Hugging Face's logo

wangrongsheng
/
CareLlama1-7b-merge

PEFT
Model card Files Community
wangrongsheng commited on
Commit
8da6a42
·
1 Parent(s): 4798fca

commit from root

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. all_results.json +7 -0
  5. checkpoint-10000/README.md +9 -0
  6. checkpoint-10000/adapter_config.json +21 -0
  7. checkpoint-10000/adapter_model.bin +3 -0
  8. checkpoint-10000/finetuning_args.json +16 -0
  9. checkpoint-10000/optimizer.pt +3 -0
  10. checkpoint-10000/rng_state_0.pth +3 -0
  11. checkpoint-10000/rng_state_1.pth +3 -0
  12. checkpoint-10000/scheduler.pt +3 -0
  13. checkpoint-10000/trainer_state.json +0 -0
  14. checkpoint-10000/training_args.bin +3 -0
  15. checkpoint-12000/README.md +9 -0
  16. checkpoint-12000/adapter_config.json +21 -0
  17. checkpoint-12000/adapter_model.bin +3 -0
  18. checkpoint-12000/finetuning_args.json +16 -0
  19. checkpoint-12000/optimizer.pt +3 -0
  20. checkpoint-12000/rng_state_0.pth +3 -0
  21. checkpoint-12000/rng_state_1.pth +3 -0
  22. checkpoint-12000/scheduler.pt +3 -0
  23. checkpoint-12000/trainer_state.json +0 -0
  24. checkpoint-12000/training_args.bin +3 -0
  25. checkpoint-14000/README.md +9 -0
  26. checkpoint-14000/adapter_config.json +21 -0
  27. checkpoint-14000/adapter_model.bin +3 -0
  28. checkpoint-14000/finetuning_args.json +16 -0
  29. checkpoint-14000/optimizer.pt +3 -0
  30. checkpoint-14000/rng_state_0.pth +3 -0
  31. checkpoint-14000/rng_state_1.pth +3 -0
  32. checkpoint-14000/scheduler.pt +3 -0
  33. checkpoint-14000/trainer_state.json +0 -0
  34. checkpoint-14000/training_args.bin +3 -0
  35. checkpoint-16000/README.md +9 -0
  36. checkpoint-16000/adapter_config.json +21 -0
  37. checkpoint-16000/adapter_model.bin +3 -0
  38. checkpoint-16000/finetuning_args.json +16 -0
  39. checkpoint-16000/optimizer.pt +3 -0
  40. checkpoint-16000/rng_state_0.pth +3 -0
  41. checkpoint-16000/rng_state_1.pth +3 -0
  42. checkpoint-16000/scheduler.pt +3 -0
  43. checkpoint-16000/trainer_state.json +0 -0
  44. checkpoint-16000/training_args.bin +3 -0
  45. checkpoint-18000/README.md +9 -0
  46. checkpoint-18000/adapter_config.json +21 -0
  47. checkpoint-18000/adapter_model.bin +3 -0
  48. checkpoint-18000/finetuning_args.json +16 -0
  49. checkpoint-18000/optimizer.pt +3 -0
  50. checkpoint-18000/rng_state_0.pth +3 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "./Llama-7b-hf",
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": 32.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c47efc2da37962c2e2c3e668b18cb51018acdba97a711616f7d12d903d10a52
3
+ size 16821197
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.0,
3
+ "train_loss": 0.8193962926164442,
4
+ "train_runtime": 109363.8797,
5
+ "train_samples_per_second": 5.396,
6
+ "train_steps_per_second": 0.169
7
+ }
checkpoint-10000/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
checkpoint-10000/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "./Llama-7b-hf",
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": 32.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-10000/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56790a51e98f188dac51d41e0ee5b95a9f619339203a04b9ee1a7c20d0d1504c
3
+ size 16821197
checkpoint-10000/finetuning_args.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dpo_beta": 0.1,
3
+ "finetuning_type": "lora",
4
+ "lora_alpha": 32.0,
5
+ "lora_dropout": 0.1,
6
+ "lora_rank": 8,
7
+ "lora_target": [
8
+ "q_proj",
9
+ "v_proj"
10
+ ],
11
+ "name_module_trainable": "mlp",
12
+ "num_hidden_layers": 32,
13
+ "num_layer_trainable": 3,
14
+ "ppo_score_norm": false,
15
+ "resume_lora_training": true
16
+ }
checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42dc40b805db4393dd5d3aa7599f863e82bfd249630f17ec9ce09b0c51996c7d
3
+ size 33661637
checkpoint-10000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79a16bfb9c9bcb34b5abed2ce3c3280867d416274f0b9f4a8bf36d643319939e
3
+ size 18679
checkpoint-10000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a802fa1f8f23309864196b1451c666b11bab32611bffbb65d9925eb9d9849c8c
3
+ size 18679
checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc70af0644baa5e36bbad69272f75abc66332d6eac71e4aa747692258b3e0ed2
3
+ size 627
checkpoint-10000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9a38169c643b6bd0f6c56bed04a340b58cfeb76b0d8c476c64814c3a99294d
3
+ size 3265
checkpoint-12000/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
checkpoint-12000/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "./Llama-7b-hf",
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": 32.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-12000/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef85ee8ac4f0def7684714243abafe8b9be4b61bd46b59f9f30add78b179822
3
+ size 16821197
checkpoint-12000/finetuning_args.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dpo_beta": 0.1,
3
+ "finetuning_type": "lora",
4
+ "lora_alpha": 32.0,
5
+ "lora_dropout": 0.1,
6
+ "lora_rank": 8,
7
+ "lora_target": [
8
+ "q_proj",
9
+ "v_proj"
10
+ ],
11
+ "name_module_trainable": "mlp",
12
+ "num_hidden_layers": 32,
13
+ "num_layer_trainable": 3,
14
+ "ppo_score_norm": false,
15
+ "resume_lora_training": true
