Hugging Face's logo

BluebrainAI
/
duo-predict-gpt2-medium-wikitext

Feature Extraction
Transformers
Safetensors
duo-predict-gpt2
Generated from Trainer
custom_code
Model card Files
xet
Community
shivanandmn commited on
Commit
2cab8fe
·
verified ·
1 Parent(s): 9b295f1

Training in progress, step 5

Browse files
Files changed (6) hide show
  1. all_results.json +17 -0
  2. eval_results.json +12 -0
  3. model.safetensors +1 -1
  4. train_results.json +8 -0
  5. trainer_state.json +51 -0
  6. training_args.bin +1 -1
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.027886497064579255,
4
+ "eval_bleu": 0.0021463467173750564,
5
+ "eval_loss": 8.901089668273926,
6
+ "eval_perplexity": 7339.967312596559,
7
+ "eval_runtime": 2.9365,
8
+ "eval_samples": 4,
9
+ "eval_samples_per_second": 1.362,
10
+ "eval_steps_per_second": 0.341,
11
+ "perplexity": 7339.967312596559,
12
+ "total_flos": 37111750410240.0,
13
+ "train_loss": 19.501985168457033,
14
+ "train_runtime": 33.6762,
15
+ "train_samples_per_second": 0.594,
16
+ "train_steps_per_second": 0.148
17
+ }
eval_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_accuracy": 0.027886497064579255,
4
+ "eval_bleu": 0.0021463467173750564,
5
+ "eval_loss": 8.901089668273926,
6
+ "eval_perplexity": 7339.967312596559,
7
+ "eval_runtime": 2.9365,
8
+ "eval_samples": 4,
9
+ "eval_samples_per_second": 1.362,
10
+ "eval_steps_per_second": 0.341,
11
+ "perplexity": 7339.967312596559
12
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c787492475b899e7fe3a221eb40378e352502642def6d74997b5a1809dc3103
3
  size 1417229824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27bc8eb3b15560df54abe40fea156b75b88024ad128c5613eced7289e6007698
3
  size 1417229824
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "total_flos": 37111750410240.0,
4
+ "train_loss": 19.501985168457033,
5
+ "train_runtime": 33.6762,
6
+ "train_samples_per_second": 0.594,
7
+ "train_steps_per_second": 0.148
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 5.0,
13
+ "step": 5,
14
+ "total_flos": 37111750410240.0,
15
+ "train_loss": 19.501985168457033,
16
+ "train_runtime": 33.6762,
17
+ "train_samples_per_second": 0.594,
18
+ "train_steps_per_second": 0.148
19
+ }
20
+ ],
21
+ "logging_steps": 100,
22
+ "max_steps": 5,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "stateful_callbacks": {
27
+ "EarlyStoppingCallback": {
28
+ "args": {
29
+ "early_stopping_patience": 2,
30
+ "early_stopping_threshold": 0.0
31
+ },
32
+ "attributes": {
33
+ "early_stopping_patience_counter": 0
34
+ }
35
+ },
36
+ "TrainerControl": {
37
+ "args": {
38
+ "should_epoch_stop": false,
39
+ "should_evaluate": false,
40
+ "should_log": false,
41
+ "should_save": true,
42
+ "should_training_stop": true
43
+ },
44
+ "attributes": {}
45
+ }
46
+ },
47
+ "total_flos": 37111750410240.0,
48
+ "train_batch_size": 8,
49
+ "trial_name": null,
50
+ "trial_params": null
51
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27c7796c9953530c71ff11a3b7d839277449cb339116cc009145de4a012fac0f
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cbf4e022680dd32fb89b366b15405b4a72821c9a060d5074735c6b62ff171bd
3
  size 5496