Hugging Face's logo

mlfoundations-dev
/
open-o1-sft-original

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
mikeam commited on
Commit
b86e7f2
·
verified ·
1 Parent(s): 248b409

Training in progress, epoch 0

Browse files
Files changed (8) hide show
  1. README.md +66 -0
  2. generation_config.json +9 -0
  3. model-00001-of-00004.safetensors +1 -1
  4. model-00002-of-00004.safetensors +1 -1
  5. model-00003-of-00004.safetensors +1 -1
  6. model-00004-of-00004.safetensors +1 -1
  7. trainer_log.jsonl +17 -26
  8. training_args.bin +1 -1
README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: llama3.1
4
+ base_model: meta-llama/Meta-Llama-3.1-8B
5
+ tags:
6
+ - llama-factory
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: open-o1-sft-original
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # open-o1-sft-original
17
+
18
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.5192
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-06
40
+ - train_batch_size: 8
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - distributed_type: multi-GPU
44
+ - num_devices: 8
45
+ - gradient_accumulation_steps: 8
46
+ - total_train_batch_size: 512
47
+ - total_eval_batch_size: 64
48
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: constant
50
+ - num_epochs: 3.0
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.5577 | 0.9954 | 82 | 0.5473 |
57
+ | 0.4963 | 1.9939 | 164 | 0.5244 |
58
+ | 0.4507 | 2.9924 | 246 | 0.5192 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.46.1
64
+ - Pytorch 2.5.1
65
+ - Datasets 3.0.2
66
+ - Tokenizers 0.20.3
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": 128001,
6
+ "temperature": 0.6,
7
+ "top_p": 0.9,
8
+ "transformers_version": "4.46.1"
9
+ }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b08b2efedb963a297454b19b9a93b84c55c66611a8fd5c4401e8a0aaa0f22005
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00a5106aa6398b096d05eb3c5c357f475df263ff1c5f1d05c794d446e85cf0f4
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac2d95a09d4c3b39e6f62419c954b2abb9acc6ad86d50850a123fe18884e8c62
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c80dc3843837eb4f5679a782936ab8a839101ad0d3186f45a269d4abef656a5c
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b3f3c1a14d52e37be4c8cb799f9df3e79bdff8a99b6e6c72357d17f075ea08c
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b83e7b89a44f272c412438cd8a460b7aa7a45e0a4f1a85f87a5871c7f70c5615
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8409661ef7c3b5a47b468f5e4462d8d7f5affeee69dbedf8e9500a5935b0078d
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4dc144b591ef8e3b1a26a29f86e9942499190d6de29d5c72210c0718d5c8c94c
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,26 +1,17 @@
1
- {"current_steps": 10, "total_steps": 246, "loss": 0.7712, "lr": 5e-06, "epoch": 0.12139605462822459, "percentage": 4.07, "elapsed_time": "0:03:55", "remaining_time": "1:32:48"}
2
- {"current_steps": 20, "total_steps": 246, "loss": 0.6684, "lr": 5e-06, "epoch": 0.24279210925644917, "percentage": 8.13, "elapsed_time": "0:07:48", "remaining_time": "1:28:18"}
3
- {"current_steps": 30, "total_steps": 246, "loss": 0.6263, "lr": 5e-06, "epoch": 0.36418816388467373, "percentage": 12.2, "elapsed_time": "0:11:41", "remaining_time": "1:24:13"}
4
- {"current_steps": 40, "total_steps": 246, "loss": 0.6051, "lr": 5e-06, "epoch": 0.48558421851289835, "percentage": 16.26, "elapsed_time": "0:15:34", "remaining_time": "1:20:14"}
5
- {"current_steps": 50, "total_steps": 246, "loss": 0.588, "lr": 5e-06, "epoch": 0.6069802731411229, "percentage": 20.33, "elapsed_time": "0:19:27", "remaining_time": "1:16:18"}
6
