End of training

README.md

@@ -0,0 +1,56 @@
+---
+license: apache-2.0
+base_model: HuggingFaceM4/idefics2-8b
+tags:
+- generated_from_trainer
+model-index:
+- name: working
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# working
+
+This model is a fine-tuned version of [HuggingFaceM4/idefics2-8b](https://huggingface.co/HuggingFaceM4/idefics2-8b) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 2
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.0.dev0
+- Pytorch 2.1.2
+- Datasets 2.18.0
+- Tokenizers 0.19.1

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": ".*(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:e04f63b0c5591894d9ac603630a0ae89a7e7889d3d5e38f3697f668fd342677e
+size 99375704

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"
+}

trainer_state.json

@@ -0,0 +1,37 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.92,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.9292863011360168,
+      "learning_rate": 4.230769230769231e-05,
+      "loss": 0.4778,
+      "step": 25
+    },
+    {
+      "epoch": 1.92,
+      "step": 36,
+      "total_flos": 3.444055882369344e+16,
+      "train_loss": 0.35278993679417503,
+      "train_runtime": 5731.2572,
+      "train_samples_per_second": 0.105,
+      "train_steps_per_second": 0.006
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 36,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "total_flos": 3.444055882369344e+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:eb16d4730102babb6770d0fbe676cebdf0e12f0900f21c4aae99b6b2e03031c2
+size 4984