Hugging Face's logo

CharlesLi
/
llama_2_llama_2_code_math_0_full

Text Generation
Transformers
TensorBoard
Safetensors
llama
alignment-handbook
trl
sft
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Metrics Community
CharlesLi commited on
Commit
2ef6121
·
verified ·
1 Parent(s): a772bf8

Model save

Browse files
Files changed (9) hide show
  1. README.md +1 -6
  2. all_results.json +4 -4
  3. config.json +1 -1
  4. model-00001-of-00003.safetensors +1 -1
  5. model-00002-of-00003.safetensors +1 -1
  6. model-00003-of-00003.safetensors +1 -1
  7. runs/Jan20_01-24-43_dgx-a100-13/events.out.tfevents.1737333022.dgx-a100-13.1035717.0 +3 -0
  8. train_results.json +4 -4
  9. training_args.bin +1 -1
README.md CHANGED
@@ -3,12 +3,9 @@ library_name: transformers
3
  license: llama2
4
  base_model: meta-llama/Llama-2-7b-chat-hf
5
  tags:
6
- - alignment-handbook
7
- - trl
8
- - sft
9
- - generated_from_trainer
10
  - trl
11
  - sft
 
12
  - generated_from_trainer
13
  datasets:
14
  - generator
@@ -23,8 +20,6 @@ should probably proofread and complete it, then remove this comment. -->
23
  # llama_2_llama_2_code_math_0_full
24
 
25
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
26
- It achieves the following results on the evaluation set:
27
- - Loss: 0.8370
28
 
29
  ## Model description
30
 
 
3
  license: llama2
4
  base_model: meta-llama/Llama-2-7b-chat-hf
5
  tags:
 
 
 
 
6
  - trl
7
  - sft
8
+ - alignment-handbook
9
  - generated_from_trainer
10
  datasets:
11
  - generator
 
20
  # llama_2_llama_2_code_math_0_full
21
 
22
  This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
 
 
23
 
24
  ## Model description
25
 
all_results.json CHANGED
@@ -6,9 +6,9 @@
6
  "eval_samples_per_second": 4.408,
7
  "eval_steps_per_second": 1.469,
8
  "total_flos": 261724569600.0,
9
- "train_loss": 1.2802486419677734,
10
- "train_runtime": 17.9623,
11
  "train_samples": 480,
12
- "train_samples_per_second": 5.066,
13
- "train_steps_per_second": 0.167
14
  }
 
6
  "eval_samples_per_second": 4.408,
7
  "eval_steps_per_second": 1.469,
8
  "total_flos": 261724569600.0,
9
+ "train_loss": 1.2803109486897786,
10
+ "train_runtime": 18.114,
11
  "train_samples": 480,
12
+ "train_samples_per_second": 5.024,
13
+ "train_steps_per_second": 0.166
14
  }
config.json CHANGED
@@ -24,6 +24,6 @@
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.44.2",
27
- "use_cache": true,
28
  "vocab_size": 32000
29
  }
 
24
  "tie_word_embeddings": false,
25
  "torch_dtype": "bfloat16",
26
  "transformers_version": "4.44.2",
27
+ "use_cache": false,
28
  "vocab_size": 32000
29
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5668a1bacc8aadfca5fc8c5e21482abef9fe7e7d5d62d01aac6040db307742a9
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2032025d47c36c049987e9cede3d7749c9568a1d7d9bccf0ca2318dd8e817306
3
  size 4938985352
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3827271aa06a494b0149efcca8b351ea6624349d023359fad542e0a324a5d45b
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:223a5b9e200b0e797bd5f99eddc562df00aab66e35a3fcf63c817ae7fb6649a9
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff9f6cd1885a77bc09560c20d038f05b034438567fac5de47e93ecb804e1089d
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e690e58ffa8f6d4823fa456fa2c5255c19f24aec6702c47f14b266e33caf18c
3
  size 3590488816
runs/Jan20_01-24-43_dgx-a100-13/events.out.tfevents.1737333022.dgx-a100-13.1035717.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:935cd26207052d4d719e50017e0ad02233b2a200fa5bf99390a315a8dbeb0488
3
+ size 6232
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 261724569600.0,
4
- "train_loss": 1.2802486419677734,
5
- "train_runtime": 17.9623,
6
  "train_samples": 480,
7
- "train_samples_per_second": 5.066,
8
- "train_steps_per_second": 0.167
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 261724569600.0,
4
+ "train_loss": 1.2803109486897786,
5
+ "train_runtime": 18.114,
6
  "train_samples": 480,
7
+ "train_samples_per_second": 5.024,
8
+ "train_steps_per_second": 0.166
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f242f2f6e00b4bfc771d571af5181cca9dc88a39bc45d260a27306989dc562e4
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0969ef742d48215d32c6153949ee951e14ef90b433866a6a1b7cafd36217d6
3
  size 7032