sedrickkeh commited on
Commit
3d461f7
·
verified ·
1 Parent(s): cbff7d7

End of training

Browse files
README.md CHANGED
@@ -4,6 +4,7 @@ license: llama3.1
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
 
7
  - generated_from_trainer
8
  model-index:
9
  - name: stackexchange_opensource
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # stackexchange_opensource
17
 
18
- This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
  - Loss: 0.9941
21
 
 
4
  base_model: meta-llama/Meta-Llama-3.1-8B
5
  tags:
6
  - llama-factory
7
+ - full
8
  - generated_from_trainer
9
  model-index:
10
  - name: stackexchange_opensource
 
16
 
17
  # stackexchange_opensource
18
 
19
+ This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/stackexchange_opensource dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 0.9941
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9310344827586206,
3
+ "eval_loss": 0.9940618276596069,
4
+ "eval_runtime": 5.8474,
5
+ "eval_samples_per_second": 33.006,
6
+ "eval_steps_per_second": 0.684,
7
+ "total_flos": 34966402498560.0,
8
+ "train_loss": 1.1650703861599876,
9
+ "train_runtime": 999.8758,
10
+ "train_samples_per_second": 10.972,
11
+ "train_steps_per_second": 0.021
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9310344827586206,
3
+ "eval_loss": 0.9940618276596069,
4
+ "eval_runtime": 5.8474,
5
+ "eval_samples_per_second": 33.006,
6
+ "eval_steps_per_second": 0.684
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.9310344827586206,
3
+ "total_flos": 34966402498560.0,
4
+ "train_loss": 1.1650703861599876,
5
+ "train_runtime": 999.8758,
6
+ "train_samples_per_second": 10.972,
7
+ "train_steps_per_second": 0.021
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,80 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.9310344827586206,
5
+ "eval_steps": 500,
6
+ "global_step": 21,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.9655172413793104,
13
+ "eval_loss": 1.096757173538208,
14
+ "eval_runtime": 6.7816,
15
+ "eval_samples_per_second": 28.459,
16
+ "eval_steps_per_second": 0.59,
17
+ "step": 7
18
+ },
19
+ {
20
+ "epoch": 1.396551724137931,
21
+ "grad_norm": 2.9408685872324747,
22
+ "learning_rate": 5e-06,
23
+ "loss": 1.2507,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 1.9482758620689655,
28
+ "eval_loss": 1.0302181243896484,
29
+ "eval_runtime": 6.5287,
30
+ "eval_samples_per_second": 29.562,
31
+ "eval_steps_per_second": 0.613,
32
+ "step": 14
33
+ },
34
+ {
35
+ "epoch": 2.793103448275862,
36
+ "grad_norm": 3.329244747809881,
37
+ "learning_rate": 5e-06,
38
+ "loss": 1.0989,
39
+ "step": 20
40
+ },
41
+ {
42
+ "epoch": 2.9310344827586206,
43
+ "eval_loss": 0.9940618276596069,
44
+ "eval_runtime": 5.3751,
45
+ "eval_samples_per_second": 35.907,
46
+ "eval_steps_per_second": 0.744,
47
+ "step": 21
48
+ },
49
+ {
50
+ "epoch": 2.9310344827586206,
51
+ "step": 21,
52
+ "total_flos": 34966402498560.0,
53
+ "train_loss": 1.1650703861599876,
54
+ "train_runtime": 999.8758,
55
+ "train_samples_per_second": 10.972,
56
+ "train_steps_per_second": 0.021
57
+ }
58
+ ],
59
+ "logging_steps": 10,
60
+ "max_steps": 21,
61
+ "num_input_tokens_seen": 0,
62
+ "num_train_epochs": 3,
63
+ "save_steps": 500,
64
+ "stateful_callbacks": {
65
+ "TrainerControl": {
66
+ "args": {
67
+ "should_epoch_stop": false,
68
+ "should_evaluate": false,
69
+ "should_log": false,
70
+ "should_save": true,
71
+ "should_training_stop": true
72
+ },
73
+ "attributes": {}
74
+ }
75
+ },
76
+ "total_flos": 34966402498560.0,
77
+ "train_batch_size": 8,
78
+ "trial_name": null,
79
+ "trial_params": null
80
+ }
training_eval_loss.png ADDED
training_loss.png ADDED