End of training

README.md

@@ -0,0 +1,53 @@
+---
+license: apache-2.0
+base_model: togethercomputer/evo-1-8k-base
+tags:
+- generated_from_trainer
+model-index:
+- name: virus_evo_70_1024_two_d
+  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. -->
+
+# virus_evo_70_1024_two_d
+
+This model is a fine-tuned version of [togethercomputer/evo-1-8k-base](https://huggingface.co/togethercomputer/evo-1-8k-base) 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: 5e-05
+- train_batch_size: 6
+- eval_batch_size: 6
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,90 @@
+{
+  "_commit_hash": "6d7baa4482172f2c451ca4b36c87d50c8359a134",
+  "_name_or_path": "togethercomputer/evo-1-8k-base",
+  "architectures": [
+    "StripedHyenaModelForCausalLM"
+  ],
+  "attn_layer_idxs": [
+    8,
+    16,
+    24
+  ],
+  "auto_map": {
+    "AutoConfig": "togethercomputer/evo-1-131k-base--configuration_hyena.StripedHyenaConfig",
+    "AutoModelForCausalLM": "togethercomputer/evo-1-131k-base--modeling_hyena.StripedHyenaModelForCausalLM",
+    "AutoTokenizer": "Hack90/virus_pythia_31_1024"
+  },
+  "bos_token_id": 0,
+  "column_split": false,
+  "column_split_hyena": true,
+  "eos_token_id": 0,
+  "eps": 1e-06,
+  "final_norm": true,
+  "hidden_size": 512,
+  "hyena_filter_groups": 1,
+  "hyena_layer_idxs": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31
+  ],
+  "inference_mode": false,
+  "inner_mlp_size": 1024,
+  "log_intermediate_values": false,
+  "make_vocab_size_divisible_by": 8,
+  "max_seqlen": 1024,
+  "mha_out_proj_bias": true,
+  "mlp_activation": "gelu",
+  "model_parallel_size": 1,
+  "model_type": "stripedhyena",
+  "num_attention_heads": 32,
+  "num_filters": 512,
+  "num_layers": 32,
+  "pipe_parallel_size": 1,
+  "prefill_style": "fft",
+  "proj_groups": 1,
+  "qkv_proj_bias": true,
+  "rotary_emb_base": 10000,
+  "rotary_emb_scaling_factor": 1,
+  "short_filter_bias": true,
+  "short_filter_length": 3,
+  "smeared_gqa": false,
+  "split_k0": true,
+  "state_size": 8,
+  "tie_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": null,
+  "use_cache": true,
+  "use_flash_attention_2": true,
+  "use_flash_attn": true,
+  "use_flash_depthwise": false,
+  "use_flash_rmsnorm": false,
+  "use_flashfft": false,
+  "use_interpolated_rotary_pos_emb": false,
+  "vocab_size": 8
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.40.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68ee407ab4b0f1538b7fa04820ebbd261b5789e3942ff3cd4b4c29a2e1f450c5
+size 170320048

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,96 @@
+{
+  "version": "1.0",
+  "truncation": null,
+  "padding": null,
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<|beginoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": true,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<|unknown|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": {
+    "type": "NFC"
+  },
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "TemplateProcessing",
+    "single": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      }
+    ],
+    "pair": [
+      {
+        "Sequence": {
+          "id": "A",
+          "type_id": 0
+        }
+      },
+      {
+        "Sequence": {
+          "id": "B",
+          "type_id": 1
+        }
+      }
+    ],
+    "special_tokens": {}
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": "<|unknown|>",
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<|beginoftext|>": 0,
+      "<|endoftext|>": 1,
+      "<|unknown|>": 2,
+      "a": 3,
+      "c": 4,
+      "g": 5,
+      "t": 6,
+      "n": 7
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|beginoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|unknown|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|beginoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|unknown|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:102f149063e5a05893e2a626a294d973935e2ce0507835f119450711f1123462
+size 4920