SoyGema commited on
Commit
5eacd8c
1 Parent(s): b9846c6

End of training

Browse files
README.md CHANGED
@@ -1,13 +1,31 @@
1
  ---
 
 
 
2
  license: apache-2.0
3
  base_model: t5-small
4
  tags:
5
  - generated_from_trainer
6
  datasets:
7
  - opus100
 
 
8
  model-index:
9
  - name: english-georgian
10
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +33,11 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  # english-georgian
17
 
18
- This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus100 dataset.
 
 
 
 
19
 
20
  ## Model description
21
 
 
1
  ---
2
+ language:
3
+ - en
4
+ - ka
5
  license: apache-2.0
6
  base_model: t5-small
7
  tags:
8
  - generated_from_trainer
9
  datasets:
10
  - opus100
11
+ metrics:
12
+ - bleu
13
  model-index:
14
  - name: english-georgian
15
+ results:
16
+ - task:
17
+ name: Translation
18
+ type: translation
19
+ dataset:
20
+ name: opus100 en-ka
21
+ type: opus100
22
+ config: en-ka
23
+ split: validation
24
+ args: en-ka
25
+ metrics:
26
+ - name: Bleu
27
+ type: bleu
28
+ value: 44.7969
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  # english-georgian
35
 
36
+ This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus100 en-ka dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.2662
39
+ - Bleu: 44.7969
40
+ - Gen Len: 22.625
41
 
42
  ## Model description
43
 
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_bleu": 44.7969,
4
+ "eval_gen_len": 22.625,
5
+ "eval_loss": 0.26616597175598145,
6
+ "eval_runtime": 122.1534,
7
+ "eval_samples": 32,
8
+ "eval_samples_per_second": 0.262,
9
+ "eval_steps_per_second": 0.065,
10
+ "train_loss": 0.3655550269614728,
11
+ "train_runtime": 1226.4853,
12
+ "train_samples": 5896,
13
+ "train_samples_per_second": 14.422,
14
+ "train_steps_per_second": 3.605
15
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_bleu": 44.7969,
4
+ "eval_gen_len": 22.625,
5
+ "eval_loss": 0.26616597175598145,
6
+ "eval_runtime": 122.1534,
7
+ "eval_samples": 32,
8
+ "eval_samples_per_second": 0.262,
9
+ "eval_steps_per_second": 0.065
10
+ }
generation_config.json CHANGED
@@ -1,5 +1,4 @@
1
  {
2
- "_from_model_config": true,
3
  "decoder_start_token_id": 0,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
 
1
  {
 
2
  "decoder_start_token_id": 0,
3
  "eos_token_id": 1,
4
  "pad_token_id": 0,
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.3655550269614728,
4
+ "train_runtime": 1226.4853,
5
+ "train_samples": 5896,
6
+ "train_samples_per_second": 14.422,
7
+ "train_steps_per_second": 3.605
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 4422,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.34,
13
+ "learning_rate": 4.434644957033017e-05,
14
+ "loss": 0.484,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.68,
19
+ "learning_rate": 3.869289914066034e-05,
20
+ "loss": 0.4117,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 1.02,
25
+ "learning_rate": 3.30393487109905e-05,
26
+ "loss": 0.3563,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 1.36,
31
+ "learning_rate": 2.7385798281320668e-05,
32
+ "loss": 0.365,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 1.7,
37
+ "learning_rate": 2.173224785165084e-05,
38
+ "loss": 0.3432,
39
+ "step": 2500
40
+ },
41
+ {
42
+ "epoch": 2.04,
43
+ "learning_rate": 1.6078697421981004e-05,
44
+ "loss": 0.3333,
45
+ "step": 3000
46
+ },
47
+ {
48
+ "epoch": 2.37,
49
+ "learning_rate": 1.0425146992311172e-05,
50
+ "loss": 0.3353,
51
+ "step": 3500
52
+ },
53
+ {
54
+ "epoch": 2.71,
55
+ "learning_rate": 4.771596562641339e-06,
56
+ "loss": 0.3278,
57
+ "step": 4000
58
+ },
59
+ {
60
+ "epoch": 3.0,
61
+ "step": 4422,
62
+ "total_flos": 109498918895616.0,
63
+ "train_loss": 0.3655550269614728,
64
+ "train_runtime": 1226.4853,
65
+ "train_samples_per_second": 14.422,
66
+ "train_steps_per_second": 3.605
67
+ }
68
+ ],
69
+ "logging_steps": 500,
70
+ "max_steps": 4422,
71
+ "num_train_epochs": 3,
72
+ "save_steps": 500,
73
+ "total_flos": 109498918895616.0,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }