Model save

README.md

@@ -0,0 +1,109 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: progen2_cross_attention_only_h
+  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. -->
+
+# progen2_cross_attention_only_h
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4917
+- Perplexity: 12.0823
+
+## 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: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine_with_restarts
+- lr_scheduler_warmup_ratio: 0.1
+- training_steps: 5000
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss | Perplexity |
+|:-------------:|:-------:|:----:|:---------------:|:----------:|
+| 32.5486       | 0.2909  | 100  | 7.6093          | 2016.7766  |
+| 22.5738       | 0.5818  | 200  | 2.8788          | 17.7926    |
+| 11.4858       | 0.8727  | 300  | 2.8572          | 17.4123    |
+| 11.391        | 1.1658  | 400  | 2.8481          | 17.2545    |
+| 11.6307       | 1.4567  | 500  | 2.6227          | 13.7734    |
+| 10.2311       | 1.7476  | 600  | 2.4862          | 12.0155    |
+| 9.9477        | 2.0407  | 700  | 2.4658          | 11.7733    |
+| 9.8694        | 2.3316  | 800  | 2.6730          | 14.4827    |
+| 9.8291        | 2.6225  | 900  | 2.4811          | 11.9541    |
+| 31.1466       | 2.9135  | 1000 | 8.7851          | 6536.0332  |
+| 34.9023       | 3.2065  | 1100 | 7.7230          | 2259.8149  |
+| 30.5868       | 3.4975  | 1200 | 7.5959          | 1990.0344  |
+| 30.4004       | 3.7884  | 1300 | 7.5865          | 1971.3219  |
+| 31.7038       | 4.0815  | 1400 | 8.0208          | 3043.6248  |
+| 31.3893       | 4.3724  | 1500 | 7.2647          | 1428.9806  |
+| 25.8028       | 4.6633  | 1600 | 5.7546          | 315.6425   |
+| 22.4188       | 4.9542  | 1700 | 5.3616          | 213.0554   |
+| 21.249        | 5.2473  | 1800 | 5.3029          | 200.9226   |
+| 20.9864       | 5.5382  | 1900 | 5.3000          | 200.3277   |
+| 20.9816       | 5.8291  | 2000 | 5.1496          | 172.3635   |
+| 20.6328       | 6.1222  | 2100 | 4.6971          | 109.6314   |
+| 18.4146       | 6.4131  | 2200 | 4.5423          | 93.9023    |
+| 17.0501       | 6.704   | 2300 | 3.8270          | 45.9244    |
+| 15.666        | 6.9949  | 2400 | 3.4366          | 31.0810    |
+| 15.927        | 7.288   | 2500 | 3.9706          | 53.0142    |
+| 13.5433       | 7.5789  | 2600 | 2.9892          | 19.8694    |
+| 12.3278       | 7.8698  | 2700 | 3.1080          | 22.3761    |
+| 12.0588       | 8.1629  | 2800 | 2.7287          | 15.3123    |
+| 11.1222       | 8.4538  | 2900 | 2.6745          | 14.5055    |
+| 10.9132       | 8.7447  | 3000 | 2.6467          | 14.1074    |
+| 10.9437       | 9.0378  | 3100 | 2.6341          | 13.9301    |
+| 10.8436       | 9.3287  | 3200 | 3.8787          | 48.3626    |
+| 10.6462       | 9.6196  | 3300 | 2.6104          | 13.6050    |
+| 10.5014       | 9.9105  | 3400 | 2.6434          | 14.0614    |
+| 10.4753       | 10.2036 | 3500 | 2.6008          | 13.4750    |
+| 10.4235       | 10.4945 | 3600 | 2.5825          | 13.2301    |
+| 10.2556       | 10.7855 | 3700 | 2.5495          | 12.8001    |
+| 10.2415       | 11.0785 | 3800 | 2.5396          | 12.6741    |
+| 10.1531       | 11.3695 | 3900 | 2.5290          | 12.5413    |
+| 10.1279       | 11.6604 | 4000 | 2.5270          | 12.5158    |
+| 10.0816       | 11.9513 | 4100 | 2.5152          | 12.3687    |
+| 10.0384       | 12.2444 | 4200 | 2.5198          | 12.4260    |
+| 10.0156       | 12.5353 | 4300 | 2.5003          | 12.1862    |
+| 9.9928        | 12.8262 | 4400 | 2.4984          | 12.1632    |
+| 10.0172       | 13.1193 | 4500 | 2.4940          | 12.1100    |
+| 9.9678        | 13.4102 | 4600 | 2.4955          | 12.1281    |
+| 9.9605        | 13.7011 | 4700 | 2.4927          | 12.0943    |
+| 9.9324        | 13.992  | 4800 | 2.4920          | 12.0851    |
+| 9.9536        | 14.2851 | 4900 | 2.4916          | 12.0804    |
+| 9.9154        | 14.576  | 5000 | 2.4917          | 12.0823    |
+
+
+### Framework versions
+
+- Transformers 4.47.1
+- Pytorch 2.1.0.post301
+- Datasets 3.0.2
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 30
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "ProGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "embed_dim": 1536,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "kinase_embedding_dim": 1280,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "progen",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 27,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 48,
+  "scale_attn_weights": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_cross_attention": true,
+  "vocab_size_emb": 32,
+  "vocab_size_lm_head": 32
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.47.1"
+}

