Hugging Face's logo

DrishtiSharma
/
llama-2-chat-gptq-english-quotes-test-lora-alpha-16

TensorBoard
Model card Files Metrics Community
DrishtiSharma commited on
Commit
a132199
•
1 Parent(s): 0acefdb

Upload folder using huggingface_hub

Browse files
Files changed (15) hide show
  1. checkpoint-500/README.md +27 -0
  2. checkpoint-500/adapter_config.json +23 -0
  3. checkpoint-500/adapter_model.bin +3 -0
  4. checkpoint-500/optimizer.pt +3 -0
  5. checkpoint-500/rng_state.pth +3 -0
  6. checkpoint-500/scheduler.pt +3 -0
  7. checkpoint-500/trainer_state.json +18 -0
  8. checkpoint-500/training_args.bin +3 -0
  9. runs/Sep13_21-16-45_b04c78a5e2b1/events.out.tfevents.1694639806.b04c78a5e2b1.723.0 +3 -0
  10. runs/Sep13_21-19-02_b04c78a5e2b1/events.out.tfevents.1694639943.b04c78a5e2b1.5549.0 +3 -0
  11. runs/Sep13_21-22-11_b04c78a5e2b1/events.out.tfevents.1694640132.b04c78a5e2b1.5549.1 +3 -0
  12. runs/Sep13_21-23-09_b04c78a5e2b1/events.out.tfevents.1694640189.b04c78a5e2b1.6813.0 +3 -0
  13. runs/Sep13_21-30-53_b04c78a5e2b1/events.out.tfevents.1694640653.b04c78a5e2b1.8924.0 +3 -0
  14. runs/Sep13_21-40-28_b04c78a5e2b1/events.out.tfevents.1694641228.b04c78a5e2b1.11505.0 +3 -0
  15. runs/Sep13_21-42-45_b04c78a5e2b1/events.out.tfevents.1694641365.b04c78a5e2b1.12272.0 +3 -0
checkpoint-500/README.md ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: gptq
9
+ - bits: 4
10
+ - tokenizer: None
11
+ - dataset: None
12
+ - group_size: 128
13
+ - damp_percent: 0.01
14
+ - desc_act: False
15
+ - sym: True
16
+ - true_sequential: True
17
+ - use_cuda_fp16: False
18
+ - model_seqlen: None
19
+ - block_name_to_quantize: None
20
+ - module_name_preceding_first_block: None
21
+ - batch_size: 1
22
+ - pad_token_id: None
23
+ - disable_exllama: True
24
+ ### Framework versions
25
+
26
+
27
+ - PEFT 0.5.0
checkpoint-500/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "TheBloke/Llama-2-7b-Chat-GPTQ",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "k_proj",
18
+ "o_proj",
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-500/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c7451b995bfe9350610c624a2f89e9dee085ce2d8b7abfabbf631815e2fb1a
3
+ size 33646413
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:774cad98d0d38ffa9250377b57c466017faa962a552893d80900a84f444ca92a
3
+ size 67259845
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a96d8cb2dc19b877b7f6b77e9146065542979479699d9292b595ece4f5ae13a
3
+ size 14575
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aca4bc1103f34868d9bf2a4d0332b82cb43f74c39d8828ced8a54bd609e4dab8
3
+ size 627
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.24925224327018944,
5
+ "eval_steps": 800,
6
+ "global_step": 500,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 800,
12
+ "max_steps": 2400,
13
+ "num_train_epochs": 2,
14
+ "save_steps": 500,
15
+ "total_flos": 21776429260800.0,
16
+ "trial_name": null,
17
+ "trial_params": null
18
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26222bca74034b96f46df793570ab3358c1e63077abf7a6fb8549b5a0e2f4bfa
3
+ size 3963
runs/Sep13_21-16-45_b04c78a5e2b1/events.out.tfevents.1694639806.b04c78a5e2b1.723.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:755e73b4cc8a6b8f791f4e5128b195150d99b9346121d839b4496ebc695e86f5
3
+ size 4184
runs/Sep13_21-19-02_b04c78a5e2b1/events.out.tfevents.1694639943.b04c78a5e2b1.5549.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33d1239ad6b2d11019e807b6b60d8cfddf205390edfdde123d47fb7a650b6ca4
3
+ size 4552
runs/Sep13_21-22-11_b04c78a5e2b1/events.out.tfevents.1694640132.b04c78a5e2b1.5549.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed71c6c08d707010d4640840563a0a807c3788e880aeb7bc1380b6b732bd5bb
3
+ size 4552
runs/Sep13_21-23-09_b04c78a5e2b1/events.out.tfevents.1694640189.b04c78a5e2b1.6813.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:466dff0d1ad258b285329301a51424bbdce494e6efd379dd76f646ba88827a37
3
+ size 4980
runs/Sep13_21-30-53_b04c78a5e2b1/events.out.tfevents.1694640653.b04c78a5e2b1.8924.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd4b462e7f8befa893ff76ca8f3d399467a8de5048f1c6a7a1710fa834b2caf6
3
+ size 6146
runs/Sep13_21-40-28_b04c78a5e2b1/events.out.tfevents.1694641228.b04c78a5e2b1.11505.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:200fb0a9c2239679ae940390ea255a533bfcac30f417cbfea4d96f79f96af49a
3
+ size 5123
runs/Sep13_21-42-45_b04c78a5e2b1/events.out.tfevents.1694641365.b04c78a5e2b1.12272.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b339f77be757ab5df966921391cec056512992e311ee188487b733c5ed92dc66
3
+ size 6997