ZeroUniqueness commited on
Commit
c42280a
1 Parent(s): be488e4

Training in progress, step 400

Browse files
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15e3346b176d6fcd29f1030224d15a9659a7886dfde431254b0c2c482f7f12ee
3
  size 500897101
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2c8c652ceb91eadfbf67d32090cb9a34334c3412448c51b0e46ba33e9d0a53
3
  size 500897101
checkpoint-400/README.md ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: True
16
+ - bnb_4bit_compute_dtype: bfloat16
17
+ ### Framework versions
18
+
19
+
20
+ - PEFT 0.5.0.dev0
checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
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": 16,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 32,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "up_proj",
19
+ "gate_proj",
20
+ "k_proj",
21
+ "down_proj",
22
+ "o_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM"
26
+ }
checkpoint-400/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de2c8c652ceb91eadfbf67d32090cb9a34334c3412448c51b0e46ba33e9d0a53
3
+ size 500897101
checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cb58ed2829a0fabde0c3bf1dc245ad84334041ed18a961f1eeb21bf93129fd8
3
+ size 1001737021
checkpoint-400/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9131bc870cac3189b167b638d4dbc0ee80374a6faac82c3587d19bf85fcdee16
3
+ size 27772
checkpoint-400/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef92d5e279737363f4c68efdbe993477a275650160f241edfb04b532547afe42
3
+ size 27772
checkpoint-400/rng_state_10.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bdba2aa6de1fa9f48073e8f31a09c5c053e6b4da845d048cb72b1c8800a118
3
+ size 27789
checkpoint-400/rng_state_11.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743f80dd731663223d4f00901ff3349a3044216b052f46488405ea125a3903f1
3
+ size 27789
checkpoint-400/rng_state_12.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5af6d551aad67d98abf32394790611d835014060a2a31ab20d21469701ce9019
3
+ size 27789
checkpoint-400/rng_state_13.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:970037ffc7aab6ce9f60138f7107accf43ebc87d2ac3f24f6dcdfecf3408df47
3
+ size 27789
checkpoint-400/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c7379a917a02406dd5047a443259b8ca44eae99f9775863277ba1b857280b7d
3
+ size 27772
checkpoint-400/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77eca0a08b8c05ec8552138ddf6cd29fa370a4a9f8ba8402f34c5299dc126b22
3
+ size 27772
checkpoint-400/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:413d4535fee1926347b9f1257faf06685b951de4665e40327e5d48ed4bb9d7b9
3
+ size 27772
checkpoint-400/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973f09149d072982dd98c7501515ed1f40a2705cd75b7a2131ab15bb1a5225c9
3
+ size 27772
checkpoint-400/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dda8dbc3d3bfb454a1070f4898ea3d332e92ac177175e72ae6267c5d048079d
3
+ size 27772
checkpoint-400/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79c1a3a32acbe008362193a3e99b9fc15c9837adf3a81beccacbaf4c35975342
3
+ size 27772
checkpoint-400/rng_state_8.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d2b2ab68c44d59d853f9c86c488abd76ce697dae7289cfd7c3c71eb1e5476a
3
+ size 27772
checkpoint-400/rng_state_9.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4d03141ba9483e191ff283149aa4ff01a6b3d4525dbd3ff4a080d94a3aa4639
3
+ size 27772
checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b200bf94e090388e19457e61e5dc10f4bbbee568d22b1db4e6b2f28c0739166b
3
+ size 627
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.15509887553315238,
5
+ "global_step": 400,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 0.0001999867761371633,
13
+ "loss": 1.0435,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 0.00019993306018843102,
19
+ "loss": 0.8918,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 0.06,
24
+ "learning_rate": 0.00019983804784290833,
25
+ "loss": 0.8874,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 0.08,
30
+ "learning_rate": 0.00019970177836355307,
31
+ "loss": 0.8839,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 0.1,
36
+ "learning_rate": 0.00019952430806244534,
37
+ "loss": 0.8777,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 0.12,
42
+ "learning_rate": 0.00019930571027751713,
43
+ "loss": 0.8753,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 0.14,
48
+ "learning_rate": 0.00019904607534224612,
49
+ "loss": 0.8749,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 0.16,
54
+ "learning_rate": 0.00019874551054832625,
55
+ "loss": 0.8711,
56
+ "step": 400
57
+ }
58
+ ],
59
+ "max_steps": 7737,
60
+ "num_train_epochs": 3,
61
+ "total_flos": 1.7210263980359025e+18,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7d8e6ca3ee52d610ea6af580762703958acb68894884ff8627b9a467240686f
3
+ size 4027