End of training

README.md

@@ -0,0 +1,62 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: facebook/blenderbot_small-90M
+tags:
+- generated_from_trainer
+datasets:
+- eli5_category
+model-index:
+- name: text_model_blenderbot
+  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. -->
+
+# text_model_blenderbot
+
+This model is a fine-tuned version of [facebook/blenderbot_small-90M](https://huggingface.co/facebook/blenderbot_small-90M) on the eli5_category dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0598
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.1209        | 1.0   | 1356 | 0.0663          |
+| 0.0627        | 2.0   | 2712 | 0.0603          |
+| 0.0623        | 3.0   | 4068 | 0.0598          |
+
+
+### Framework versions
+
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "facebook/blenderbot_small-90M",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BlenderbotSmallForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 8,
+  "decoder_start_token_id": 1,
+  "do_blenderbot_90_layernorm": true,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 8,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 0,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_decoder": true,
+  "is_encoder_decoder": false,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layernorm_variant": "xlm",
+  "length_penalty": null,
+  "max_length": null,
+  "max_position_embeddings": 512,
+  "min_length": null,
+  "model_type": "blenderbot-small",
+  "no_repeat_ngram_size": null,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": null,
+  "num_hidden_layers": 8,
+  "pad_token_id": 0,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "unk_token_id": 3,
+  "use_cache": true,
+  "vocab_size": 54944
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "decoder_start_token_id": 1,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "length_penalty": 0.65,
+  "max_length": 128,
+  "min_length": 20,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 10,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20e1ea6e841e2b487602ddae9740c5c8c8d9680b59f0145e63d8ea3a6d9eb8c
+size 248131760

runs/Nov18_22-19-59_bd882ffc99aa/events.out.tfevents.1731968402.bd882ffc99aa.454.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d28ea991fc342a6454732156125b92093499c5e6ae1ddad584083e460c13a85e
+size 8836

runs/Nov18_22-19-59_bd882ffc99aa/events.out.tfevents.1731969310.bd882ffc99aa.454.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:457133adf6839658daa93019332af27efb6aae190eb24d2ee2d59f5e8b3bccf6
+size 359

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "__start__",
+  "eos_token": "__end__",
+  "pad_token": "__end__",
+  "unk_token": "__unk__"
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "__null__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "__start__",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "__end__",
+      "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
+    }
+  },
+  "bos_token": "__start__",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "__end__",
+  "model_max_length": 512,
+  "pad_token": "__end__",
+  "tokenizer_class": "BlenderbotSmallTokenizer",
+  "unk_token": "__unk__"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26da6f434d14ddd9b72f06ed3d62059ce573730154a03d150be7a4551a2d99f1
+size 5304