amino-acid-sequence-5500

README.md

@@ -0,0 +1,46 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model was trained from scratch 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: 3
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.04
+- training_steps: 10000
+
+### Framework versions
+
+- Transformers 4.42.4
+- Pytorch 2.3.1+cu121
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "/content/output/checkpoint-5500",
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 1,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 2,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 512,
+  "model_type": "gemma2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 14,
+  "num_key_value_heads": 16,
+  "pad_token_id": 3,
+  "query_pre_attn_scalar": 224,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 24
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.42.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d14c6ea4cc5d67042ea6865b4d09b53671400a4e3ff0a3b725dcc253cb1f7e4a
+size 1101271208

runs/Jul23_18-19-52_6bd021382e5b/events.out.tfevents.1721758794.6bd021382e5b.476.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:246c72b7780526adb610591989a99e47bda61decc11cf5730736427a0e91f1ef
+size 35790

runs/Jul23_18-21-04_6bd021382e5b/events.out.tfevents.1721758873.6bd021382e5b.476.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35dfb688f62ffca856c45d097f4bf6c1623362b215e59d73e67c17e575fa2749
+size 353817

runs/Jul23_19-05-59_6bd021382e5b/events.out.tfevents.1721761567.6bd021382e5b.476.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc69d319fc8b3cd29fce5d32f5de89fab9e32757a35208e0d58a46ed417f62e
+size 947151

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c758947f00481b09bb92b8b2eb645883e84d8d37e801ae778e0be072ae389cfb
+size 5112