Hugging Face's logo

NobodyExistsOnTheInternet
/
PuffedLIMA13bQLORA

Model card Files
xet
 Community
1
NobodyExistsOnTheInternet commited on
Commit
eb0bfef
·
1 Parent(s): a2afe1e

Training in progress, epoch 3, checkpoint

Browse files
Files changed (11) hide show
  1. checkpoint-11862/README.md +21 -0
  2. checkpoint-11862/adapter_config.json +29 -0
  3. checkpoint-11862/adapter_model.bin +3 -0
  4. checkpoint-11862/adapter_model/README.md +21 -0
  5. checkpoint-11862/adapter_model/adapter_config.json +29 -0
  6. checkpoint-11862/adapter_model/adapter_model.bin +3 -0
  7. checkpoint-11862/optimizer.pt +3 -0
  8. checkpoint-11862/rng_state.pth +3 -0
  9. checkpoint-11862/scheduler.pt +3 -0
  10. checkpoint-11862/trainer_state.json +0 -0
  11. checkpoint-11862/training_args.bin +3 -0
checkpoint-11862/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: True
10
+ - load_in_4bit: False
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.6.0.dev0
checkpoint-11862/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 256,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": [
13
+ "embed_tokens",
14
+ "lm_head"
15
+ ],
16
+ "peft_type": "LORA",
17
+ "r": 128,
18
+ "revision": null,
19
+ "target_modules": [
20
+ "v_proj",
21
+ "down_proj",
22
+ "up_proj",
23
+ "q_proj",
24
+ "k_proj",
25
+ "gate_proj",
26
+ "o_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM"
29
+ }
checkpoint-11862/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c163ee950ef13965057da5b94bf691e9403c24f8ea8371b55a932b9e9e3383
3
+ size 2658342933
checkpoint-11862/adapter_model/README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: True
10
+ - load_in_4bit: False
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: fp4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float32
18
+ ### Framework versions
19
+
20
+
21
+ - PEFT 0.6.0.dev0
checkpoint-11862/adapter_model/adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": null,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 256,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": [
13
+ "embed_tokens",
14
+ "lm_head"
15
+ ],
16
+ "peft_type": "LORA",
17
+ "r": 128,
18
+ "revision": null,
19
+ "target_modules": [
20
+ "v_proj",
21
+ "down_proj",
22
+ "up_proj",
23
+ "q_proj",
24
+ "k_proj",
25
+ "gate_proj",
26
+ "o_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM"
29
+ }
checkpoint-11862/adapter_model/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56c163ee950ef13965057da5b94bf691e9403c24f8ea8371b55a932b9e9e3383
3
+ size 2658342933
checkpoint-11862/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701877ad61a043d86ad104e8705ef97af705d78da34c4f860d0fe1574d8a9723
3
+ size 1660660519
checkpoint-11862/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eedf1af49bf20134138c4d0573bd79dbc91fef766de9f0939960585094f7154f
3
+ size 14575
checkpoint-11862/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ec8a5f34bc66f43fe478d878f44f2f158e23a1c7025b4c6e2d28849e76e8b4f
3
+ size 627
checkpoint-11862/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-11862/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d82a66905172b90a96d88f770b828581b344f2b3131016353d3bf3052a1d9691
3
+ size 4283