Hugging Face's logo

rayane-donni
/
zephyr-7b-sft-qlora

PEFT
Safetensors
mistral
alignment-handbook
trl
sft
Generated from Trainer
Model card Files
xet
Community
rayane-donni commited on
Commit
c3a5a0b
·
verified ·
1 Parent(s): 5653ec5

Model save

Browse files
Files changed (7) hide show
  1. README.md +1 -0
  2. adapter_config.json +4 -4
  3. all_results.json +3 -3
  4. config.json +26 -0
  5. train_results.json +3 -3
  6. trainer_state.json +3 -3
  7. training_args.bin +1 -1
README.md CHANGED
@@ -4,6 +4,7 @@ library_name: peft
4
  tags:
5
  - trl
6
  - sft
 
7
  - generated_from_trainer
8
  base_model: mistralai/Mistral-7B-v0.1
9
  datasets:
 
4
  tags:
5
  - trl
6
  - sft
7
+ - alignment-handbook
8
  - generated_from_trainer
9
  base_model: mistralai/Mistral-7B-v0.1
10
  datasets:
adapter_config.json CHANGED
@@ -19,12 +19,12 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "down_proj",
23
- "v_proj",
24
  "o_proj",
25
- "k_proj",
26
- "up_proj",
27
  "q_proj",
 
 
 
 
28
  "gate_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "o_proj",
 
 
23
  "q_proj",
24
+ "up_proj",
25
+ "v_proj",
26
+ "k_proj",
27
+ "down_proj",
28
  "gate_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.17,
3
  "train_loss": 0.0,
4
- "train_runtime": 1.4575,
5
  "train_samples": 41573,
6
- "train_samples_per_second": 38212.736,
7
- "train_steps_per_second": 1193.805
8
  }
 
1
  {
2
  "epoch": 0.17,
3
  "train_loss": 0.0,
4
+ "train_runtime": 1.4131,
5
  "train_samples": 41573,
6
+ "train_samples_per_second": 39413.236,
7
+ "train_steps_per_second": 1231.31
8
  }
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistralai/Mistral-7B-v0.1",
3
+ "architectures": [
4
+ "MistralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 4096,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 14336,
13
+ "max_position_embeddings": 32768,
14
+ "model_type": "mistral",
15
+ "num_attention_heads": 32,
16
+ "num_hidden_layers": 32,
17
+ "num_key_value_heads": 8,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_theta": 10000.0,
20
+ "sliding_window": 4096,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "bfloat16",
23
+ "transformers_version": "4.39.3",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.17,
3
  "train_loss": 0.0,
4
- "train_runtime": 1.4575,
5
  "train_samples": 41573,
6
- "train_samples_per_second": 38212.736,
7
- "train_steps_per_second": 1193.805
8
  }
 
1
  {
2
  "epoch": 0.17,
3
  "train_loss": 0.0,
4
+ "train_runtime": 1.4131,
5
  "train_samples": 41573,
6
+ "train_samples_per_second": 39413.236,
7
+ "train_steps_per_second": 1231.31
8
  }
trainer_state.json CHANGED
@@ -4080,9 +4080,9 @@
4080
  "step": 2900,
4081
  "total_flos": 2.039075623887962e+18,
4082
  "train_loss": 0.0,
4083
- "train_runtime": 1.4575,
4084
- "train_samples_per_second": 38212.736,
4085
- "train_steps_per_second": 1193.805
4086
  }
4087
  ],
4088
  "logging_steps": 5,
 
4080
  "step": 2900,
4081
  "total_flos": 2.039075623887962e+18,
4082
  "train_loss": 0.0,
4083
+ "train_runtime": 1.4131,
4084
+ "train_samples_per_second": 39413.236,
4085
+ "train_steps_per_second": 1231.31
4086
  }
4087
  ],
4088
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5eb45c194b280bd04907b41b4ed2b7c768f41d327ecea1edc47a9b00ab6f853f
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:862f66d6ef58758d4c90f7ee63aea25b36926fa8fa3c8d0bebf46d19de31eba7
3
  size 5048