Upload folder using huggingface_hub

.gitattributes

@@ -40,3 +40,4 @@ checkpoint-75/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-125/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-65/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-300/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

checkpoint-300/config.json

@@ -0,0 +1,64 @@
+{
+  "_sliding_window_pattern": 6,
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 256,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 1152,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": 512,
+  "sliding_window_pattern": 6,
+  "transformers_version": "4.57.1",
+  "use_bidirectional_attention": false,
+  "use_cache": true,
+  "vocab_size": 262144
+}

checkpoint-300/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    106
+  ],
+  "pad_token_id": 0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a639938f53f443c0dc92996c1fea7ea8618b2deeb5f92b5cf41d16551951f2
+size 1999811208

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001560c4be4c072b6dcd158fe795b79fc3772406c480917a864a3e70c8b2f674
+size 3999834207

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1255b82ec9f462fef6f8c2f4a8ee876c4b6d998a53c99546a4eddcc1aabaefc7
+size 14645

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6899f9f82cea064fe52ac09813b47d526ed686cbe04f0925eb7e665a0e61bfae
+size 1465

checkpoint-300/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": "<eos>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-300/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db5eba787198c9cb1d12d0dc4d653f46747749da078219b0b3f4a11b7487eb19
+size 33384832

checkpoint-300/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

checkpoint-300/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 10.75,
+      "learning_rate": 4.85e-05,
+      "loss": 2.3182,
+      "step": 10
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.71875,
+      "learning_rate": 4.683333333333334e-05,
+      "loss": 1.674,
+      "step": 20
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 5.90625,
+      "learning_rate": 4.516666666666667e-05,
+      "loss": 1.618,
+      "step": 30
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 5.6875,
+      "learning_rate": 4.35e-05,
+      "loss": 1.5503,
+      "step": 40
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 4.3125,
+      "learning_rate": 4.183333333333334e-05,
+      "loss": 1.5248,
+      "step": 50
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 4.59375,
+      "learning_rate": 4.016666666666667e-05,
+      "loss": 1.3144,
+      "step": 60
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 9.1875,
+      "learning_rate": 3.85e-05,
+      "loss": 1.2945,
+      "step": 70
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 6.3125,
+      "learning_rate": 3.683333333333334e-05,
+      "loss": 1.2991,
+      "step": 80
+    },
+    {
+      "epoch": 3.6,
+      "grad_norm": 6.15625,
+      "learning_rate": 3.516666666666667e-05,
+      "loss": 1.052,
+      "step": 90
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 8.375,
+      "learning_rate": 3.35e-05,
+      "loss": 1.1129,
+      "step": 100
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 19.75,
+      "learning_rate": 3.183333333333334e-05,
+      "loss": 0.9219,
+      "step": 110
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 8.375,
+      "learning_rate": 3.016666666666667e-05,
+      "loss": 0.7774,
+      "step": 120
+    },
+    {
+      "epoch": 5.2,
+      "grad_norm": 8.625,
+      "learning_rate": 2.8499999999999998e-05,
+      "loss": 0.7305,
+      "step": 130
+    },
+    {
+      "epoch": 5.6,
+      "grad_norm": 13.4375,
+      "learning_rate": 2.6833333333333333e-05,
+      "loss": 0.5266,
+      "step": 140
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.0625,
+      "learning_rate": 2.5166666666666667e-05,
+      "loss": 0.6177,
+      "step": 150
+    },
+    {
+      "epoch": 6.4,
+      "grad_norm": 14.1875,
+      "learning_rate": 2.35e-05,
+      "loss": 0.3576,
+      "step": 160
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 13.375,
+      "learning_rate": 2.1833333333333333e-05,
+      "loss": 0.3831,
+      "step": 170
+    },
+    {
+      "epoch": 7.2,
+      "grad_norm": 11.25,
+      "learning_rate": 2.0166666666666668e-05,
+      "loss": 0.2907,
+      "step": 180
+    },
+    {
+      "epoch": 7.6,
+      "grad_norm": 8.75,
+      "learning_rate": 1.85e-05,
+      "loss": 0.2107,
+      "step": 190
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 13.375,
+      "learning_rate": 1.6833333333333334e-05,
+      "loss": 0.2369,
+      "step": 200
+    },
+    {
+      "epoch": 8.4,
+      "grad_norm": 5.84375,
+      "learning_rate": 1.5166666666666668e-05,
+      "loss": 0.1433,
+      "step": 210
+    },
+    {
+      "epoch": 8.8,
+      "grad_norm": 5.5,
+      "learning_rate": 1.3500000000000001e-05,
+      "loss": 0.159,
+      "step": 220
+    },
+    {
+      "epoch": 9.2,
+      "grad_norm": 3.3125,
+      "learning_rate": 1.1833333333333334e-05,
+      "loss": 0.1216,
+      "step": 230
+    },
+    {
+      "epoch": 9.6,
+      "grad_norm": 5.03125,
+      "learning_rate": 1.0166666666666667e-05,
+      "loss": 0.0976,
+      "step": 240
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.9375,
+      "learning_rate": 8.500000000000002e-06,
+      "loss": 0.0994,
+      "step": 250
+    },
+    {
+      "epoch": 10.4,
+      "grad_norm": 3.140625,
+      "learning_rate": 6.833333333333333e-06,
+      "loss": 0.0757,
+      "step": 260
+    },
+    {
+      "epoch": 10.8,
+      "grad_norm": 6.3125,
+      "learning_rate": 5.166666666666667e-06,
+      "loss": 0.0823,
+      "step": 270
+    },
+    {
+      "epoch": 11.2,
+      "grad_norm": 1.9921875,
+      "learning_rate": 3.5000000000000004e-06,
+      "loss": 0.0683,
+      "step": 280
+    },
+    {
+      "epoch": 11.6,
+      "grad_norm": 2.234375,
+      "learning_rate": 1.8333333333333335e-06,
+      "loss": 0.0657,
+      "step": 290
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 2.484375,
+      "learning_rate": 1.6666666666666668e-07,
+      "loss": 0.0702,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 643181012582400.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4742684a093fc361873457fae1211104c151d4d7203b326aafde35d86d727093
+size 5777

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a67a16229c3a8e5242fae3d047b744f800596df5ae07b946778f74589cfbd0
+oid sha256:34a639938f53f443c0dc92996c1fea7ea8618b2deeb5f92b5cf41d16551951f2
 size 1999811208

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f47d9dfeea297f70054819c45ec532a1a9cc3bfad2833427ed1061da98947ec
+oid sha256:4742684a093fc361873457fae1211104c151d4d7203b326aafde35d86d727093
 size 5777