16
+ }
checkpoint-12000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d0199b60ddf7d8ef492b46e5744397aed2455644365881929085748e0f20e2b
3
+ size 33661637
checkpoint-12000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4965604d207d9fe3999e236c36f90a04ee1ab793a328449abdb0a1a8e2d4fef5
3
+ size 18679
checkpoint-12000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13ec63287d8c04b0f4c4d2384dde9464d6b8cbc06991d9e975ba7a54a3ee434a
3
+ size 18679
checkpoint-12000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3fa99ee9aae1e6144180f834472b6e0cee6a580e576913ddaca9fc3442d703c
3
+ size 627
checkpoint-12000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-12000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9a38169c643b6bd0f6c56bed04a340b58cfeb76b0d8c476c64814c3a99294d
3
+ size 3265
checkpoint-14000/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
checkpoint-14000/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "./Llama-7b-hf",
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": 32.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-14000/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:401c3662d939e997d9c16df31212b255c0b61349236473501aa6f6dca55cd433
3
+ size 16821197
checkpoint-14000/finetuning_args.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dpo_beta": 0.1,
3
+ "finetuning_type": "lora",
4
+ "lora_alpha": 32.0,
5
+ "lora_dropout": 0.1,
6
+ "lora_rank": 8,
7
+ "lora_target": [
8
+ "q_proj",
9
+ "v_proj"
10
+ ],
11
+ "name_module_trainable": "mlp",
12
+ "num_hidden_layers": 32,
13
+ "num_layer_trainable": 3,
14
+ "ppo_score_norm": false,
15
+ "resume_lora_training": true
16
+ }
checkpoint-14000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f56dca3375a86aef334f39885b92deae4a858bda604579cf341c9da88b9084
3
+ size 33661637
checkpoint-14000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56b20e8e6cef897f2e148ae83243613c0589f0f314083d8a6be877560d3fc342
3
+ size 18679
checkpoint-14000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:082dc0a8d1164db7db6d1fda49bb6dc4d38799700cbe87f7c193fe02c12867a9
3
+ size 18679
checkpoint-14000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6646157982872387477142f26ae5b14d4925ad61b3cc8e22ced66048ddcb307
3
+ size 627
checkpoint-14000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9a38169c643b6bd0f6c56bed04a340b58cfeb76b0d8c476c64814c3a99294d
3
+ size 3265
checkpoint-16000/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
checkpoint-16000/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "./Llama-7b-hf",
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": 32.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-16000/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff47f2af715601921b2afd0677ee1a4f541c850e2531ffccd68b4365207f3ad9
3
+ size 16821197
checkpoint-16000/finetuning_args.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dpo_beta": 0.1,
3
+ "finetuning_type": "lora",
4
+ "lora_alpha": 32.0,
5
+ "lora_dropout": 0.1,
6
+ "lora_rank": 8,
7
+ "lora_target": [
8
+ "q_proj",
9
+ "v_proj"
10
+ ],
11
+ "name_module_trainable": "mlp",
12
+ "num_hidden_layers": 32,
13
+ "num_layer_trainable": 3,
14
+ "ppo_score_norm": false,
15
+ "resume_lora_training": true
16
+ }
checkpoint-16000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2579de472b784c52bc708e32df0bb2a2ad8ee1128757e08ddbaf4a66bbcd8315
3
+ size 33661637
checkpoint-16000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34b9700738aa559215442c5d96f8f7052bc5ed48ba735377259ea8bad69622e1
3
+ size 18679
checkpoint-16000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d007c3dad6a45bcc022890c3c1d9086dd00132db58915e54dcb0f4a879b68ae
3
+ size 18679
checkpoint-16000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28e29c97fad50596cb2eec21f5e1698f71e304ef0ea831c3a4cc5203c177bdd1
3
+ size 627
checkpoint-16000/trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-16000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b9a38169c643b6bd0f6c56bed04a340b58cfeb76b0d8c476c64814c3a99294d
3
+ size 3265
checkpoint-18000/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
checkpoint-18000/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "./Llama-7b-hf",
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": 32.0,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-18000/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4f6e9d95e19180f123e7c34e5bda68fd979f722d341641bfe4ae523251c26c8
3
+ size 16821197
checkpoint-18000/finetuning_args.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "dpo_beta": 0.1,
3
+ "finetuning_type": "lora",
4
+ "lora_alpha": 32.0,
5
+ "lora_dropout": 0.1,
6
+ "lora_rank": 8,
7
+ "lora_target": [
8
+ "q_proj",
9
+ "v_proj"
10
+ ],
11
+ "name_module_trainable": "mlp",
12
+ "num_hidden_layers": 32,
13
+ "num_layer_trainable": 3,
14
+ "ppo_score_norm": false,
15
+ "resume_lora_training": true
16
+ }
checkpoint-18000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6116d0eb9a4f3b04c058f4182731997461acf8057e984f15f1915b2e36851b09
3
+ size 33661637
checkpoint-18000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2362b74b5851fe6980b77eb8aa389e1244a8ebab5acef7af119780a7f7887c9f
3
+ size 18679