Upload folder using huggingface_hub

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceM4/idefics2-8b",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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_bias": false,
+  "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
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:068aae5d0c77389ac936394e6e1e51828ce7dbfddc32b35360aa741102391ac5
+size 93378688

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": "4.48.0.dev0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73055732f94173d88649be38d1d0bb0ee3a6955edb6f4b9ae82b888c6ff73bdd
+size 187031330

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdcd4833fd052e5c9ba87b1f46218b43ed44d1629e5173241cdf27417b09254e
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc05265a8fb71c036a181f9a95927c2d349e77bd2dfa09f654d934bb618d8bb3
+size 1064

trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.928,
+  "eval_steps": 500,
+  "global_step": 310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "grad_norm": 81.96082305908203,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 58.2628,
+      "step": 25
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 36.536678314208984,
+      "learning_rate": 9.4e-05,
+      "loss": 2.1587,
+      "step": 50
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 30.483903884887695,
+      "learning_rate": 9.153846153846155e-05,
+      "loss": 1.7083,
+      "step": 75
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 24.5040225982666,
+      "learning_rate": 8.192307692307693e-05,
+      "loss": 1.5561,
+      "step": 100
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 23.667861938476562,
+      "learning_rate": 7.23076923076923e-05,
+      "loss": 1.3954,
+      "step": 125
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 19.942045211791992,
+      "learning_rate": 6.307692307692308e-05,
+      "loss": 0.7723,
+      "step": 150
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 22.397857666015625,
+      "learning_rate": 5.346153846153846e-05,
+      "loss": 0.7796,
+      "step": 175
+    },
+    {
+      "epoch": 3.176,
+      "grad_norm": 17.26620101928711,
+      "learning_rate": 4.384615384615385e-05,
+      "loss": 0.6446,
+      "step": 200
+    },
+    {
+      "epoch": 3.576,
+      "grad_norm": 15.945826530456543,
+      "learning_rate": 3.4230769230769234e-05,
+      "loss": 0.4756,
+      "step": 225
+    },
+    {
+      "epoch": 3.976,
+      "grad_norm": 20.171337127685547,
+      "learning_rate": 2.461538461538462e-05,
+      "loss": 0.4989,
+      "step": 250
+    },
+    {
+      "epoch": 4.368,
+      "grad_norm": 14.564436912536621,
+      "learning_rate": 1.5e-05,
+      "loss": 0.2846,
+      "step": 275
+    },
+    {
+      "epoch": 4.768,
+      "grad_norm": 15.490738868713379,
+      "learning_rate": 5.3846153846153855e-06,
+      "loss": 0.3187,
+      "step": 300
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 2.4681387557982144e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea690f467f3a18fa3bbdf739bdcdbf01448dfe968ce14b534a8133312948b08d
+size 5368