End of training

README.md

@@ -0,0 +1,65 @@
+---
+base_model: vinai/phobert-base-v2
+tags:
+- generated_from_trainer
+model-index:
+- name: token-classification-llmlingua2-phobert-bctn-2308_sample-10_epoch_best_data
+  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. -->
+
+# token-classification-llmlingua2-phobert-bctn-2308_sample-10_epoch_best_data
+
+This model is a fine-tuned version of [vinai/phobert-base-v2](https://huggingface.co/vinai/phobert-base-v2) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3044
+
+## 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: 1e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 58   | 0.3799          |
+| No log        | 2.0   | 116  | 0.3286          |
+| No log        | 3.0   | 174  | 0.3129          |
+| No log        | 4.0   | 232  | 0.3105          |
+| No log        | 5.0   | 290  | 0.3104          |
+| No log        | 6.0   | 348  | 0.3064          |
+| No log        | 7.0   | 406  | 0.3045          |
+| No log        | 8.0   | 464  | 0.3049          |
+| 0.3309        | 9.0   | 522  | 0.3044          |
+| 0.3309        | 10.0  | 580  | 0.3054          |
+
+
+### Framework versions
+
+- Transformers 4.39.0.dev0
+- Pytorch 2.2.1+cu118
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<mask>": 64000
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "vinai/phobert-base-v2",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 258,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "PhobertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 64001
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db8623cfeeca4d4386415a4f6b40a68bf938f27db1165e532a23984ed7fe150
+size 537660792

runs/Apr25_15-41-22_aies-gpu-a30/events.out.tfevents.1714034482.aies-gpu-a30.45991.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f23ac302620027398ab2c67a12892908a529c6e8e5334010c7befddbd6b9ec5
+size 5014

runs/Apr25_15-49-00_aies-gpu-a30/events.out.tfevents.1714034941.aies-gpu-a30.45991.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9af18398c17ad2ebf7c7e1120ed7b86c7025ee7ff2c698f045f640a87eea02
+size 5014

runs/Apr25_16-01-00_aies-gpu-a30/events.out.tfevents.1714035660.aies-gpu-a30.45991.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e27c59b3794c01b7bda906f5a9363dfcd00b800a445330be987493d06fd9006
+size 5014

runs/Apr25_16-02-21_aies-gpu-a30/events.out.tfevents.1714035742.aies-gpu-a30.47117.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65275de44e8db1e1ed4b4e38c329bb3a282f2507c0d04a7087fd1c1c088d41b5
+size 5014

runs/Apr25_16-03-10_aies-gpu-a30/events.out.tfevents.1714035791.aies-gpu-a30.47117.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:247229d6f7dec8bdbacb448569fd30a415f14c9c72ab4c7858a2eaa90792df33
+size 5014

runs/Apr25_16-04-28_aies-gpu-a30/events.out.tfevents.1714035871.aies-gpu-a30.47324.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:046775ed91b8c2a5a98069a7a216bd1e56352e9e0236364eb59de031ab2ae236
+size 8279

runs/Apr25_16-04-28_aies-gpu-a30/events.out.tfevents.1714036411.aies-gpu-a30.47324.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3032d995f5165455241a5ef1ccc587e16a99d80a7c9b6acf60408ce1f38608b
+size 359

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

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
+    },
+    "64000": {
+      "content": "<mask>",
+      "lstrip": false,
+      "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": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "PhobertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22984602c0f565fe96e679e9489040570f5d8081ab852e6f391ee00940267ef2
+size 5176