- {"current_steps": 60, "total_steps": 246, "loss": 0.576, "lr": 5e-06, "epoch": 0.7283763277693475, "percentage": 24.39, "elapsed_time": "0:23:20", "remaining_time": "1:12:22"}
7
- {"current_steps": 70, "total_steps": 246, "loss": 0.5632, "lr": 5e-06, "epoch": 0.849772382397572, "percentage": 28.46, "elapsed_time": "0:27:13", "remaining_time": "1:08:28"}
8
- {"current_steps": 80, "total_steps": 246, "loss": 0.5577, "lr": 5e-06, "epoch": 0.9711684370257967, "percentage": 32.52, "elapsed_time": "0:31:06", "remaining_time": "1:04:33"}
9
- {"current_steps": 82, "total_steps": 246, "eval_loss": 0.5473200082778931, "epoch": 0.9954476479514416, "percentage": 33.33, "elapsed_time": "0:32:27", "remaining_time": "1:04:55"}
10
- {"current_steps": 90, "total_steps": 246, "loss": 0.5736, "lr": 5e-06, "epoch": 1.095599393019727, "percentage": 36.59, "elapsed_time": "0:37:13", "remaining_time": "1:04:31"}
11
- {"current_steps": 100, "total_steps": 246, "loss": 0.5097, "lr": 5e-06, "epoch": 1.2169954476479514, "percentage": 40.65, "elapsed_time": "0:41:06", "remaining_time": "1:00:01"}
12
- {"current_steps": 110, "total_steps": 246, "loss": 0.5101, "lr": 5e-06, "epoch": 1.338391502276176, "percentage": 44.72, "elapsed_time": "0:44:59", "remaining_time": "0:55:37"}
13
- {"current_steps": 120, "total_steps": 246, "loss": 0.5086, "lr": 5e-06, "epoch": 1.4597875569044005, "percentage": 48.78, "elapsed_time": "0:48:52", "remaining_time": "0:51:19"}
14
- {"current_steps": 130, "total_steps": 246, "loss": 0.4991, "lr": 5e-06, "epoch": 1.5811836115326252, "percentage": 52.85, "elapsed_time": "0:52:45", "remaining_time": "0:47:04"}
15
- {"current_steps": 140, "total_steps": 246, "loss": 0.4973, "lr": 5e-06, "epoch": 1.7025796661608497, "percentage": 56.91, "elapsed_time": "0:56:38", "remaining_time": "0:42:53"}
16
- {"current_steps": 150, "total_steps": 246, "loss": 0.501, "lr": 5e-06, "epoch": 1.8239757207890743, "percentage": 60.98, "elapsed_time": "1:00:35", "remaining_time": "0:38:46"}
17
- {"current_steps": 160, "total_steps": 246, "loss": 0.4963, "lr": 5e-06, "epoch": 1.945371775417299, "percentage": 65.04, "elapsed_time": "1:04:29", "remaining_time": "0:34:39"}
18
- {"current_steps": 164, "total_steps": 246, "eval_loss": 0.5243988037109375, "epoch": 1.9939301972685888, "percentage": 66.67, "elapsed_time": "1:06:39", "remaining_time": "0:33:19"}
19
- {"current_steps": 170, "total_steps": 246, "loss": 0.5178, "lr": 5e-06, "epoch": 2.069802731411229, "percentage": 69.11, "elapsed_time": "1:10:34", "remaining_time": "0:31:33"}
20
- {"current_steps": 180, "total_steps": 246, "loss": 0.4477, "lr": 5e-06, "epoch": 2.191198786039454, "percentage": 73.17, "elapsed_time": "1:14:27", "remaining_time": "0:27:18"}
21
- {"current_steps": 190, "total_steps": 246, "loss": 0.4478, "lr": 5e-06, "epoch": 2.3125948406676784, "percentage": 77.24, "elapsed_time": "1:18:20", "remaining_time": "0:23:05"}
22
- {"current_steps": 200, "total_steps": 246, "loss": 0.45, "lr": 5e-06, "epoch": 2.433990895295903, "percentage": 81.3, "elapsed_time": "1:22:13", "remaining_time": "0:18:54"}
23
- {"current_steps": 210, "total_steps": 246, "loss": 0.4474, "lr": 5e-06, "epoch": 2.5553869499241273, "percentage": 85.37, "elapsed_time": "1:26:06", "remaining_time": "0:14:45"}
24
- {"current_steps": 220, "total_steps": 246, "loss": 0.4493, "lr": 5e-06, "epoch": 2.676783004552352, "percentage": 89.43, "elapsed_time": "1:30:01", "remaining_time": "0:10:38"}
25
- {"current_steps": 230, "total_steps": 246, "loss": 0.4476, "lr": 5e-06, "epoch": 2.7981790591805766, "percentage": 93.5, "elapsed_time": "1:33:54", "remaining_time": "0:06:31"}
26
- {"current_steps": 240, "total_steps": 246, "loss": 0.4507, "lr": 5e-06, "epoch": 2.919575113808801, "percentage": 97.56, "elapsed_time": "1:37:47", "remaining_time": "0:02:26"}
 
