End of training

README.md

@@ -0,0 +1,50 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: MiniBOB
+  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. -->
+
+# MiniBOB
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "RobertaForCausalLM"
+  ],
+  "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,
+  "is_decoder": true,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "roberta",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 512000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "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:d25d7c5f5394cdc86e32ed5e8c6b711d716e89522d94e08a4b8ea5f0e104e2ed
+size 2264065256

runs/Jan27_00-39-09_9d1471f48333/events.out.tfevents.1706315954.9d1471f48333.183.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58ebe884f8d06e7f8c0655453757f2dc0a003cf145c3e1c16669d3f19df22193
+size 4184

runs/Jan27_00-53-20_9d1471f48333/events.out.tfevents.1706316802.9d1471f48333.11933.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13ef22ceec600a097375e0a9f69d53800ffb69594dacbfdbda402b4ca202f1af
+size 4125

runs/Jan27_00-54-14_9d1471f48333/events.out.tfevents.1706316857.9d1471f48333.11933.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52e1ab9560df525a296ba010b41fa71a8933d040a6fb18e8a9797b4837ab9bd5
+size 4184

runs/Jan27_00-54-33_9d1471f48333/events.out.tfevents.1706316878.9d1471f48333.11933.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c53b5bd016fc48592d2d812ae06c4bf23e52ef6c586e575ed04375bbfee546d7
+size 88

runs/Jan27_00-54-52_9d1471f48333/events.out.tfevents.1706316895.9d1471f48333.11933.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf9fb1213bf64c50d068bcef16b091356b92b6ca495cb1204e3b2cbe11e3593f
+size 88

runs/Jan27_00-55-07_9d1471f48333/events.out.tfevents.1706316909.9d1471f48333.11933.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53cc95b3f1c2377a296ca3ef6d6a00370cd6be52a6f2ba63f0a5aead44e1aabf
+size 4184

runs/Jan27_00-55-26_9d1471f48333/events.out.tfevents.1706316928.9d1471f48333.11933.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02f4aa99b0b9b8bbb46840f6c0507058d3047c016fc19d24e3c10a20ab20675c
+size 4184

runs/Jan27_01-08-43_9d1471f48333/events.out.tfevents.1706317728.9d1471f48333.15812.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6e54ccb315fc5d93735e4335788231b119daa6ac32a7b784673ade4790472e8
+size 88

runs/Jan27_01-48-18_9d1471f48333/events.out.tfevents.1706320100.9d1471f48333.23178.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64918f7165b06ace0bbe1b2923cb420d356334d9ad117d314ed4f80f943ece70
+size 88

runs/Jan27_01-48-52_9d1471f48333/events.out.tfevents.1706320137.9d1471f48333.23178.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec95926655d3a9d3a2587f7e02281da7c06db6cd5c645f71ab2cac35ed6dfb7d
+size 88

runs/Jan27_01-50-16_9d1471f48333/events.out.tfevents.1706320229.9d1471f48333.29274.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb818a6a0970cf214d4aca202e7b6e6e2c5e5883b3cdab9351113b95fdfc1014
+size 88

runs/Jan27_01-51-54_9d1471f48333/events.out.tfevents.1706320319.9d1471f48333.29776.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f378fe6ea97e3f4cc26688a95b0fc60dd5113330218f6236dcb3059e89c92d
+size 88

runs/Jan27_01-54-08_9d1471f48333/events.out.tfevents.1706320451.9d1471f48333.30392.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9ad1392e9e9bb9714d624d34ab3d1bafc3448713e7289aa5410ec3462d7623
+size 88

runs/Jan27_01-55-35_9d1471f48333/events.out.tfevents.1706320541.9d1471f48333.30865.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6938d578801bedf3677ba04c5613c300ba915a7380f0a3883fc95195dc612572
+size 88

runs/Jan27_01-58-51_9d1471f48333/events.out.tfevents.1706320737.9d1471f48333.31705.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:addb7fcd0a93e96e41e4ad67bb19751813c7ef4bcc13b3ec9c26b1c605bd143c
+size 4123

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5125a8649900bea45754480762da0d3e9ef743fe90757a4b8962e935ae70ccd0
+size 4536