lillian039 commited on
Commit
3a3124e
1 Parent(s): 3bdd32d

End of training

Browse files
README.md CHANGED
@@ -1,8 +1,11 @@
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
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # barc-llama3.1-8b-instruct-lora64-induction-gpt4mini20k_lr2e-4_epoch3
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: 0.3327
22
 
 
1
  ---
2
  base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
3
+ datasets:
4
+ - barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3
5
  library_name: peft
6
  license: llama3.1
7
  tags:
8
+ - alignment-handbook
9
  - trl
10
  - sft
11
  - generated_from_trainer
 
19
 
20
  # barc-llama3.1-8b-instruct-lora64-induction-gpt4mini20k_lr2e-4_epoch3
21
 
22
+ 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 the barc0/induction_100k_gpt4o-mini_generated_problems_seed100.jsonl_messages_format_0.3 dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: 0.3327
25
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 3.0,
 
 
 
 
 
3
  "total_flos": 1.6172409563591475e+17,
4
  "train_loss": 0.366262159849468,
5
  "train_runtime": 5417.5508,
 
1
  {
2
  "epoch": 3.0,
3
+ "eval_loss": 0.3327427804470062,
4
+ "eval_runtime": 158.2222,
5
+ "eval_samples": 5105,
6
+ "eval_samples_per_second": 32.265,
7
+ "eval_steps_per_second": 1.011,
8
  "total_flos": 1.6172409563591475e+17,
9
  "train_loss": 0.366262159849468,
10
  "train_runtime": 5417.5508,
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": [
10
+ 128001,
11
+ 128008,
12
+ 128009
13
+ ],
14
+ "head_dim": 128,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 4096,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 14336,
19
+ "max_position_embeddings": 131072,
20
+ "mlp_bias": false,
21
+ "model_type": "llama",
22
+ "num_attention_heads": 32,
23
+ "num_hidden_layers": 32,
24
+ "num_key_value_heads": 8,
25
+ "pretraining_tp": 1,
26
+ "rms_norm_eps": 1e-05,
27
+ "rope_scaling": {
28
+ "factor": 8.0,
29
+ "high_freq_factor": 4.0,
30
+ "low_freq_factor": 1.0,
31
+ "original_max_position_embeddings": 8192,
32
+ "rope_type": "llama3"
33
+ },
34
+ "rope_theta": 500000.0,
35
+ "tie_word_embeddings": false,
36
+ "torch_dtype": "bfloat16",
37
+ "transformers_version": "4.45.0.dev0",
38
+ "use_cache": true,
39
+ "vocab_size": 128256
40
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_loss": 0.3327427804470062,
4
+ "eval_runtime": 158.2222,
5
+ "eval_samples": 5105,
6
+ "eval_samples_per_second": 32.265,
7
+ "eval_steps_per_second": 1.011
8
+ }
runs/Sep27_09-24-28_instance-20240925-140811/events.out.tfevents.1727434844.instance-20240925-140811.12579.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3312bd90b9ae3c3dc8c49b7132bb2699953d6473d13857e0f5766f997b05e85
3
+ size 359