archit11/nous-fn-finetuned-model

README.md

@@ -0,0 +1,56 @@
+---
+library_name: transformers
+license: mit
+base_model: nisten/Biggie-SmoLlm-0.15B-Base
+tags:
+- generated_from_trainer
+model-index:
+- name: capybara_finetuned_results
+  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. -->
+
+# capybara_finetuned_results
+
+This model is a fine-tuned version of [nisten/Biggie-SmoLlm-0.15B-Base](https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-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: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 30
+- training_steps: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0
+- Datasets 3.0.0
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "nisten/Biggie-SmoLlm-0.15B-Base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 35,
+  "num_key_value_heads": 3,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f79a74f930e801892fad66bcf37e034d6f7dad773965f4529985ef344a0100dc
+size 304466592

runs/Sep25_21-01-34_4cfab063c3dc/events.out.tfevents.1727298095.4cfab063c3dc.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6d0e7c270ef299505935702fe8bbc35c208524759ddf0accbdc553a5062f56
+size 5036

runs/Sep26_11-43-19_d0d4ee6aec48/events.out.tfevents.1727351001.d0d4ee6aec48.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b494de8a8ea7a3701e0e7b35e83e8a1300b1493dde54418205b319b38904fc2e
+size 5589

runs/Sep26_12-00-38_f57f1acbd579/events.out.tfevents.1727352040.f57f1acbd579.30.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1ba49118d7ad41f6caee89268ee2e793091725e0a17e366eed9db28fb824481
+size 5381

runs/Sep26_12-02-07_f57f1acbd579/events.out.tfevents.1727352129.f57f1acbd579.30.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fbc08be87b4ad365241ea9c0029f8b5eae5a34eb436afba460f56213118f838
+size 5381

runs/Sep26_12-21-06_f57f1acbd579/events.out.tfevents.1727353267.f57f1acbd579.30.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c604e05c6204aaf3c35b956d16bbbab0af66fb3ec718286e0ba269856fa70039
+size 5381

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdcc514972bdbd8c76671b859d85a1515b3472ad0265bbbe79a7a519b8520307
+size 5176