merges.txt

@@ -0,0 +1 @@
+#version: 0.2

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c707b5df56c355f22732fca91c4b5efbe639e91ecbbd32a457d4e333f1465cf1
+size 4086674752

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|pad|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer.json

@@ -0,0 +1,119 @@
+{
+  "version": "1.0",
+  "truncation": {
+    "direction": "Right",
+    "max_length": 17,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 17
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<|pad|>"
+  },
+  "added_tokens": [
+    {
+      "id": 0,
+      "content": "<|pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 1,
+      "content": "<|bos|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 2,
+      "content": "<|eos|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    {
+      "id": 30,
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  ],
+  "normalizer": null,
+  "pre_tokenizer": {
+    "type": "ByteLevel",
+    "add_prefix_space": false,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "post_processor": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "decoder": {
+    "type": "ByteLevel",
+    "add_prefix_space": true,
+    "trim_offsets": true,
+    "use_regex": true
+  },
+  "model": {
+    "type": "BPE",
+    "dropout": null,
+    "unk_token": null,
+    "continuing_subword_prefix": null,
+    "end_of_word_suffix": null,
+    "fuse_unk": false,
+    "byte_fallback": false,
+    "ignore_merges": false,
+    "vocab": {
+      "<|pad|>": 0,
+      "<|bos|>": 1,
+      "<|eos|>": 2,
+      "1": 3,
+      "2": 4,
+      "A": 5,
+      "B": 6,
+      "C": 7,
+      "D": 8,
+      "E": 9,
+      "F": 10,
+      "G": 11,
+      "H": 12,
+      "I": 13,
+      "K": 14,
+      "L": 15,
+      "M": 16,
+      "N": 17,
+      "O": 18,
+      "P": 19,
+      "Q": 20,
+      "R": 21,
+      "S": 22,
+      "T": 23,
+      "U": 24,
+      "V": 25,
+      "W": 26,
+      "X": 27,
+      "Y": 28,
+      "Z": 29
+    },
+    "merges": []
+  }
+}

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|eos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da901a36057b98547f37028c4768588adeb113f0f1c641b71449990d50a95b0
+size 5432

vocab.json

@@ -0,0 +1 @@
+{"<|pad|>":0,"<|bos|>":1,"<|eos|>":2,"1":3,"2":4,"A":5,"B":6,"C":7,"D":8,"E":9,"F":10,"G":11,"H":12,"I":13,"K":14,"L":15,"M":16,"N":17,"O":18,"P":19,"Q":20,"R":21,"S":22,"T":23,"U":24,"V":25,"W":26,"X":27,"Y":28,"Z":29}