End of training

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: EleutherAI/pythia-410m
+tags:
+- generated_from_trainer
+model-index:
+- name: robust_llm_pythia-410m_mz-135_WordLength_n-its-10-seed-0
+  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. -->
+
+# robust_llm_pythia-410m_mz-135_WordLength_n-its-10-seed-0
+
+This model is a fine-tuned version of [EleutherAI/pythia-410m](https://huggingface.co/EleutherAI/pythia-410m) 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 64
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "EleutherAI/pythia-410m",
+  "architectures": [
+    "GPTNeoXForSequenceClassification"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd5666be80a217e8e59c08a6b5e017043e3efb97ffca6a1e827ce970bb8fc6c1
+size 1415333128

runs/Apr30_07-51-24_rllm-mz-135-multi-see-20-t5v72/events.out.tfevents.1714463494.rllm-mz-135-multi-see-20-t5v72.67.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:341629fd8432ce87d22ab90832c6ea6abe6b1d87632d2893c79f1e8f49bfa7cc
+size 6896

runs/Apr30_07-51-24_rllm-mz-135-multi-see-20-t5v72/events.out.tfevents.1714469644.rllm-mz-135-multi-see-20-t5v72.67.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ac887bd260983a23275d362f810e6981bc7e6c6716921b569d280f8d74cb14
+size 7716

runs/Apr30_07-51-24_rllm-mz-135-multi-see-20-t5v72/events.out.tfevents.1714475822.rllm-mz-135-multi-see-20-t5v72.67.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:294d08d54886bb93910c7f54632112fc64683217cfa645619fd0972bea179459
+size 7716

runs/Apr30_07-51-24_rllm-mz-135-multi-see-20-t5v72/events.out.tfevents.1714482021.rllm-mz-135-multi-see-20-t5v72.67.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8ee400f3b0c5d5f8edfbf4ace0db31f640863faf2215935a403d7bb3071eacc
+size 8487

runs/Apr30_07-51-24_rllm-mz-135-multi-see-20-t5v72/events.out.tfevents.1714488252.rllm-mz-135-multi-see-20-t5v72.67.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e6c0027272e63ac2f04ada7fc27099a35a21e16233ff05f18b39df57d8cfb85
+size 9258

runs/Apr30_07-51-24_rllm-mz-135-multi-see-20-t5v72/events.out.tfevents.1714494492.rllm-mz-135-multi-see-20-t5v72.67.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0262e3d95619decbcb139bba4276c162f99a1bb6e8b34994b02262bd17f9350
+size 9258

runs/Apr30_07-51-24_rllm-mz-135-multi-see-20-t5v72/events.out.tfevents.1714501479.rllm-mz-135-multi-see-20-t5v72.67.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcf5ce3ebd32d6eddb0d61055c37afb4d695702e06db546134767f169744c073
+size 10029

runs/Apr30_07-51-24_rllm-mz-135-multi-see-20-t5v72/events.out.tfevents.1714508439.rllm-mz-135-multi-see-20-t5v72.67.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7134181ee8a12f6c6990f69498fa241807add299fe3c6113052fd51e0e44bc7
+size 10029

runs/Apr30_07-51-24_rllm-mz-135-multi-see-20-t5v72/events.out.tfevents.1714515419.rllm-mz-135-multi-see-20-t5v72.67.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a984fe996ab85681e9c66e9d8d5372acc2f4ea578b0ddd6fa5539e2aa6964d2
+size 10800

runs/Apr30_07-51-24_rllm-mz-135-multi-see-20-t5v72/events.out.tfevents.1714521815.rllm-mz-135-multi-see-20-t5v72.67.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d536457fcfb33a6810dcdb50932450f09810fc5e3f369a49c2993d4f6a36bdba
+size 11571

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8267e097c7c7fc4e933060c72dc0a3a3cad0cae4efec7ec4dab5c761841e958b
+size 5176