Training in progress, step 500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+training_log.jsonl filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: 4M-ACT
+  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. -->
+
+# 4M-ACT
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2265
+
+## 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: 0.0003
+- train_batch_size: 64
+- eval_batch_size: 64
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- training_steps: 2000
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 3.5628        | 0.0135 | 200  | 3.3842          |
+| 0.9894        | 0.0270 | 400  | 0.9332          |
+| 0.4599        | 0.0404 | 600  | 0.4535          |
+| 0.3477        | 0.0539 | 800  | 0.3484          |
+| 0.3309        | 0.0674 | 1000 | 0.3159          |
+| 0.2846        | 0.0809 | 1200 | 0.2793          |
+| 0.2547        | 0.0944 | 1400 | 0.2563          |
+| 0.2558        | 0.1079 | 1600 | 0.2577          |
+| 0.2350        | 0.1213 | 1800 | 0.2339          |
+| 0.2251        | 0.1348 | 2000 | 0.2265          |
+
+
+### Framework versions
+
+- Transformers 5.15.0.dev0
+- Pytorch 2.6.0+cu124
+- Datasets 5.0.1
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,35 @@
+{
+  "activation": "silu",
+  "architectures": [
+    "TinyLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 256,
+  "max_position_embeddings": 512,
+  "mlp_bias": false,
+  "mlp_type": "glu",
+  "model_type": "tiny_llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 46,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "tokenizer_name": "w-ahmad/tiny-stories-tokenizer",
+  "transformers_version": "5.15.0.dev0",
+  "use_cache": false,
+  "vocab_size": 4096
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ace022739b6ee53d41de2009c9dd33d26b1ce6117ee1e5ac3a51a86a7cb8306
+size 16191120

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f140c32e59bb3258af37cfe1385e25a0991c0518680e3b3a76d2f0dd00e0915e
+size 4856

training_log.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2fac813f7336b1c546893a891bef6b213dd52c89b6afd7c6da6f89dda40c97
+size 11628618