thenlpresearcher commited on
Commit
7597815
·
verified ·
1 Parent(s): 46da46e

End of training

Browse files
README.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: mistralai/Mistral-7B-v0.3
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: mistral_sequence_classification
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # mistral_sequence_classification
16
+
17
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.2667
20
+ - Pearson: 0.9704
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0001
40
+ - train_batch_size: 32
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - num_epochs: 5
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss | Pearson |
50
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
51
+ | No log | 1.0 | 206 | 0.3305 | 0.9028 |
52
+ | No log | 2.0 | 412 | 0.2609 | 0.9532 |
53
+ | 0.4868 | 3.0 | 618 | 0.2432 | 0.9611 |
54
+ | 0.4868 | 4.0 | 824 | 0.2611 | 0.9639 |
55
+ | 0.0417 | 5.0 | 1030 | 0.2667 | 0.9704 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - PEFT 0.14.0
61
+ - Transformers 4.45.2
62
+ - Pytorch 2.4.0a0+f70bd71a48.nv24.06
63
+ - Datasets 3.2.0
64
+ - Tokenizers 0.20.3
adapter_config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
5
+ "bias": "none",
6
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 16,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.05,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": [
21
+ "classifier",
22
+ "score"
23
+ ],
24
+ "peft_type": "LORA",
25
+ "r": 64,
26
+ "rank_pattern": {},
27
+ "revision": null,
28
+ "target_modules": [
29
+ "q_proj",
30
+ "v_proj",
31
+ "o_proj",
32
+ "k_proj"
33
+ ],
34
+ "task_type": "SEQ_CLS",
35
+ "use_dora": false,
36
+ "use_rslora": false
37
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6269f2ea8b7e459750a2c271665b6bad832e0b0d3fc4084a26d26ad24d7a28a6
3
+ size 218220600
runs/Feb06_10-22-02_e38d418088f5/events.out.tfevents.1738837323.e38d418088f5.80606.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5436be6497c1d9d92829edb3f17db7e99b9f6064e7036b5d23cee65107292b3a
3
+ size 5706
runs/Feb06_10-23-46_e38d418088f5/events.out.tfevents.1738837430.e38d418088f5.80985.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbc1b671467eb08e26f5ed3f77e80a0bb7c7b508b281587db54d2200872daa13
3
+ size 8092
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
trainer_state.json ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.24322812259197235,
3
+ "best_model_checkpoint": "mistral_sequence_classification/checkpoint-618",
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 1030,
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_loss": 0.3304608464241028,
14
+ "eval_pearson": 0.9027747531908439,
15
+ "eval_runtime": 15.8259,
16
+ "eval_samples_per_second": 58.891,
17
+ "eval_steps_per_second": 7.393,
18
+ "step": 206
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_loss": 0.2608998417854309,
23
+ "eval_pearson": 0.9531635605038489,
24
+ "eval_runtime": 15.7775,
25
+ "eval_samples_per_second": 59.071,
26
+ "eval_steps_per_second": 7.416,
27
+ "step": 412
28
+ },
29
+ {
30
+ "epoch": 2.4271844660194173,
31
+ "grad_norm": 21.120954513549805,
32
+ "learning_rate": 5.145631067961165e-05,
33
+ "loss": 0.4868,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_loss": 0.24322812259197235,
39
+ "eval_pearson": 0.961136250737733,
40
+ "eval_runtime": 15.732,
41
+ "eval_samples_per_second": 59.242,
42
+ "eval_steps_per_second": 7.437,
43
+ "step": 618
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_loss": 0.26112988591194153,
48
+ "eval_pearson": 0.9639457727475045,
49
+ "eval_runtime": 15.8547,
50
+ "eval_samples_per_second": 58.784,
51
+ "eval_steps_per_second": 7.38,
52
+ "step": 824
53
+ },
54
+ {
55
+ "epoch": 4.854368932038835,
56
+ "grad_norm": 0.005307361483573914,
57
+ "learning_rate": 2.912621359223301e-06,
58
+ "loss": 0.0417,
59
+ "step": 1000
60
+ },
61
+ {
62
+ "epoch": 5.0,
63
+ "eval_loss": 0.2666521966457367,
64
+ "eval_pearson": 0.9703769235281202,
65
+ "eval_runtime": 15.6636,
66
+ "eval_samples_per_second": 59.501,
67
+ "eval_steps_per_second": 7.47,
68
+ "step": 1030
69
+ },
70
+ {
71
+ "epoch": 5.0,
72
+ "step": 1030,
73
+ "total_flos": 6.321458643082445e+16,
74
+ "train_loss": 0.2567840828768258,
75
+ "train_runtime": 1141.9471,
76
+ "train_samples_per_second": 28.745,
77
+ "train_steps_per_second": 0.902
78
+ }
79
+ ],
80
+ "logging_steps": 500,
81
+ "max_steps": 1030,
82
+ "num_input_tokens_seen": 0,
83
+ "num_train_epochs": 5,
84
+ "save_steps": 500,
85
+ "stateful_callbacks": {
86
+ "TrainerControl": {
87
+ "args": {
88
+ "should_epoch_stop": false,
89
+ "should_evaluate": false,
90
+ "should_log": false,
91
+ "should_save": true,
92
+ "should_training_stop": true
93
+ },
94
+ "attributes": {}
95
+ }
96
+ },
97
+ "total_flos": 6.321458643082445e+16,
98
+ "train_batch_size": 32,
99
+ "trial_name": null,
100
+ "trial_params": null
101
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85bb051bb15730e29fa95904009fe6bb5c0ca34a62b2d544bbafe6024bd57a92
3
+ size 5240