Upload folder using huggingface_hub

README.md

@@ -0,0 +1,10 @@
+---
+library_name: peft
+---
+## Training procedure
+
+### Framework versions
+
+- PEFT 0.4.0
+
+- PEFT 0.4.0

adapter_config.json

@@ -0,0 +1,83 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "q-future/one-align",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 256,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "revision": null,
+  "target_modules": [
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.10.self_attn.v_proj.multiway.1",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.6.self_attn.v_proj.multiway.1",
+    "model.layers.17.self_attn.v_proj.multiway.1",
+    "model.layers.20.self_attn.v_proj.multiway.1",
+    "model.layers.24.self_attn.v_proj.multiway.1",
+    "model.layers.13.self_attn.v_proj.multiway.1",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.21.self_attn.v_proj.multiway.1",
+    "model.layers.15.self_attn.v_proj.multiway.1",
+    "model.layers.2.self_attn.v_proj.multiway.1",
+    "model.layers.27.self_attn.v_proj.multiway.1",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.28.self_attn.v_proj.multiway.1",
+    "model.layers.30.self_attn.q_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.22.self_attn.v_proj.multiway.1",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.25.self_attn.v_proj.multiway.1",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.18.self_attn.v_proj.multiway.1",
+    "model.layers.31.self_attn.q_proj",
+    "model.layers.0.self_attn.v_proj.multiway.1",
+    "model.layers.1.self_attn.v_proj.multiway.1",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.30.self_attn.v_proj.multiway.1",
+    "model.layers.29.self_attn.v_proj.multiway.1",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.31.self_attn.v_proj.multiway.1",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.5.self_attn.v_proj.multiway.1",
+    "model.layers.26.self_attn.v_proj.multiway.1",
+    "model.layers.8.self_attn.v_proj.multiway.1",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.7.self_attn.v_proj.multiway.1",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.4.self_attn.v_proj.multiway.1",
+    "model.layers.14.self_attn.v_proj.multiway.1",
+    "model.layers.16.self_attn.v_proj.multiway.1",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.28.self_attn.q_proj",
+    "model.layers.9.self_attn.v_proj.multiway.1",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.3.self_attn.v_proj.multiway.1",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.12.self_attn.v_proj.multiway.1",
+    "model.layers.19.self_attn.v_proj.multiway.1",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.11.self_attn.v_proj.multiway.1",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.23.self_attn.v_proj.multiway.1",
+    "model.layers.29.self_attn.q_proj",
+    "model.layers.18.self_attn.q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced90ec0bc072c12d9792c22e5bff526134b04ba1075fe7474915b8725ea47ac
+size 134262669

config.json

@@ -0,0 +1,192 @@
+{
+  "_name_or_path": "q-future/one-align",
+  "architectures": [
+    "MPLUGOwl2LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "q-future/one-align--configuration_mplug_owl2.MPLUGOwl2Config",
+    "AutoModel": "q-future/one-align--modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM",
+    "AutoModelForCausalLM": "q-future/one-align--modeling_mplug_owl2.MPLUGOwl2LlamaForCausalLM"
+  },
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_vision_model": false,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "image_grid_pinpoints": null,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "mplug_owl2",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.1",
+  "tune_visual_abstractor": true,
+  "use_cache": true,
+  "visual_abstractor_lr": 2e-05,
+  "visual_config": {
+    "visual_abstractor": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_probs_dropout_prob": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_hidden_size": 1024,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "grid_size": 32,
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "initializer_range": 0.02,
+      "intermediate_size": 2816,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "mplug_owl_visual_abstract",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_hidden_layers": 6,
+      "num_learnable_queries": 64,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "prefix": null,
+      "problem_type": null,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.28.1",
+      "typical_p": 1.0,
+      "use_bfloat16": false
+    },
+    "visual_model": {
+      "_name_or_path": "",
+      "add_cross_attention": false,
+      "architectures": null,
+      "attention_dropout": 0.0,
+      "bad_words_ids": null,
+      "begin_suppress_tokens": null,
+      "bos_token_id": null,
+      "chunk_size_feed_forward": 0,
+      "cross_attention_hidden_size": null,
+      "decoder_start_token_id": null,
+      "diversity_penalty": 0.0,
+      "do_sample": false,
+      "early_stopping": false,
+      "encoder_no_repeat_ngram_size": 0,
+      "eos_token_id": null,
+      "exponential_decay_length_penalty": null,
+      "finetuning_task": null,
+      "forced_bos_token_id": null,
+      "forced_eos_token_id": null,
+      "hidden_act": "quick_gelu",
+      "hidden_size": 1024,
+      "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+      },
+      "image_size": 448,
+      "initializer_factor": 1.0,
+      "initializer_range": 0.02,
+      "intermediate_size": 4096,
+      "is_decoder": false,
+      "is_encoder_decoder": false,
+      "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+      },
+      "layer_norm_eps": 1e-06,
+      "length_penalty": 1.0,
+      "max_length": 20,
+      "min_length": 0,
+      "model_type": "mplug_owl_vision_model",
+      "no_repeat_ngram_size": 0,
+      "num_attention_heads": 16,
+      "num_beam_groups": 1,
+      "num_beams": 1,
+      "num_channels": 3,
+      "num_hidden_layers": 24,
+      "num_return_sequences": 1,
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "output_scores": false,
+      "pad_token_id": null,
+      "patch_size": 14,
+      "prefix": null,
+      "problem_type": null,
+      "projection_dim": 768,
+      "pruned_heads": {},
+      "remove_invalid_values": false,
+      "repetition_penalty": 1.0,
+      "return_dict": true,
+      "return_dict_in_generate": false,
+      "sep_token_id": null,
+      "suppress_tokens": null,
+      "task_specific_params": null,
+      "temperature": 1.0,
+      "tf_legacy_loss": false,
+      "tie_encoder_decoder": false,
+      "tie_word_embeddings": true,
+      "tokenizer_class": null,
+      "top_k": 50,
+      "top_p": 1.0,
+      "torch_dtype": null,
+      "torchscript": false,
+      "transformers_version": "4.28.1",
+      "typical_p": 1.0,
+      "use_bfloat16": false,
+      "use_flash_attn": false
+    }
+  },
+  "vocab_size": 32000
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9a6301cac7ed0e6cefe54e66ef8d1c29415f91308bfc8012be40ddd4ac356c
+size 162998185

preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 448,
+  "do_center_crop": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 448
+}
+

trainer_state.json

@@ -0,0 +1,366 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9846153846153847,
+  "eval_steps": 500,
+  "global_step": 56,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001,
+      "loss": 0.1065,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002,
+      "loss": 0.1299,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00019983081582712685,
+      "loss": 0.145,
+      "step": 3
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019932383577419432,
+      "loss": 0.1167,
+      "step": 4
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019848077530122083,
+      "loss": 0.1202,
+      "step": 5
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 0.1051,
+      "step": 6
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001957989512315489,
+      "loss": 0.1127,
+      "step": 7
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 0.0987,
+      "step": 8
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019182161068802741,
+      "loss": 0.0992,
+      "step": 9
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00018936326403234125,
+      "loss": 0.129,
+      "step": 10
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 0.0898,
+      "step": 11
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018354878114129367,
+      "loss": 0.1101,
+      "step": 12
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0001802123192755044,
+      "loss": 0.0951,
+      "step": 13
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 0.0916,
+      "step": 14
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017273736415730488,
+      "loss": 0.0969,
+      "step": 15
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 0.082,
+      "step": 16
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00016427876096865394,
+      "loss": 0.0842,
+      "step": 17
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00015971585917027862,
+      "loss": 0.0923,
+      "step": 18
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0001549508978070806,
+      "loss": 0.0867,
+      "step": 19
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.1179,
+      "step": 20
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00014487991802004623,
+      "loss": 0.1062,
+      "step": 21
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001396079766039157,
+      "loss": 0.1287,
+      "step": 22
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00013420201433256689,
+      "loss": 0.0968,
+      "step": 23
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00012868032327110904,
+      "loss": 0.0906,
+      "step": 24
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00012306158707424403,
+      "loss": 0.0819,
+      "step": 25
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.0878,
+      "step": 26
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011160929141252303,
+      "loss": 0.0793,
+      "step": 27
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010581448289104758,
+      "loss": 0.099,
+      "step": 28
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0001,
+      "loss": 0.1027,
+      "step": 29
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.418551710895243e-05,
+      "loss": 0.093,
+      "step": 30
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.839070858747697e-05,
+      "loss": 0.0949,
+      "step": 31
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 0.0938,
+      "step": 32
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.693841292575598e-05,
+      "loss": 0.0996,
+      "step": 33
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.131967672889101e-05,
+      "loss": 0.0976,
+      "step": 34
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.579798566743314e-05,
+      "loss": 0.1112,
+      "step": 35
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.039202339608432e-05,
+      "loss": 0.0932,
+      "step": 36
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.5120081979953785e-05,
+      "loss": 0.1011,
+      "step": 37
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0911,
+      "step": 38
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.50491021929194e-05,
+      "loss": 0.0997,
+      "step": 39
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.028414082972141e-05,
+      "loss": 0.0987,
+      "step": 40
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 0.0935,
+      "step": 41
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.137583621312665e-05,
+      "loss": 0.1054,
+      "step": 42
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7262635842695127e-05,
+      "loss": 0.0869,
+      "step": 43
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.095,
+      "step": 44
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.9787680724495617e-05,
+      "loss": 0.1,
+      "step": 45
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.6451218858706374e-05,
+      "loss": 0.0985,
+      "step": 46
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.088,
+      "step": 47
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.0636735967658784e-05,
+      "loss": 0.0777,
+      "step": 48
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 8.178389311972612e-06,
+      "loss": 0.0844,
+      "step": 49
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.0971,
+      "step": 50
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.20104876845111e-06,
+      "loss": 0.0946,
+      "step": 51
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 2.6955129420176196e-06,
+      "loss": 0.0853,
+      "step": 52
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.0889,
+      "step": 53
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 6.761642258056978e-07,
+      "loss": 0.0927,
+      "step": 54
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6918417287318245e-07,
+      "loss": 0.0971,
+      "step": 55
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0,
+      "loss": 0.1002,
+      "step": 56
+    },
+    {
+      "epoch": 0.98,
+      "step": 56,
+      "total_flos": 1401921699840.0,
+      "train_loss": 0.0989542007446289,
+      "train_runtime": 4591.4133,
+      "train_samples_per_second": 0.791,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 56,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 800,
+  "total_flos": 1401921699840.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}