Hugging Face's logo

scottsuk0306
/
easylm-helpsteer-rm-gemma-2-9b-it

Safetensors
gemma2
easylm
alignment-handbook
trl
reward-trainer
Generated from Trainer
Eval Results
Model card Files Community
scottsuk0306 commited on
Commit
b7ea48e
•
1 Parent(s): b35bd5e

Model save

Browse files
Files changed (4) hide show
  1. README.md +58 -0
  2. all_results.json +9 -0
  3. train_results.json +9 -0
  4. trainer_state.json +98 -0
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: gemma
3
+ base_model: google/gemma-2-9b-it
4
+ tags:
5
+ - trl
6
+ - reward-trainer
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: easylm-helpsteer-rm-gemma-2-9b-it
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # easylm-helpsteer-rm-gemma-2-9b-it
17
+
18
+ This model is a fine-tuned version of [google/gemma-2-9b-it](https://huggingface.co/google/gemma-2-9b-it) on an unknown dataset.
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 2e-05
38
+ - train_batch_size: 1
39
+ - eval_batch_size: 1
40
+ - seed: 42
41
+ - distributed_type: multi-GPU
42
+ - num_devices: 8
43
+ - total_train_batch_size: 8
44
+ - total_eval_batch_size: 8
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine
47
+ - num_epochs: 1
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - Transformers 4.43.3
56
+ - Pytorch 2.4.0+cu121
57
+ - Datasets 2.20.0
58
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.678250733167115,
5
+ "train_runtime": 2802.1852,
6
+ "train_samples": 6550,
7
+ "train_samples_per_second": 2.337,
8
+ "train_steps_per_second": 0.292
9
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "total_flos": 0.0,
4
+ "train_loss": 0.678250733167115,
5
+ "train_runtime": 2802.1852,
6
+ "train_samples": 6550,
7
+ "train_samples_per_second": 2.337,
8
+ "train_steps_per_second": 0.292
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,98 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 1000,
6
+ "global_step": 819,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.1221001221001221,
13
+ "grad_norm": 1.2653954029083252,
14
+ "learning_rate": 1.9273274812612557e-05,
15
+ "loss": 0.7694,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.2442002442002442,
20
+ "grad_norm": 2.224886417388916,
21
+ "learning_rate": 1.7198725150046886e-05,
22
+ "loss": 0.6902,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.3663003663003663,
27
+ "grad_norm": 2.236462354660034,
28
+ "learning_rate": 1.4077876510757502e-05,
29
+ "loss": 0.682,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.4884004884004884,
34
+ "grad_norm": 3.3600499629974365,
35
+ "learning_rate": 1.0364328757183504e-05,
36
+ "loss": 0.6664,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.6105006105006106,
41
+ "grad_norm": 3.620539426803589,
42
+ "learning_rate": 6.597827626742537e-06,
43
+ "loss": 0.6666,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 0.7326007326007326,
48
+ "grad_norm": 2.775991916656494,
49
+ "learning_rate": 3.325815367397557e-06,
50
+ "loss": 0.6593,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 0.8547008547008547,
55
+ "grad_norm": 3.9067025184631348,
56
+ "learning_rate": 1.0238627236098619e-06,
57
+ "loss": 0.6638,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 0.9768009768009768,
62
+ "grad_norm": 2.6926493644714355,
63
+ "learning_rate": 2.654708866217548e-08,
64
+ "loss": 0.6488,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 1.0,
69
+ "step": 819,
70
+ "total_flos": 0.0,
71
+ "train_loss": 0.678250733167115,
72
+ "train_runtime": 2802.1852,
73
+ "train_samples_per_second": 2.337,
74
+ "train_steps_per_second": 0.292
75
+ }
76
+ ],
77
+ "logging_steps": 100,
78
+ "max_steps": 819,
79
+ "num_input_tokens_seen": 0,
80
+ "num_train_epochs": 1,
81
+ "save_steps": 500,
82
+ "stateful_callbacks": {
83
+ "TrainerControl": {
84
+ "args": {
85
+ "should_epoch_stop": false,
86
+ "should_evaluate": false,
87
+ "should_log": false,
88
+ "should_save": true,
89
+ "should_training_stop": true
90
+ },
91
+ "attributes": {}
92
+ }
93
+ },
94
+ "total_flos": 0.0,
95
+ "train_batch_size": 1,
96
+ "trial_name": null,
97
+ "trial_params": null
98
+ }