Training in progress, step 744

README.md

@@ -4,9 +4,9 @@ library_name: transformers
 model_name: m_augment2
 tags:
 - generated_from_trainer
-- trl
-- sft
 - unsloth
+- sft
+- trl
 licence: license
 ---
 
@@ -28,7 +28,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/e1lgdx7n) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/6efuahke) 
 
 
 This model was trained with SFT.

config.json

@@ -0,0 +1,73 @@
+{
+  "architectures": [
+    "Mistral3ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "image_token_index": 10,
+  "model_type": "mistral3",
+  "multimodal_projector_bias": false,
+  "pad_token_id": 11,
+  "projector_hidden_act": "gelu",
+  "spatial_merge_size": 2,
+  "text_config": {
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "dtype": "bfloat16",
+    "eos_token_id": 2,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 3072,
+    "initializer_range": 0.02,
+    "intermediate_size": 9216,
+    "max_position_embeddings": 262144,
+    "model_type": "ministral3",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 26,
+    "num_key_value_heads": 8,
+    "pad_token_id": 11,
+    "rms_norm_eps": 1e-05,
+    "rope_parameters": {
+      "beta_fast": 32.0,
+      "beta_slow": 1.0,
+      "factor": 16.0,
+      "llama_4_scaling_beta": 0.1,
+      "mscale": 1.0,
+      "mscale_all_dim": 1.0,
+      "original_max_position_embeddings": 16384,
+      "rope_theta": 1000000.0,
+      "rope_type": "yarn",
+      "type": "yarn"
+    },
+    "sliding_window": null,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 131072
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.1.dev0",
+  "unsloth_fixed": true,
+  "unsloth_version": "2026.1.4",
+  "use_cache": false,
+  "vision_config": {
+    "attention_dropout": 0.0,
+    "dtype": "bfloat16",
+    "head_dim": 64,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "image_size": 1540,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "pixtral",
+    "num_attention_heads": 16,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "rope_parameters": {
+      "rope_theta": 10000.0,
+      "rope_type": "default"
+    }
+  },
+  "vision_feature_layer": -1
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "max_length": 262144,
+  "pad_token_id": 11,
+  "transformers_version": "5.0.1.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82cfd8c1220e84d32fa064e6297ac77a4d2a6c16cfed2f784dbb4de5d360c7c4
+size 8503547592

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cccdff4035de185fe5523668cf007d2c9c488520e1b5166679c84b1390ba024
+oid sha256:2eb58d89dbac60654e5bc9b2c63211f8655fbfd4793522039e73ecdea82b46f6
 size 5713