End of training

README.md

@@ -0,0 +1,52 @@
+---
+license: apache-2.0
+base_model: EleutherAI/pythia-160m
+tags:
+- generated_from_trainer
+model-index:
+- name: robust_llm_pythia-160m_ian-022_IMDB_n-its-10
+  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-160m_ian-022_IMDB_n-its-10
+
+This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) 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-160m",
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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 sha256:4542ef17b3d822ff00f6adce2ae1528e0e38d6f886e732dae97c75e1bf2b0a3c
+size 494780976

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713395831.rllm-ian-022-adv-trai-18-19-z6n2w.66.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af153140e209d933d55efd1d3b32dfefbce68a0ef10a0e459cdc074ba8577e4c
+size 6695

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713395831.rllm-ian-022-adv-trai-18-19-z6n2w.67.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2799cd58899d9dae231d367016d0c6bd3bbf7992adb58010b458373701c835b7
+size 6696

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713398640.rllm-ian-022-adv-trai-18-19-z6n2w.66.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1d6ec6b0690e6f4a32933897a78b9be03b380010ad934d6da8a06af078ed4f3
+size 7515

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713401444.rllm-ian-022-adv-trai-18-19-z6n2w.66.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:916d687b4176333ebf6e15debd9065d4cfe332aabfdd511a9ae1b86f40d2a851
+size 7515

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713404186.rllm-ian-022-adv-trai-18-19-z6n2w.66.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf4d1d161cce86ff7e5da9cb01af1917a77810ea5031cdaaca8762c92a89926
+size 8286

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713404962.rllm-ian-022-adv-trai-18-19-z6n2w.67.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eddb1641377f5ffe0a9bac2cb32e2990ed88d5eea82fc43a6c4ea6b39de4f39c
+size 7516

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713407035.rllm-ian-022-adv-trai-18-19-z6n2w.66.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74333ff3279419af6bf396cc45857b4fd3532ccabb175d68db16ad54684219db
+size 9057

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713409943.rllm-ian-022-adv-trai-18-19-z6n2w.66.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9add92b7ad5e518ccc375ea8fa4a73d74e6f5ca348b3d6a260ea5050238c34f
+size 9057

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713412838.rllm-ian-022-adv-trai-18-19-z6n2w.66.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb2aaa5992ccb16e308b6298a600397de72008c044b9dff163650fab6056f982
+size 9828

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713414243.rllm-ian-022-adv-trai-18-19-z6n2w.67.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6158e81e0d8c78768729b8f06b7615b4e66c873bd4f232990094be2d6a65962d
+size 7516

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713415696.rllm-ian-022-adv-trai-18-19-z6n2w.66.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab07c9f7d9a760fe4837d06d658e75e61180f2845d3004d222140b5e562be288
+size 9828

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713418204.rllm-ian-022-adv-trai-18-19-z6n2w.66.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9addf5688f19ecfe3ce6a587705fdfb83244dbf5de6684ec91b0790d9769d212
+size 10599

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713420772.rllm-ian-022-adv-trai-18-19-z6n2w.66.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f42f43fe0e7c9f84e0b4b5d0f78602aa66aad4b64e44628078977ec657e1915
+size 11370

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713422205.rllm-ian-022-adv-trai-18-19-z6n2w.67.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6894934b41338c2adfdd8d7992d9cd51c3bb13db013ea4638c55c64e45c3f9df
+size 8287

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713429023.rllm-ian-022-adv-trai-18-19-z6n2w.67.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19f5a4b75a7c15bb40c21e442e2fd4132d9a1cedf27462e3099eba35e0f20359
+size 9058

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713436005.rllm-ian-022-adv-trai-18-19-z6n2w.67.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98c27e31a2de6fe31107db53e46060477b6037db6e0ca109f93183cedb2a13a5
+size 9058

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713442714.rllm-ian-022-adv-trai-18-19-z6n2w.67.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1495a7d3752c1efc60721c2a5a1e76e4f97cba841139c37905b9eb5f780d3b19
+size 9829

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713449371.rllm-ian-022-adv-trai-18-19-z6n2w.67.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688470dbf5ec210c8ccf21cb2e9a0e7ea70b85a2c65ff0dc5faf46bafd4d177f
+size 9829

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713455772.rllm-ian-022-adv-trai-18-19-z6n2w.67.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75c426c657fa34305b64f525ea2cd6d6573d39953e0a5762dc94bcf3183706b1
+size 10600

runs/Apr17_23-17-01_rllm-ian-022-adv-trai-18-19-z6n2w/events.out.tfevents.1713462333.rllm-ian-022-adv-trai-18-19-z6n2w.67.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66491eea86ee735071190e0e4d370e13af2a1638d71cfc8db4cd6f9870aa2fb4
+size 11371

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 sha256:56e8c91490122b2242f2ba57b3d195ca8f8dc08331d3e909883c7ba2ee2bf026
+size 4984