Hugging Face's logo

CharlesLi
/
llama_2_llama_2_code_math_1_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
e54fdea
·
verified ·
1 Parent(s): 0de48b3

Model save

Browse files
Files changed (9) hide show
  1. README.md +0 -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_14-49-13_dgx-a100-16/events.out.tfevents.1737380977.dgx-a100-16.3124001.0 +3 -0
  8. train_results.json +4 -4
  9. training_args.bin +1 -1
README.md CHANGED
@@ -3,10 +3,6 @@ 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
  - alignment-handbook
@@ -24,8 +20,6 @@ should probably proofread and complete it, then remove this comment. -->
24
  # llama_2_llama_2_code_math_1_full
25
 
26
  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.
27
- It achieves the following results on the evaluation set:
28
- - Loss: 0.8364
29
 
30
  ## Model description
31
 
 
3
  license: llama2
4
  base_model: meta-llama/Llama-2-7b-chat-hf
5
  tags:
 
 
 
 
6
  - trl
7
  - sft
8
  - alignment-handbook
 
20
  # llama_2_llama_2_code_math_1_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": 5.836,
7
  "eval_steps_per_second": 1.459,
8
  "total_flos": 575794053120.0,
9
- "train_loss": 1.0960698922475178,
10
- "train_runtime": 34.0457,
11
  "train_samples": 980,
12
- "train_samples_per_second": 5.258,
13
- "train_steps_per_second": 0.176
14
  }
 
6
  "eval_samples_per_second": 5.836,
7
  "eval_steps_per_second": 1.459,
8
  "total_flos": 575794053120.0,
9
+ "train_loss": 1.0954708258310955,
10
+ "train_runtime": 34.3617,
11
  "train_samples": 980,
12
+ "train_samples_per_second": 5.209,
13
+ "train_steps_per_second": 0.175
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 sha256:819e163277818f837be67b0ca5371f67f9bdc40c72cbbef488f5f1587ac10438
3
  size 4938985352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f61228634b760449cda8df947d1c3696c0440efdbfff8def0323747fc07e5d9a
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:cbd9eb9b978034b2c156bd0c0e7f1358c875906789ae33b6ac99655aa3d4bc10
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e2bc95035c92b128e21f162cb47f4eb65af4dc51154fd58155524e1505ae77f
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:b9d05e0b592d83ab2e12e42ff5cdfd298aec89600228285aadd93b9f807feb33
3
  size 3590488816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5021f2be1d34cd3b4469b715880db2adbc166aae4afc389fa6b626eba6a7b29a
3
  size 3590488816
runs/Jan20_14-49-13_dgx-a100-16/events.out.tfevents.1737380977.dgx-a100-16.3124001.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5877c07864bdff937704b1131b5a5f97057813f6a413ea4de478d583ff66475
3
+ size 6232
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 575794053120.0,
4
- "train_loss": 1.0960698922475178,
5
- "train_runtime": 34.0457,
6
  "train_samples": 980,
7
- "train_samples_per_second": 5.258,
8
- "train_steps_per_second": 0.176
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 575794053120.0,
4
+ "train_loss": 1.0954708258310955,
5
+ "train_runtime": 34.3617,
6
  "train_samples": 980,
7
+ "train_samples_per_second": 5.209,
8
+ "train_steps_per_second": 0.175
9
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:164efc751f2409ac9ed9b510aa917133c06dea1384c94c3842604d6ce9cbe0c1
3
  size 7032
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:608403a0596032c58f44512a90baa45b2af6a4f83aa3afaf3440439c75c5a6e5
3
  size 7032