Pushed the IDEFICS_mlc 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:b7bd2463f188c8eca62ff1bf5b8e93376f630c5663671e8794609eafeca04d72
+size 93378688

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": "4.45.0.dev0"
+}

checkpoint-25/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821045b050098b90f3694700ff6265fa538735f35aec6a8bdb294f9e8408644f
+size 47425352

checkpoint-25/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:319eb2092dd64ee0ffbe346a32d14e843470dc85244fc017370211a5dd2d2f59
+size 14244

checkpoint-25/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b1ece0846e2afe71b4b44981fd9a82ee7e8be48b72c44e6ff1c690617d2b724
+size 1064

checkpoint-25/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3125,
+  "eval_steps": 10,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0625,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 5.3433,
+      "step": 5
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 22.1121883392334,
+      "learning_rate": 0.00016,
+      "loss": 0.8498,
+      "step": 10
+    },
+    {
+      "epoch": 0.125,
+      "eval_loss": 0.46461257338523865,
+      "eval_runtime": 675.933,
+      "eval_samples_per_second": 0.473,
+      "eval_steps_per_second": 0.237,
+      "step": 10
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 5.5990471839904785,
+      "learning_rate": 0.00012,
+      "loss": 0.2796,
+      "step": 15
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.6768269538879395,
+      "learning_rate": 8e-05,
+      "loss": 0.0708,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.06857629865407944,
+      "eval_runtime": 677.5709,
+      "eval_samples_per_second": 0.472,
+      "eval_steps_per_second": 0.236,
+      "step": 20
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 1.486285924911499,
+      "learning_rate": 4e-05,
+      "loss": 0.0593,
+      "step": 25
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 1937423719150656.0,
+  "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 sha256:25496fe56f5353a7bb4b83694c97bccbb6c45d84f6db289821a907dd5f38a007
+size 5176