Hugging Face's logo

hiba2
/
resultsara_5epoch

TensorBoard
Safetensors
mbart
Generated from Trainer
Model card Files Metrics Community
hiba2 commited on
Commit
f2b7fb9
·
verified ·
1 Parent(s): b60df30

End of training

Browse files
Files changed (14) hide show
  1. README.md +70 -0
  2. config.json +59 -0
  3. generation_config.json +12 -0
  4. model.safetensors +3 -0
  5. runs/Sep02_18-14-15_952fa8a340e4/events.out.tfevents.1725300910.952fa8a340e4.1598.0 +3 -0
  6. runs/Sep02_18-14-15_952fa8a340e4/events.out.tfevents.1725301283.952fa8a340e4.1598.1 +3 -0
  7. runs/Sep02_18-32-51_952fa8a340e4/events.out.tfevents.1725301985.952fa8a340e4.1598.2 +3 -0
  8. runs/Sep02_18-32-51_952fa8a340e4/events.out.tfevents.1725302569.952fa8a340e4.1598.3 +3 -0
  9. runs/Sep02_18-32-51_952fa8a340e4/events.out.tfevents.1725302904.952fa8a340e4.1598.4 +3 -0
  10. runs/Sep02_18-32-51_952fa8a340e4/events.out.tfevents.1725303640.952fa8a340e4.1598.5 +3 -0
  11. runs/Sep02_19-05-02_952fa8a340e4/events.out.tfevents.1725303916.952fa8a340e4.1598.6 +3 -0
  12. runs/Sep02_19-27-56_952fa8a340e4/events.out.tfevents.1725305309.952fa8a340e4.1598.7 +3 -0
  13. runs/Sep02_19-28-55_952fa8a340e4/events.out.tfevents.1725305344.952fa8a340e4.1598.8 +3 -0
  14. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: moussaKam/AraBART
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: resultsara_5epoch
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # resultsara_5epoch
15
+
16
+ This model is a fine-tuned version of [moussaKam/AraBART](https://huggingface.co/moussaKam/AraBART) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.6393
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 5e-05
38
+ - train_batch_size: 16
39
+ - eval_batch_size: 16
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: linear
43
+ - num_epochs: 8
44
+ - mixed_precision_training: Native AMP
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:------:|:----:|:---------------:|
50
+ | 0.4457 | 0.1333 | 500 | 0.7199 |
51
+ | 0.8534 | 0.2667 | 1000 | 0.6676 |
52
+ | 0.9825 | 0.4 | 1500 | 0.6572 |
53
+ | 0.9602 | 0.5333 | 2000 | 0.6492 |
54
+ | 0.9685 | 0.6667 | 2500 | 0.6411 |
55
+ | 0.9596 | 0.8 | 3000 | 0.6374 |
56
+ | 0.9561 | 0.9333 | 3500 | 0.6312 |
57
+ | 0.8599 | 1.0667 | 4000 | 0.6394 |
58
+ | 0.7501 | 1.2 | 4500 | 0.6413 |
59
+ | 0.7739 | 1.3333 | 5000 | 0.6376 |
60
+ | 0.7791 | 1.4667 | 5500 | 0.6465 |
61
+ | 0.7911 | 1.6 | 6000 | 0.6414 |
62
+ | 0.7889 | 1.7333 | 6500 | 0.6393 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - Transformers 4.42.4
68
+ - Pytorch 2.4.0+cu121
69
+ - Datasets 2.21.0
70
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "moussaKam/AraBART",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "do_blenderbot_90_layernorm": false,
21
+ "dropout": 0.1,
22
+ "early_stopping": true,
23
+ "encoder_attention_heads": 12,
24
+ "encoder_ffn_dim": 3072,
25
+ "encoder_layerdrop": 0.0,
26
+ "encoder_layers": 6,
27
+ "eos_token_id": 2,
28
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": false,
30
+ "forced_eos_token_id": 2,
31
+ "gradient_checkpointing": false,
