End of training

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: EleutherAI/pythia-1b
+tags:
+- generated_from_trainer
+model-index:
+- name: robust_llm_pythia-1b_mz-135_WordLength_n-its-10-seed-4
+  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-1b_mz-135_WordLength_n-its-10-seed-4
+
+This model is a fine-tuned version of [EleutherAI/pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) 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: 4
+- 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-1b",
+  "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": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 16,
+  "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 sha256:4d8d7f5270300192ad5c1ebb1ade7407034282075fe13fa8c975cca7001534dc
+size 3635075536

runs/Apr30_07-51-31_rllm-mz-135-multi-see-29-dkzmt/events.out.tfevents.1714463501.rllm-mz-135-multi-see-29-dkzmt.66.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48880a5d678cac46ebf60eede1c923746ad20de2a135efff432a3fea631aff31
+size 6885

runs/Apr30_07-51-31_rllm-mz-135-multi-see-29-dkzmt/events.out.tfevents.1714472254.rllm-mz-135-multi-see-29-dkzmt.66.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438987e3618fee2afee059f95bcc5396c2be65c653ccc06933733f8d4bf9d102
+size 7705

runs/Apr30_07-51-31_rllm-mz-135-multi-see-29-dkzmt/events.out.tfevents.1714481031.rllm-mz-135-multi-see-29-dkzmt.66.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d97d577c66dfedbd30e42860e4eb1cfbb621fc5e2564facdeb2b3ba3531a7402
+size 7705

runs/Apr30_07-51-31_rllm-mz-135-multi-see-29-dkzmt/events.out.tfevents.1714489866.rllm-mz-135-multi-see-29-dkzmt.66.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3175145d0de19df7ca04db454a95100bd6344e844eb265446721b1f421623d9f
+size 8476

runs/Apr30_07-51-31_rllm-mz-135-multi-see-29-dkzmt/events.out.tfevents.1714499028.rllm-mz-135-multi-see-29-dkzmt.66.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22660303db4f6d66fdab7f6a0a3e3d4c7b555478968f7019c8b0bd82e9da4bb7
+size 9247

runs/Apr30_07-51-31_rllm-mz-135-multi-see-29-dkzmt/events.out.tfevents.1714508607.rllm-mz-135-multi-see-29-dkzmt.66.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:215a04d0124bb636eca4c924c4012ac5c6ba0fa39fe7da4361395bb234c04a04
+size 9247

runs/Apr30_07-51-31_rllm-mz-135-multi-see-29-dkzmt/events.out.tfevents.1714518097.rllm-mz-135-multi-see-29-dkzmt.66.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3d14aac15296ee49cb94bc6d852421253b83d4482b0ec03324a6b3cd38cebfe
+size 10018

runs/Apr30_07-51-31_rllm-mz-135-multi-see-29-dkzmt/events.out.tfevents.1714527000.rllm-mz-135-multi-see-29-dkzmt.66.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec1bc64bbc2440729fcd4e22e65636373681dc2db80aa7392d36db73fdf48ee
+size 10018

runs/Apr30_07-51-31_rllm-mz-135-multi-see-29-dkzmt/events.out.tfevents.1714535880.rllm-mz-135-multi-see-29-dkzmt.66.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e085be7d8ccdf7acbb094f201efbd91e7440a971fe46bcfc6a93d69a7ce7c1a2
+size 10789

runs/Apr30_07-51-31_rllm-mz-135-multi-see-29-dkzmt/events.out.tfevents.1714544845.rllm-mz-135-multi-see-29-dkzmt.66.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9396f9265de349aeb957601762e7d86fb0ece5b360a36693d6c17c94dc4346ab
+size 11560

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 sha256:1d8a2d368bb3cecda519c64f8bfd9180dde68d4242cbeef9993f7483c4a5f9b4
+size 5112