EtashGuha commited on
Commit
9e56cb6
·
verified ·
1 Parent(s): 48778da

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: llama3-1_8b_mlfoundations-dev-stackexchange_poker
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # llama3-1_8b_mlfoundations-dev-stackexchange_poker
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: 1.1535
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: llama3-1_8b_mlfoundations-dev-stackexchange_poker
 
16
 
17
  # llama3-1_8b_mlfoundations-dev-stackexchange_poker
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_poker dataset.
20
  It achieves the following results on the evaluation set:
21
  - Loss: 1.1535
22
 
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.2857142857142856,
3
+ "eval_loss": 1.153542399406433,
4
+ "eval_runtime": 12.2762,
5
+ "eval_samples_per_second": 8.553,
6
+ "eval_steps_per_second": 0.326,
7
+ "total_flos": 14970645381120.0,
8
+ "train_loss": 1.2536535263061523,
9
+ "train_runtime": 1609.5914,
10
+ "train_samples_per_second": 3.711,
11
+ "train_steps_per_second": 0.006
12
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.2857142857142856,
3
+ "eval_loss": 1.153542399406433,
4
+ "eval_runtime": 12.2762,
5
+ "eval_samples_per_second": 8.553,
6
+ "eval_steps_per_second": 0.326
7
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.2857142857142856,
3
+ "total_flos": 14970645381120.0,
4
+ "train_loss": 1.2536535263061523,
5
+ "train_runtime": 1609.5914,
6
+ "train_samples_per_second": 3.711,
7
+ "train_steps_per_second": 0.006
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.2857142857142856,
5
+ "eval_steps": 500,
6
+ "global_step": 9,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7619047619047619,
13
+ "eval_loss": 1.2543432712554932,
14
+ "eval_runtime": 12.2168,
15
+ "eval_samples_per_second": 8.595,
16
+ "eval_steps_per_second": 0.327,
17
+ "step": 3
18
+ },
19
+ {
20
+ "epoch": 1.7777777777777777,
21
+ "eval_loss": 1.1833806037902832,
22
+ "eval_runtime": 12.3175,
23
+ "eval_samples_per_second": 8.524,
24
+ "eval_steps_per_second": 0.325,
25
+ "step": 7
26
+ },
27
+ {
28
+ "epoch": 2.2857142857142856,
29
+ "eval_loss": 1.153542399406433,
30
+ "eval_runtime": 12.9628,
31
+ "eval_samples_per_second": 8.1,
32
+ "eval_steps_per_second": 0.309,
33
+ "step": 9
34
+ },
35
+ {
36
+ "epoch": 2.2857142857142856,
37
+ "step": 9,
38
+ "total_flos": 14970645381120.0,
39
+ "train_loss": 1.2536535263061523,
40
+ "train_runtime": 1609.5914,
41
+ "train_samples_per_second": 3.711,
42
+ "train_steps_per_second": 0.006
43
+ }
44
+ ],
45
+ "logging_steps": 10,
46
+ "max_steps": 9,
47
+ "num_input_tokens_seen": 0,
48
+ "num_train_epochs": 3,
49
+ "save_steps": 500,
50
+ "stateful_callbacks": {
51
+ "TrainerControl": {
52
+ "args": {
53
+ "should_epoch_stop": false,
54
+ "should_evaluate": false,
55
+ "should_log": false,
56
+ "should_save": true,
57
+ "should_training_stop": true
58
+ },
59
+ "attributes": {}
60
+ }
61
+ },
62
+ "total_flos": 14970645381120.0,
63
+ "train_batch_size": 8,
64
+ "trial_name": null,
65
+ "trial_params": null
66
+ }
training_eval_loss.png ADDED