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 sha256:23e1c9c686cc80f200f1186faebffeca933a9ef8a1af677ba574b56dbbf4781d
+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": "4.41.0.dev0"
+}

checkpoint-25/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8900f9e55909effa1a86409c500e7a0032ebe21e71f207e9bbf1b39dcd9dd6ba
+size 47425352

checkpoint-25/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9074f921536ffa293f89e0b77f5c1ad4c03c94210763584f8596bec2ffe23fba
+size 14244

checkpoint-25/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630fe59a784956405be1a950d9ce52e5bf6a2f1c12f3a8bd4f3869766a5850cd
+size 1064

checkpoint-25/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "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": 17.099790573120117,
+      "learning_rate": 0.000168,
+      "loss": 3.0989,
+      "step": 5
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 29.087034225463867,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 0.9182,
+      "step": 10
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.9490247964859009,
+      "eval_runtime": 309.484,
+      "eval_samples_per_second": 0.646,
+      "eval_steps_per_second": 0.323,
+      "step": 10
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 15.529748916625977,
+      "learning_rate": 9.6e-05,
+      "loss": 0.8735,
+      "step": 15
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 14.30168342590332,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.8218,
+      "step": 20
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.9457312226295471,
+      "eval_runtime": 308.6735,
+      "eval_samples_per_second": 0.648,
+      "eval_steps_per_second": 0.324,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 11.396862983703613,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.693,
+      "step": 25
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "total_flos": 2002777078676352.0,
+  "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:b5d639c2d9b07a270b7b1a633a2862b78a9ed053404fc040cd10109ad7071cd1
+size 4984