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-131f_IMDB
+  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-131f_IMDB
+
+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: 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-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:ec9730f308b3d2dba7ebc41c5f6d4ff6e382e33c22dbedee73e0e57163eeb6bf
+size 3635075536

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714063501.rllm-mz-131f-adv-trai-10-cwp78.66.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65f18d77b572a0b21cda65c4d42343bfd06282c5d4c18c768c448eeaba1291ce
+size 6801

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714071835.rllm-mz-131f-adv-trai-10-cwp78.66.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9728106e2faca5157b923ea5bc70bc214702a9415d59b7f5ffafc8fd8c4071
+size 6850

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714080049.rllm-mz-131f-adv-trai-10-cwp78.66.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1eed01b2829a225b23ca1cc1c6de36fb411c68075280fa3592b28cfe3ce89d2
+size 7621

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714087896.rllm-mz-131f-adv-trai-10-cwp78.66.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e9b093de983e7259f97fb371d3db1f1afe48f38ab44403ddcb6c241c06563c9
+size 7621

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714095818.rllm-mz-131f-adv-trai-10-cwp78.66.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec46babe86d08422607e60d8cfe8b5d3f00bc0a7314aff1150b3c0742142012a
+size 7621

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714103877.rllm-mz-131f-adv-trai-10-cwp78.66.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36aa6c5b281801b198866025ad6028e2178aafd92ec6249b081968f05a2bf694
+size 7621

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714111480.rllm-mz-131f-adv-trai-10-cwp78.66.6

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18a0cf767a5893d3559e0922b04eea2005281431f7084669a856ca9029ac5846
+size 8392

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714119215.rllm-mz-131f-adv-trai-10-cwp78.66.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f19bf9af1872149aa3a28c114b58dc57b7ad457d52f2f15c3559895294773fb
+size 8392

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714126920.rllm-mz-131f-adv-trai-10-cwp78.66.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed8e9b5518edf720bac3929c6e34ee820f7044168f328ce78ba32e92209f3f2
+size 8392

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714134502.rllm-mz-131f-adv-trai-10-cwp78.66.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4b3bbe2bb69d8a219aee1c6d798ead75fc485629775a20ad438f5bfa654429d
+size 8392

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714142292.rllm-mz-131f-adv-trai-10-cwp78.66.10

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d67fa8db53bf3ac637453b3157f9d1901e4b748da9cf6e757b780fcd1cd8e0c
+size 9163

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714150041.rllm-mz-131f-adv-trai-10-cwp78.66.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f61de4da971c82d41480c68252c3c92ca0df67a1dffa00bd985c09ea0a55325
+size 9163

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714157890.rllm-mz-131f-adv-trai-10-cwp78.66.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2471f5924301196fdec9c8bf4b1e9f34da77a4b9f55a4335119008cf6f39f87
+size 9163

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714165779.rllm-mz-131f-adv-trai-10-cwp78.66.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506a999d8dbbc606d48cbe900a3b22ec6986e02df3953457f3b05d85cb616bf3
+size 9163

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714173828.rllm-mz-131f-adv-trai-10-cwp78.66.14

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e544359fe91b6d6b20bcd2068a48d8b47dcf600f04e254a801aa3cab4fd8a568
+size 9934

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714181720.rllm-mz-131f-adv-trai-10-cwp78.66.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ca99c4e3e156949cc9d2d0d982ff96a499eb7d588d861da9b1b791fcdb5f21
+size 9934

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714189691.rllm-mz-131f-adv-trai-10-cwp78.66.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c98f02a27ddc700fea7f1ede5fe65dbe966a02427ce1c373fe6dee78cd2e9a3
+size 9934

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714197805.rllm-mz-131f-adv-trai-10-cwp78.66.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:722f9c5fb52711ee44029cb20e1aa63b996f608a287cf5a5c7a34b3f18812aef
+size 9934

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714205987.rllm-mz-131f-adv-trai-10-cwp78.66.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7bf043a51da18c8cf4de55f7a349f8837ad770b8fbcf95108fae42ab9d4b269
+size 10705

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714214590.rllm-mz-131f-adv-trai-10-cwp78.66.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60430060dfd692d9315912ae2672cdcb92993acf01f722860c2847bf751d3f85
+size 10705

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714223357.rllm-mz-131f-adv-trai-10-cwp78.66.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb897a031119e0193ad20b1ac250ca315b8700fbd17d53f43d22f99ebc7c15c1
+size 10705

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714232165.rllm-mz-131f-adv-trai-10-cwp78.66.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:535f8a21e320a2ebeb8a4acebf10fbe7cdaa5f5cf7ab4299a1c774b9652b9a47
+size 10705

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714241268.rllm-mz-131f-adv-trai-10-cwp78.66.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f853623062b49f1fa95e6e3fba61c79b24fb222951e19e68099b67cc18cf4e40
+size 11476

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714250288.rllm-mz-131f-adv-trai-10-cwp78.66.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d54c2ee89cde6f15f840c7207b52adcf0ac0e201ba112a61339042be36d6705
+size 11476

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714259516.rllm-mz-131f-adv-trai-10-cwp78.66.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77a0a4d074a11d29677e6722fb2ad9b4a7c020dc3edc94642411979058e32888
+size 11476

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714268606.rllm-mz-131f-adv-trai-10-cwp78.66.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce7c25fc0356efa80569ae171302eadcdd181d7b9175cc0243eea7fa042e7c81
+size 11476

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714277707.rllm-mz-131f-adv-trai-10-cwp78.66.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca11871904ecf13f29f2935f270ff60208d649289114ca98de4124c625e72b6a
+size 12247

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714286838.rllm-mz-131f-adv-trai-10-cwp78.66.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b39b155876bc1210aef65bef6357f14cfc773d98c2a1d58269723eedfd512a8
+size 12247

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714296060.rllm-mz-131f-adv-trai-10-cwp78.66.28

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76964d1186030b4f970f8ffdcd8bbc529e708e206ef43a94220521ba75943718
+size 12247

runs/Apr25_16-44-48_rllm-mz-131f-adv-trai-10-cwp78/events.out.tfevents.1714305206.rllm-mz-131f-adv-trai-10-cwp78.66.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec21b0ff14bbed8ecd770dc7a4d051e8d8412dbf6be04f6ec2c29e45b6a83f1
+size 12247

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 sha256:6251f5adf5ee1b83c8d3c154446909df48d71db5760f3239285e15a25e9f2c70
+size 5048