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:be2452c4d668cac0bb2251339bd6ee818fa1bb921c81a17f5cc9f1602c2cf14c
+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 sha256:4f017b10bf305a279d0e9025770a5d7e84136d20df1171a7f4fa1e2277914aab
+size 47425352

checkpoint-25/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0910be81df074e1f6268480a7f559dfba60b25e3690ef51cd70f55700fe968
+size 14244

checkpoint-25/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a05716f05747fb967268b6b65bee49602693de25bf95ae9c915a7eff48a89265
+size 1064

checkpoint-25/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4,
+  "eval_steps": 10,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": NaN,
+      "learning_rate": 0.000168,
+      "loss": 5.0883,
+      "step": 5
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 47.44880294799805,
+      "learning_rate": 0.000152,
+      "loss": 1.8313,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.8116276264190674,
+      "eval_runtime": 65.2786,
+      "eval_samples_per_second": 3.064,
+      "eval_steps_per_second": 1.532,
+      "step": 10
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 8.983357429504395,
+      "learning_rate": 0.00011200000000000001,
+      "loss": 0.5976,
+      "step": 15
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.9880592823028564,
+      "learning_rate": 7.2e-05,
+      "loss": 0.357,
+      "step": 20
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.3371765613555908,
+      "eval_runtime": 64.2071,
+      "eval_samples_per_second": 3.115,
+      "eval_steps_per_second": 1.557,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 3.457772731781006,
+      "learning_rate": 3.2000000000000005e-05,
+      "loss": 0.284,
+      "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": 1864510458066432.0,
+  "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:d17ca6cee48eb04db7c95b0c6730414410815aa88689042af60b4ff5b66c4572
+size 5176