Training in progress, step 5000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,189 @@
+{
+  "_name_or_path": "ddobokki/vision-encoder-decoder-vit-gpt2-coco-ko",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "skt/kogpt2-base-v2",
+    "_num_labels": 1,
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "author": "Heewon Jeon(madjakarta@gmail.com)",
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "created_date": "2021-04-28",
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "id2label": {
+      "0": "LABEL_0"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "license": "CC-BY-NC-SA 4.0",
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 3,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "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,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 51200
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_name_or_path": "google/vit-base-patch16-224-in21k",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTModel"
+    ],
+    "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_no_repeat_ngram_size": 0,
+    "encoder_stride": 16,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "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,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "eos_token_id": 1,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "vocab_size": 51200
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 0,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 3,
+  "transformers_version": "4.42.3"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d9110422c3b26640261dc785e9b6989d3c913f8b478a6f48d3a23b84a1ede2d
+size 959732416

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c5a24f32c4c53426b5bbd40549706956c3582e9dfea8c7ee78415bf9c68859
+size 1919732806

last-checkpoint/preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c881ad54e2aae8feeb160e05a97e39cf1c147f9aae0937a1b7e41a0710f93d0
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08c589f3acbeec5c6e36834591171153e8af682ebbd66860ce42dbcde5e025a9
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.676727028839705,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1676727028839705,
+      "grad_norm": 0.24329866468906403,
+      "learning_rate": 4.83232729711603e-05,
+      "loss": 0.2725,
+      "step": 500
+    },
+    {
+      "epoch": 0.335345405767941,
+      "grad_norm": 0.3848712146282196,
+      "learning_rate": 4.6646545942320594e-05,
+      "loss": 0.2125,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5030181086519114,
+      "grad_norm": 0.3457760214805603,
+      "learning_rate": 4.4969818913480886e-05,
+      "loss": 0.1794,
+      "step": 1500
+    },
+    {
+      "epoch": 0.670690811535882,
+      "grad_norm": 0.4547400176525116,
+      "learning_rate": 4.3293091884641186e-05,
+      "loss": 0.1597,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8383635144198525,
+      "grad_norm": 0.37468263506889343,
+      "learning_rate": 4.161636485580148e-05,
+      "loss": 0.1498,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 100.0,
+      "eval_loss": 0.11297082155942917,
+      "eval_rouge1": 0.1508,
+      "eval_rouge2": 0.1508,
+      "eval_rougeL": 0.1508,
+      "eval_rougeLsum": 0.1508,
+      "eval_runtime": 1532.6018,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.217,
+      "step": 2982
+    },
+    {
+      "epoch": 1.0060362173038229,
+      "grad_norm": 0.40761449933052063,
+      "learning_rate": 3.993963782696177e-05,
+      "loss": 0.1293,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1737089201877935,
+      "grad_norm": 0.3620559573173523,
+      "learning_rate": 3.826291079812207e-05,
+      "loss": 0.1038,
+      "step": 3500
+    },
+    {
+      "epoch": 1.341381623071764,
+      "grad_norm": 0.3626340925693512,
+      "learning_rate": 3.658618376928236e-05,
+      "loss": 0.0899,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5090543259557343,
+      "grad_norm": 0.5226974487304688,
+      "learning_rate": 3.490945674044266e-05,
+      "loss": 0.0818,
+      "step": 4500
+    },
+    {
+      "epoch": 1.676727028839705,
+      "grad_norm": 0.4590921700000763,
+      "learning_rate": 3.323272971160295e-05,
+      "loss": 0.0746,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14910,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.6087364307291996e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3be77d244f10d48dc812b520eeb95e50cd4ecbd995ee8774502bcfbdb56d5c
+size 5368