3.1.0
61
+ - Tokenizers 0.20.3
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.9994890883877088,
3
+ "total_flos": 314559562137600.0,
4
+ "train_loss": 0.37921321576147854,
5
+ "train_runtime": 11931.8387,
6
+ "train_samples": 109602,
7
+ "train_samples_per_second": 18.371,
8
+ "train_steps_per_second": 0.287
9
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": 128001,
5
+ "max_length": 4096,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.46.3"
9
+ }
runs/Nov25_09-18-59_nb-fe82f499-97ca-407e-866f-4c442a8383ec-5786c4f6b9-b5vn4/events.out.tfevents.1732526456.nb-fe82f499-97ca-407e-866f-4c442a8383ec-5786c4f6b9-b5vn4.108033.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c3a55061579cd4674ef25321c8f06d34b28914220c825455cb5ca335091ea68
3
- size 727726
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e45ba7e1d4fe95bdea95f8565ae3ff0af0c484e10cb2869b34b3afce7b6baa79
3
+ size 728080
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.9994890883877088,
3
+ "total_flos": 314559562137600.0,
4
+ "train_loss": 0.37921321576147854,
5
+ "train_runtime": 11931.8387,
6
+ "train_samples": 109602,
7
+ "train_samples_per_second": 18.371,
8
+ "train_steps_per_second": 0.287
9
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff