End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,119 @@
+---
+base_model: hhhhzy/deltalm-base-xlsum
+tags:
+- generated_from_trainer
+model-index:
+- name: T10
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# T10
+
+This model is a fine-tuned version of [hhhhzy/deltalm-base-xlsum](https://huggingface.co/hhhhzy/deltalm-base-xlsum) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6357
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 64
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.805         | 1.0   | 6    | 0.3684          |
+| 0.2843        | 2.0   | 12   | 0.3604          |
+| 0.2494        | 3.0   | 18   | 0.3970          |
+| 0.1528        | 4.0   | 24   | 0.4507          |
+| 0.0779        | 5.0   | 30   | 0.5024          |
+| 0.0482        | 6.0   | 36   | 0.5399          |
+| 0.0246        | 7.0   | 42   | 0.5612          |
+| 0.0202        | 8.0   | 48   | 0.5788          |
+| 0.0172        | 9.0   | 54   | 0.6024          |
+| 0.0147        | 10.0  | 60   | 0.6003          |
+| 0.0115        | 11.0  | 66   | 0.5960          |
+| 0.0124        | 12.0  | 72   | 0.6035          |
+| 0.0122        | 13.0  | 78   | 0.6135          |
+| 0.0121        | 14.0  | 84   | 0.6105          |
+| 0.0101        | 15.0  | 90   | 0.6155          |
+| 0.0103        | 16.0  | 96   | 0.6188          |
+| 0.0087        | 17.0  | 102  | 0.6192          |
+| 0.015         | 18.0  | 108  | 0.6113          |
+| 0.0092        | 19.0  | 114  | 0.6141          |
+| 0.0091        | 20.0  | 120  | 0.6220          |
+| 0.0088        | 21.0  | 126  | 0.6243          |
+| 0.009         | 22.0  | 132  | 0.6239          |
+| 0.0085        | 23.0  | 138  | 0.6199          |
+| 0.0093        | 24.0  | 144  | 0.6183          |
+| 0.0092        | 25.0  | 150  | 0.6170          |
+| 0.0086        | 26.0  | 156  | 0.6154          |
+| 0.0084        | 27.0  | 162  | 0.6154          |
+| 0.0082        | 28.0  | 168  | 0.6182          |
+| 0.0083        | 29.0  | 174  | 0.6224          |
+| 0.0082        | 30.0  | 180  | 0.6250          |
+| 0.0086        | 31.0  | 186  | 0.6263          |
+| 0.0078        | 32.0  | 192  | 0.6270          |
+| 0.0081        | 33.0  | 198  | 0.6271          |
+| 0.0081        | 34.0  | 204  | 0.6276          |
+| 0.0082        | 35.0  | 210  | 0.6280          |
+| 0.0078        | 36.0  | 216  | 0.6292          |
+| 0.0078        | 37.0  | 222  | 0.6302          |
+| 0.0079        | 38.0  | 228  | 0.6314          |
+| 0.0081        | 39.0  | 234  | 0.6319          |
+| 0.0083        | 40.0  | 240  | 0.6318          |
+| 0.0076        | 41.0  | 246  | 0.6317          |
+| 0.0079        | 42.0  | 252  | 0.6309          |
+| 0.0084        | 43.0  | 258  | 0.6304          |
+| 0.0078        | 44.0  | 264  | 0.6307          |
+| 0.0079        | 45.0  | 270  | 0.6309          |
+| 0.0076        | 46.0  | 276  | 0.6312          |
+| 0.0076        | 47.0  | 282  | 0.6313          |
+| 0.008         | 48.0  | 288  | 0.6316          |
+| 0.0081        | 49.0  | 294  | 0.6320          |
+| 0.0077        | 50.0  | 300  | 0.6323          |
+| 0.0075        | 51.0  | 306  | 0.6328          |
+| 0.0077        | 52.0  | 312  | 0.6336          |
+| 0.0076        | 53.0  | 318  | 0.6342          |
+| 0.0077        | 54.0  | 324  | 0.6344          |
+| 0.0075        | 55.0  | 330  | 0.6346          |
+| 0.0079        | 56.0  | 336  | 0.6350          |
+| 0.0076        | 57.0  | 342  | 0.6350          |
+| 0.0078        | 58.0  | 348  | 0.6355          |
+| 0.0077        | 59.0  | 354  | 0.6357          |
+| 0.0074        | 60.0  | 360  | 0.6358          |
+| 0.0075        | 61.0  | 366  | 0.6358          |
+| 0.0075        | 62.0  | 372  | 0.6358          |
+| 0.0077        | 63.0  | 378  | 0.6357          |
+| 0.0073        | 64.0  | 384  | 0.6357          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "hhhhzy/deltalm-base-xlsum",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "DeltalmForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "encoder_normalize_before": false,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "ignore_index": -100,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "label_smoothing": 0.1,
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "Deltalm",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 5,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 250104
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "max_length": 512,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a8ba8d1895d45f4ba061f1c0c769fecc8739d38bb0cbd1ea984ee8758b819d
+size 1452970712

runs/Feb13_11-03-45_84c9dc6cf005/events.out.tfevents.1707822232.84c9dc6cf005.1607.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a18b79e180902cb1fd63fd5f5628095cd6bb864a7c0448cd7cbb939e6ef9694
+size 34371

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:437b282134b435844a6ca1e559833b02821fbb9168825228264214be09ef90ed
+size 17083020

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:220a224686f1f31262efca28cd1c5ac7d17308357c2b28439b049f99f4c7759f
+size 4536