1
+ {"current_steps": 10, "total_steps": 246, "loss": 0.775, "lr": 5e-06, "epoch": 0.12139605462822459, "percentage": 4.07, "elapsed_time": "0:04:01", "remaining_time": "1:34:54"}
2
+ {"current_steps": 20, "total_steps": 246, "loss": 0.6633, "lr": 5e-06, "epoch": 0.24279210925644917, "percentage": 8.13, "elapsed_time": "0:08:01", "remaining_time": "1:30:37"}
3
+ {"current_steps": 30, "total_steps": 246, "loss": 0.6218, "lr": 5e-06, "epoch": 0.36418816388467373, "percentage": 12.2, "elapsed_time": "0:12:02", "remaining_time": "1:26:41"}
4
+ {"current_steps": 40, "total_steps": 246, "loss": 0.6021, "lr": 5e-06, "epoch": 0.48558421851289835, "percentage": 16.26, "elapsed_time": "0:16:03", "remaining_time": "1:22:40"}
5
+ {"current_steps": 50, "total_steps": 246, "loss": 0.5861, "lr": 5e-06, "epoch": 0.6069802731411229, "percentage": 20.33, "elapsed_time": "0:20:03", "remaining_time": "1:18:37"}
6
+ {"current_steps": 60, "total_steps": 246, "loss": 0.575, "lr": 5e-06, "epoch": 0.7283763277693475, "percentage": 24.39, "elapsed_time": "0:24:03", "remaining_time": "1:14:35"}
7
+ {"current_steps": 70, "total_steps": 246, "loss": 0.5628, "lr": 5e-06, "epoch": 0.849772382397572, "percentage": 28.46, "elapsed_time": "0:28:04", "remaining_time": "1:10:34"}
8
+ {"current_steps": 80, "total_steps": 246, "loss": 0.5574, "lr": 5e-06, "epoch": 0.9711684370257967, "percentage": 32.52, "elapsed_time": "0:32:03", "remaining_time": "1:06:31"}
9
+ {"current_steps": 82, "total_steps": 246, "eval_loss": 0.5473940372467041, "epoch": 0.9954476479514416, "percentage": 33.33, "elapsed_time": "0:33:26", "remaining_time": "1:06:53"}
10
+ {"current_steps": 90, "total_steps": 246, "loss": 0.5738, "lr": 5e-06, "epoch": 1.095599393019727, "percentage": 36.59, "elapsed_time": "0:38:18", "remaining_time": "1:06:24"}
11
+ {"current_steps": 100, "total_steps": 246, "loss": 0.51, "lr": 5e-06, "epoch": 1.2169954476479514, "percentage": 40.65, "elapsed_time": "0:42:17", "remaining_time": "1:01:45"}
12
+ {"current_steps": 110, "total_steps": 246, "loss": 0.5103, "lr": 5e-06, "epoch": 1.338391502276176, "percentage": 44.72, "elapsed_time": "0:46:18", "remaining_time": "0:57:15"}
13
+ {"current_steps": 120, "total_steps": 246, "loss": 0.5091, "lr": 5e-06, "epoch": 1.4597875569044005, "percentage": 48.78, "elapsed_time": "0:50:18", "remaining_time": "0:52:49"}
14
+ {"current_steps": 130, "total_steps": 246, "loss": 0.4993, "lr": 5e-06, "epoch": 1.5811836115326252, "percentage": 52.85, "elapsed_time": "0:54:18", "remaining_time": "0:48:27"}
15
+ {"current_steps": 140, "total_steps": 246, "loss": 0.4977, "lr": 5e-06, "epoch": 1.7025796661608497, "percentage": 56.91, "elapsed_time": "0:58:17", "remaining_time": "0:44:08"}
16
+ {"current_steps": 150, "total_steps": 246, "loss": 0.5013, "lr": 5e-06, "epoch": 1.8239757207890743, "percentage": 60.98, "elapsed_time": "1:02:16", "remaining_time": "0:39:51"}
17
+ {"current_steps": 160, "total_steps": 246, "loss": 0.4967, "lr": 5e-06, "epoch": 1.945371775417299, "percentage": 65.04, "elapsed_time": "1:06:17", "remaining_time": "0:35:38"}
 
 
 
 
 
 
 
 
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:816a1b3bdec6adc49f6de19850ad2ab6ce54d635da2a4d919d6d14df15ac2646
3
  size 7224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3bcdb0cafad7d25eda78003ba92ecc4fafa5b4bba0964f9c6f6a341b2cd5682
3
  size 7224