Pushed the IDEFICS2 fine-tuned model.

checkpoint-25/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceM4/idefics2-8b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": false,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": ".*(text_model|modality_projection|perceiver_resampler).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$",
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-25/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87cc62bbca6a2cee104071467be3cf86d3e259f60c4aa703d612021b46cbf803
+size 93378688

checkpoint-25/config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Idefics2ForConditionalGeneration"
+  ],
+  "image_token_id": 32001,
+  "model_type": "idefics2",
+  "perceiver_config": {
+    "model_type": "idefics2"
+  },
+  "text_config": {
+    "max_position_embeddings": 32768,
+    "model_type": "mistral",
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-05,
+    "vocab_size": 32003
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vision_config": {
+    "hidden_size": 1152,
+    "image_size": 980,
+    "intermediate_size": 4304,
+    "model_type": "idefics2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 27,
+    "patch_size": 14
+  }
+}

checkpoint-25/generation_config.json

@@ -0,0 +1,18 @@
+{
+  "_from_model_config": true,
+  "bad_words_ids": [
+    [
+      32000
+    ],
+    [
+      32001
+    ]
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2,
+    32002
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "4.41.1"
+}

checkpoint-25/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:291a71b357a294f90749cce8fed801acd6609c512ae1591132ff16e3b7cec7d6
+size 47425352

checkpoint-25/preprocessor_config.json

@@ -0,0 +1,26 @@
+{
+  "do_convert_rgb": true,
+  "do_image_splitting": true,
+  "do_normalize": true,
+  "do_pad": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Idefics2ImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "Idefics2Processor",
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 980,
+    "shortest_edge": 378
+  }
+}

checkpoint-25/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3874113d512a94b4ef611411d7e032768aac4c7ab19904a72a34ea15dcec7c24
+size 14244

checkpoint-25/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8531775f4e5c3819ae81b2ea1cfeb7e992dc0ca011334fb9ed6fb83e3392e473
+size 1064

checkpoint-25/trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.225806451612903,
+  "eval_steps": 10,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 38.74126434326172,
+      "learning_rate": 6e-06,
+      "loss": 2.9734,
+      "step": 10
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "eval_loss": 1.578683853149414,
+      "eval_runtime": 13.1475,
+      "eval_samples_per_second": 1.521,
+      "eval_steps_per_second": 0.761,
+      "step": 10
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 39.226219177246094,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.2261,
+      "step": 20
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "eval_loss": 1.026258111000061,
+      "eval_runtime": 13.3029,
+      "eval_samples_per_second": 1.503,
+      "eval_steps_per_second": 0.752,
+      "step": 20
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2048335432805376.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-25/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7512a38cb2986a436d0d3daee19239a987baa3fa4d9adfbfc8621ab2301ed7b
+size 5112