Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: transformers
+base_model: kajuma/falcon3_1b_patch
+tags:
+- generated_from_trainer
+model-index:
+- name: 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. -->
+
+# results
+
+This model is a fine-tuned version of [kajuma/falcon3_1b_patch](https://huggingface.co/kajuma/falcon3_1b_patch) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.2373
+
+## 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: 28
+- eval_batch_size: 16
+- seed: 42
+- gradient_accumulation_steps: 9
+- total_train_batch_size: 252
+- optimizer: Use schedule_free_radam with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: constant
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.014         | 0.0515 | 500  | 2.1112          |
+| 1.8567        | 0.1029 | 1000 | 2.2158          |
+| 1.8408        | 0.1544 | 1500 | 2.2958          |
+| 1.8394        | 0.2059 | 2000 | 2.5333          |
+| 1.7843        | 0.2573 | 2500 | 2.5528          |
+| 1.7623        | 0.3088 | 3000 | 2.6474          |
+| 1.7908        | 0.3603 | 3500 | 2.7576          |
+| 1.7743        | 0.4117 | 4000 | 2.8830          |
+| 1.7513        | 0.4632 | 4500 | 2.9958          |
+| 1.7205        | 0.5147 | 5000 | 3.1096          |
+| 1.7321        | 0.5661 | 5500 | 3.2373          |
+
+
+### Framework versions
+
+- Transformers 4.48.0.dev0
+- Pytorch 2.5.1
+- Datasets 3.2.0
+- Tokenizers 0.21.0

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "kajuma/falcon3_1b_patch",
+  "activation": "swiglu",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 11,
+  "head_dim": 256,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 4,
+  "patch_size": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000042,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.0.dev0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "eos_token_id": 11,
+  "transformers_version": "4.48.0.dev0"
+}

log/events.out.tfevents.1736075972.192-222-59-10.6648.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0578f1fc678d067d55c7a7ea08e3039fa21c7925bdcb137a6dc3b8aa2bd61f4f
+size 5216

log/events.out.tfevents.1736076155.192-222-59-10.12538.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e39cc7d4cd2abd85e945a7f0e1525bfbb26b49cec3281a74ed4763564882ef9
+size 5216

log/events.out.tfevents.1736076433.192-222-59-10.17214.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8363d28f5b90117342b6e374fae1223265ece76e822c9380b9bdd3138e3d9d7
+size 88

log/events.out.tfevents.1736076610.192-222-59-10.21946.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e8d54f1369a5c5383cd03d71d72dbde03d482ee8b2b3dee58f9b2e3c6758e90
+size 12667

logs/events.out.tfevents.1736077179.192-222-59-10.26684.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c45996cbda8823c4d5aa1ef6efa6780483c612dc9f9adc51624c67177310dd4
+size 5216

logs/events.out.tfevents.1736077235.192-222-59-10.31417.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:829a42aeb3be1db86f757a99db03d3f19f163480610bfef758cb67d5c0cc0e9d
+size 7701

logs/events.out.tfevents.1736077386.192-222-59-10.36172.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c842cff2bf1f357731a801fb0ccde7c73a476d1a94fb1534a3ff9a837420b0be
+size 8322

logs/events.out.tfevents.1736077590.192-222-59-10.40888.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf3d98981ed95137b9ee396f272b0fc51f71de7dcdb0a2a1f1dbff13885918b7
+size 110208

logs/events.out.tfevents.1736083992.192-222-59-10.46954.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc7e50d082729e6a07afc02ce3aa44e261a88e04b8f27ecfe1fd2ffd339fdcf
+size 767453

logs/events.out.tfevents.1736133622.192-222-59-10.61157.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be45b09d630e722481f18873ae4cc5eaa7030cb556b5410da251d375f3e3c35
+size 325320

logs/events.out.tfevents.1736153702.192-222-59-10.69444.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c27b85c3ebee2baf9ccca5890515398a1a7a7dd151011fc329ffa1e5980958
+size 894982

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28dbb2b4c0125216250bf5ec855690b81cdb185a10f37ad814b4771259f5df26
+size 3338836632

special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+  "additional_special_tokens": [
+    ">>TITLE<<",
+    ">>ABSTRACT<<",
+    ">>INTRODUCTION<<",
+    ">>SUMMARY<<",
+    ">>COMMENT<<",
+    ">>ANSWER<<",
+    ">>QUESTION<<",
+    ">>DOMAIN<<",
+    ">>EMAIL_ADDRESS<<",
+    ">>IP_ADDRESS<<",
+    "<|startoftext|>",
+    ">>IP_ADDRESS_0<<",
+    ">>IP_ADDRESS_1<<",
+    ">>IP_ADDRESS_2<<",
+    ">>IP_ADDRESS_3<<",
+    ">>IP_ADDRESS_4<<",
+    ">>IP_ADDRESS_5<<",
+    ">>IP_ADDRESS_6<<",
+    ">>IP_ADDRESS_7<<",
+    ">>IP_ADDRESS_8<<",
+    ">>IP_ADDRESS_9<<",
+    ">>PASSWORD<<",
+    ">>KEY<<"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d888ab1550fbb4edb1685e8832f1a325ea7d60fff513f90b5bbe7a7bac0d3483
+size 5432