Model save

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: albert-base-v2
+tags:
+- generated_from_trainer
+metrics:
+- f1
+- accuracy
+model-index:
+- name: empathetic_dialogues_context_classification
+  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. -->
+
+# empathetic_dialogues_context_classification
+
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6758
+- F1: 0.5315
+- Accuracy: 0.5315
+
+## 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: constant
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | F1     | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|
+| 2.3973        | 1.0   | 558  | 2.2506          | 0.4080 | 0.4080   |
+| 1.7624        | 2.0   | 1116 | 1.8044          | 0.4870 | 0.4870   |
+| 1.5362        | 3.0   | 1674 | 1.6312          | 0.5094 | 0.5094   |
+| 1.3443        | 4.0   | 2232 | 1.6225          | 0.5145 | 0.5145   |
+| 1.2083        | 5.0   | 2790 | 1.5858          | 0.5355 | 0.5355   |
+| 1.079         | 6.0   | 3348 | 1.5721          | 0.5409 | 0.5409   |
+| 0.9522        | 7.0   | 3906 | 1.5888          | 0.5308 | 0.5308   |
+| 0.8075        | 8.0   | 4464 | 1.6758          | 0.5315 | 0.5315   |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.0+cu121
+- Datasets 3.0.2
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,102 @@
+{
+  "_name_or_path": "albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27",
+    "28": "LABEL_28",
+    "29": "LABEL_29",
+    "30": "LABEL_30",
+    "31": "LABEL_31"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_28": 28,
+    "LABEL_29": 29,
+    "LABEL_3": 3,
+    "LABEL_30": 30,
+    "LABEL_31": 31,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c916da20b389c8be80b0bed11fe1e5c4c52ceaba8736b5d8083b2e003e96db13
+size 46842495

runs/Oct28_06-02-00_ef58dfcc0109/events.out.tfevents.1730095321.ef58dfcc0109.311.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dd0ec8d564bd76a0618ce9a0afb9cc65ded7fd8cee7718f4a4248bf5243f8c1
+size 6460

runs/Oct28_06-02-45_ef58dfcc0109/events.out.tfevents.1730095371.ef58dfcc0109.311.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4da5fdb48c0682d0b3f4615d30454bf1429859052becb40d5e8212fb5867eac1
+size 6509

runs/Oct28_06-18-22_ef58dfcc0109/events.out.tfevents.1730096303.ef58dfcc0109.5496.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7ef9102cfb72d99717f3f0e525e0d5111c59c01256f5b5be8610ece6ba5a5dc
+size 7511

runs/Oct28_07-04-30_ef58dfcc0109/events.out.tfevents.1730099071.ef58dfcc0109.16809.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8a9ccfba0b159515b4f9ae6635f1cae0170c6af8e3a06ac30f017f71ddc08d
+size 6667

runs/Oct28_07-10-49_ef58dfcc0109/events.out.tfevents.1730099449.ef58dfcc0109.18475.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9ac22bb90fe075e9db950dee4be712976bc730c05c331ba1e9851842559ff67
+size 19046

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efdd4b3f403750585784e73310fb98b6d97752ce8626d7681e09a86c1a2b88ee
+size 5304