32
+ "id2label": {
33
+ "0": "LABEL_0",
34
+ "1": "LABEL_1",
35
+ "2": "LABEL_2"
36
+ },
37
+ "init_std": 0.02,
38
+ "is_encoder_decoder": true,
39
+ "label2id": {
40
+ "LABEL_0": 0,
41
+ "LABEL_1": 1,
42
+ "LABEL_2": 2
43
+ },
44
+ "max_position_embeddings": 1024,
45
+ "model_type": "mbart",
46
+ "no_repeat_ngram_size": 3,
47
+ "normalize_before": true,
48
+ "normalize_embedding": true,
49
+ "num_beams": 4,
50
+ "num_hidden_layers": 6,
51
+ "pad_token_id": 1,
52
+ "scale_embedding": false,
53
+ "static_position_embeddings": false,
54
+ "tokenizer_class": "BarthezTokenizer",
55
+ "torch_dtype": "float32",
56
+ "transformers_version": "4.42.4",
57
+ "use_cache": true,
58
+ "vocab_size": 50002
59
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
+ "no_repeat_ngram_size": 3,
9
+ "num_beams": 4,
10
+ "pad_token_id": 1,
11
+ "transformers_version": "4.42.4"
12
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81d1a010b2bc2dee8679968888f117f574f04cc1f358abe1089563c5d3ec7c42
3
+ size 557116312
runs/Sep02_18-14-15_952fa8a340e4/events.out.tfevents.1725300910.952fa8a340e4.1598.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:471e7795c1f91d2f11b493bdbae988762510716e567c096b67a54f927eb6b6bb
3
+ size 5838
runs/Sep02_18-14-15_952fa8a340e4/events.out.tfevents.1725301283.952fa8a340e4.1598.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55274ca68e673ca89f825117ccd9ce39e6f24c84ad44b1f814fb2064281c5462
3
+ size 34377
runs/Sep02_18-32-51_952fa8a340e4/events.out.tfevents.1725301985.952fa8a340e4.1598.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6aafac7ee647663ecd66d24e984b582b1f67bb6373f50c4e09c073972acaa80
3
+ size 17338
runs/Sep02_18-32-51_952fa8a340e4/events.out.tfevents.1725302569.952fa8a340e4.1598.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a6269a473f915b811261bf86a4c31188b2dd3674bed4df4e7935c8fc679c8ae9
3
+ size 6802
runs/Sep02_18-32-51_952fa8a340e4/events.out.tfevents.1725302904.952fa8a340e4.1598.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60a8b615a5c742b0956796b0555677e57ccb40defe19f2564d0800ee69e28162
3
+ size 23088
runs/Sep02_18-32-51_952fa8a340e4/events.out.tfevents.1725303640.952fa8a340e4.1598.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:134bda34f2f6c84f9fc725881d57c5b73cbb93b9af856102887de44c3bf2f7c0
3
+ size 7073
runs/Sep02_19-05-02_952fa8a340e4/events.out.tfevents.1725303916.952fa8a340e4.1598.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3e1d64c8cb25d4edbdd41ef3eceba4b9896c1ee6a1a69f51dacbfeadea8e010
3
+ size 15139
runs/Sep02_19-27-56_952fa8a340e4/events.out.tfevents.1725305309.952fa8a340e4.1598.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08af716fa0040fa895be1985b594befe8fff086ee15dcc7dbaf8309e80bdc487
3
+ size 5676
runs/Sep02_19-28-55_952fa8a340e4/events.out.tfevents.1725305344.952fa8a340e4.1598.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5da0a8af9f01630f4f04f556035027a9ce7a1dd957829119f226f01963fa38a3
3
+ size 7476
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a2c03af9cb525f00fec1f013efe708230a410f2e18ac1278f17917c0ee59d2
3
+ size 5112