r4victor commited on
Commit
2e39c8c
1 Parent(s): 7fde4b7

End of training

Browse files
README.md CHANGED
@@ -2,12 +2,13 @@
2
  license: gemma
3
  library_name: peft
4
  tags:
 
5
  - trl
6
  - sft
7
  - generated_from_trainer
8
  base_model: google/gemma-7b
9
  datasets:
10
- - generator
11
  model-index:
12
  - name: gemma-7b-sft-qlora-no-robots
13
  results: []
@@ -18,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # gemma-7b-sft-qlora-no-robots
20
 
21
- This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
22
  It achieves the following results on the evaluation set:
23
  - Loss: 7.4575
24
 
 
2
  license: gemma
3
  library_name: peft
4
  tags:
5
+ - alignment-handbook
6
  - trl
7
  - sft
8
  - generated_from_trainer
9
  base_model: google/gemma-7b
10
  datasets:
11
+ - sayakpaul/no_robots_only_coding
12
  model-index:
13
  - name: gemma-7b-sft-qlora-no-robots
14
  results: []
 
19
 
20
  # gemma-7b-sft-qlora-no-robots
21
 
22
+ This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the sayakpaul/no_robots_only_coding dataset.
23
  It achieves the following results on the evaluation set:
24
  - Loss: 7.4575
25
 
all_results.json CHANGED
@@ -1,5 +1,10 @@
1
  {
2
  "epoch": 1.0,
 
 
 
 
 
3
  "train_loss": 12.472952842712402,
4
  "train_runtime": 44.3036,
5
  "train_samples": 334,
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 7.457533836364746,
4
+ "eval_runtime": 2.5006,
5
+ "eval_samples": 16,
6
+ "eval_samples_per_second": 0.8,
7
+ "eval_steps_per_second": 0.4,
8
  "train_loss": 12.472952842712402,
9
  "train_runtime": 44.3036,
10
  "train_samples": 334,
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/gemma-7b",
3
+ "architectures": [
4
+ "GemmaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 2,
9
+ "eos_token_id": 1,
10
+ "head_dim": 256,
11
+ "hidden_act": "gelu",
12
+ "hidden_size": 3072,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 24576,
15
+ "max_position_embeddings": 8192,
16
+ "model_type": "gemma",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 28,
19
+ "num_key_value_heads": 16,
20
+ "pad_token_id": 0,
21
+ "quantization_config": {
22
+ "_load_in_4bit": true,
23
+ "_load_in_8bit": false,
24
+ "bnb_4bit_compute_dtype": "bfloat16",
25
+ "bnb_4bit_quant_type": "nf4",
26
+ "bnb_4bit_use_double_quant": false,
27
+ "llm_int8_enable_fp32_cpu_offload": false,
28
+ "llm_int8_has_fp16_weight": false,
29
+ "llm_int8_skip_modules": null,
30
+ "llm_int8_threshold": 6.0,
31
+ "load_in_4bit": true,
32
+ "load_in_8bit": false,
33
+ "quant_method": "bitsandbytes"
34
+ },
35
+ "rms_norm_eps": 1e-06,
36
+ "rope_scaling": null,
37
+ "rope_theta": 10000.0,
38
+ "torch_dtype": "bfloat16",
39
+ "transformers_version": "4.39.0.dev0",
40
+ "use_cache": true,
41
+ "vocab_size": 256000
42
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_loss": 7.457533836364746,
4
+ "eval_runtime": 2.5006,
5
+ "eval_samples": 16,
6
+ "eval_samples_per_second": 0.8,
7
+ "eval_steps_per_second": 0.4
8
+ }
runs/Apr10_06-09-49_main-tall-pug-1-0-0/events.out.tfevents.1712743973.main-tall-pug-1-0-0.459.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b91eaa0c3ca5f41b60d78bdeddebb1c6c65eb9a416a7caf1a26947f6dc77c1cf
3
+ size 354