xshubhamx commited on
Commit
735e2dc
·
verified ·
1 Parent(s): 59690a3

Upload folder using huggingface_hub

Browse files
training_checkpoints/checkpoint-160/README.md ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: False
10
+ - _load_in_4bit: True
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: nf4
16
+ - bnb_4bit_use_double_quant: True
17
+ - bnb_4bit_compute_dtype: bfloat16
18
+ - bnb_4bit_quant_storage: uint8
19
+ - load_in_4bit: True
20
+ - load_in_8bit: False
21
+ ### Framework versions
22
+
23
+
24
+ - PEFT 0.4.0
training_checkpoints/checkpoint-160/adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
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": 64,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "gate_proj",
18
+ "q_proj",
19
+ "o_proj",
20
+ "k_proj",
21
+ "down_proj",
22
+ "up_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "SEQ_CLS"
26
+ }
training_checkpoints/checkpoint-160/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15662a76c458ab12b58631fe057751665e6764094aec72ab55d5cf3fbe0e694e
3
+ size 50626520
training_checkpoints/checkpoint-160/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f85e4f11f20c51376c1bc2b20cae42c26d43df9f312748c5de2b7618c6427d8b
3
+ size 101430714
training_checkpoints/checkpoint-160/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:782ff81e55ac932af9390332440858fb38c33185531ff2fe17a66b505e0cb757
3
+ size 14244
training_checkpoints/checkpoint-160/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7729f419e9bf44f315c2cf204824acf82bd88549d3e597acb20fea7b86e9fed6
3
+ size 1064
training_checkpoints/checkpoint-160/special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
training_checkpoints/checkpoint-160/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
training_checkpoints/checkpoint-160/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
training_checkpoints/checkpoint-160/tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_checkpoints/checkpoint-160/trainer_state.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.602571869042318,
3
+ "best_model_checkpoint": "tiny-llama/checkpoint-160",
4
+ "epoch": 0.995334370139969,
5
+ "eval_steps": 500,
6
+ "global_step": 160,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.7869868319132456,
14
+ "eval_f1_macro": 0.602571869042318,
15
+ "eval_f1_micro": 0.7869868319132455,
16
+ "eval_f1_weighted": 0.7752313093692699,
17
+ "eval_loss": 0.6672300100326538,
18
+ "eval_macro_fpr": 0.019618845690595806,
19
+ "eval_macro_sensitivity": 0.6223339304749645,
20
+ "eval_macro_specificity": 0.9839698388016963,
21
+ "eval_precision": 0.7799565431301605,
22
+ "eval_precision_macro": 0.6206625059288113,
23
+ "eval_recall": 0.7869868319132456,
24
+ "eval_recall_macro": 0.6223339304749645,
25
+ "eval_runtime": 1156.4947,
26
+ "eval_samples_per_second": 1.116,
27
+ "eval_steps_per_second": 0.14,
28
+ "eval_weighted_fpr": 0.018966825298296436,
29
+ "eval_weighted_sensitivity": 0.7869868319132456,
30
+ "eval_weighted_specificity": 0.9725607501121987,
31
+ "step": 160
32
+ }
33
+ ],
34
+ "logging_steps": 500,
35
+ "max_steps": 1600,
36
+ "num_input_tokens_seen": 0,
37
+ "num_train_epochs": 10,
38
+ "save_steps": 500,
39
+ "total_flos": 6.197742432524698e+16,
40
+ "train_batch_size": 8,
41
+ "trial_name": null,
42
+ "trial_params": null
43
+ }
training_checkpoints/checkpoint-160/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97fafdba41732eab6f8b05f79e51dec541f05fd3118d1ff77580870456d60693
3
+ size 4920