Hugging Face's logo

izzcw
/
final_combined_mc_data

Text Generation
Transformers
TensorBoard
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Metrics Community
izzcw commited on
Commit
e779e73
·
verified ·
1 Parent(s): 2e01bb0

End of training

Browse files
Files changed (8) hide show
  1. README.md +3 -2
  2. all_results.json +12 -0
  3. eval_results.json +7 -0
  4. runs/Mar25_06-37-26_cab5dc79-97e2-4af7-8451-ddd879bff597-0/events.out.tfevents.1742886915.cab5dc79-97e2-4af7-8451-ddd879bff597-0.6613.1 +3 -0
  5. train_results.json +8 -0
  6. trainer_state.json +106 -0
  7. training_eval_loss.png +0 -0
  8. training_loss.png +0 -0
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3
4
  base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: final_combined_mc_data
@@ -15,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # final_combined_mc_data
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.7356
21
 
22
  ## Model description
23
 
 
4
  base_model: meta-llama/Meta-Llama-3-8B-Instruct
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: final_combined_mc_data
 
16
 
17
  # final_combined_mc_data
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the identity and the final_combined_mc_data datasets.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.8601
22
 
23
  ## Model description
24
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.955223880597014,
3
+ "eval_loss": 0.8600807189941406,
4
+ "eval_runtime": 1.182,
5
+ "eval_samples_per_second": 18.613,
6
+ "eval_steps_per_second": 2.538,
7
+ "total_flos": 37587570917376.0,
8
+ "train_loss": 0.2476747315376997,
9
+ "train_runtime": 2030.6526,
10
+ "train_samples_per_second": 5.264,
11
+ "train_steps_per_second": 0.039
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.955223880597014,
3
+ "eval_loss": 0.8600807189941406,
4
+ "eval_runtime": 1.182,
5
+ "eval_samples_per_second": 18.613,
6
+ "eval_steps_per_second": 2.538
7
+ }
runs/Mar25_06-37-26_cab5dc79-97e2-4af7-8451-ddd879bff597-0/events.out.tfevents.1742886915.cab5dc79-97e2-4af7-8451-ddd879bff597-0.6613.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c786b30c7468f9d1032c56431bbe5d23328f675d90b5c8a21006085a9bdbcb9d
3
+ size 306
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 8.955223880597014,
3
+ "total_flos": 37587570917376.0,
4
+ "train_loss": 0.2476747315376997,
5
+ "train_runtime": 2030.6526,
6
+ "train_samples_per_second": 5.264,
7
+ "train_steps_per_second": 0.039
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.955223880597014,
5
+ "eval_steps": 50,
6
+ "global_step": 80,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.1194029850746268,
13
+ "grad_norm": 12.171414081678625,
14
+ "learning_rate": 9.980973490458728e-06,
15
+ "loss": 1.0602,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 2.2388059701492535,
20
+ "grad_norm": 5.102956254122534,
21
+ "learning_rate": 9.330127018922195e-06,
22
+ "loss": 0.4908,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 3.3582089552238807,
27
+ "grad_norm": 3.0060478102356094,
28
+ "learning_rate": 7.86788218175523e-06,
29
+ "loss": 0.224,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 4.477611940298507,
34
+ "grad_norm": 2.451051410299596,
35
+ "learning_rate": 5.8682408883346535e-06,
36
+ "loss": 0.1026,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 5.597014925373134,
41
+ "grad_norm": 1.885409477326922,
42
+ "learning_rate": 3.705904774487396e-06,
43
+ "loss": 0.0593,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 5.597014925373134,
48
+ "eval_loss": 0.7355796694755554,
49
+ "eval_runtime": 1.1864,
50
+ "eval_samples_per_second": 18.543,
51
+ "eval_steps_per_second": 2.529,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 6.7164179104477615,
56
+ "grad_norm": 1.2736191437207434,
57
+ "learning_rate": 1.7860619515673034e-06,
58
+ "loss": 0.0265,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 7.835820895522388,
63
+ "grad_norm": 1.2918144398905065,
64
+ "learning_rate": 4.6846106481675035e-07,
65
+ "loss": 0.012,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 8.955223880597014,
70
+ "grad_norm": 0.3695610719057999,
71
+ "learning_rate": 0.0,
72
+ "loss": 0.006,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 8.955223880597014,
77
+ "step": 80,
78
+ "total_flos": 37587570917376.0,
79
+ "train_loss": 0.2476747315376997,
80
+ "train_runtime": 2030.6526,
81
+ "train_samples_per_second": 5.264,
82
+ "train_steps_per_second": 0.039
83
+ }
84
+ ],
85
+ "logging_steps": 10,
86
+ "max_steps": 80,
87
+ "num_input_tokens_seen": 0,
88
+ "num_train_epochs": 10,
89
+ "save_steps": 500,
90
+ "stateful_callbacks": {
91
+ "TrainerControl": {
92
+ "args": {
93
+ "should_epoch_stop": false,
94
+ "should_evaluate": false,
95
+ "should_log": false,
96
+ "should_save": true,
97
+ "should_training_stop": true
98
+ },
99
+ "attributes": {}
100
+ }
101
+ },
102
+ "total_flos": 37587570917376.0,
103
+ "train_batch_size": 1,
104
+ "trial_name": null,
105
+ "trial_params": null
106
+ }
training_eval_loss.png ADDED
training_loss.png ADDED