Training in progress, step 53

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a002b108c20db6f1b4b8e74d165da48f306b75bbc322a1a82120a7ba22d6d33
+oid sha256:196b3198d4be453d3c50b2f13f9b9abee773d21c8da0be6adc0a0ba6bc553844
 size 901693336

tmp-checkpoint-477/config.json

@@ -0,0 +1,172 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "klue/bert-base",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "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": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "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,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
+  },
+  "decoder_start_token_id": 2,
+  "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
+  },
+  "is_encoder_decoder": true,
+  "max_length": 50,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2"
+}

tmp-checkpoint-477/generation_config.json

@@ -0,0 +1,5 @@
+{
+  "_from_model_config": true,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

tmp-checkpoint-477/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40b5dade20f27383a15987d5f4527814886ee0409017425b3e5ccc5d739d881
+size 901693336

tmp-checkpoint-477/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1657a2c4da6bd87f3060e14d5883f0d57518d84fd2dde1fa0531bca4a9af2a49
+size 1803693424

tmp-checkpoint-477/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7e1e2d686de75e6dbd295eb41ca863976241ff450acb1a7e980278e05c6c49
+size 14244

tmp-checkpoint-477/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce093ac07f5d6d4c3d196716ca4f4f8d06a87b1446d92603c86350e4990c639f
+size 1064

tmp-checkpoint-477/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_metric": 1.3590947389602661,
+  "best_model_checkpoint": "batch32_1e_5_VED/checkpoint-477",
+  "epoch": 8.91588785046729,
+  "eval_steps": 53,
+  "global_step": 477,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.99,
+      "learning_rate": 9.9e-06,
+      "loss": 5.1065,
+      "step": 53
+    },
+    {
+      "epoch": 0.99,
+      "eval_bleu": 0.0,
+      "eval_loss": 3.3200461864471436,
+      "eval_meteor": 0.09540837398436158,
+      "eval_rouge-l": 0.2812177477718752,
+      "eval_runtime": 119.5725,
+      "eval_samples_per_second": 6.331,
+      "eval_steps_per_second": 1.589,
+      "step": 53
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 9.800000000000001e-06,
+      "loss": 2.8847,
+      "step": 106
+    },
+    {
+      "epoch": 1.98,
+      "eval_bleu": 0.012973286002528122,
+      "eval_loss": 2.272148847579956,
+      "eval_meteor": 0.14245785226015273,
+      "eval_rouge-l": 0.2968901288707194,
+      "eval_runtime": 49.2416,
+      "eval_samples_per_second": 15.373,
+      "eval_steps_per_second": 3.859,
+      "step": 106
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 9.7e-06,
+      "loss": 2.2103,
+      "step": 159
+    },
+    {
+      "epoch": 2.97,
+      "eval_bleu": 0.030473187586190942,
+      "eval_loss": 1.9050257205963135,
+      "eval_meteor": 0.1878936938586751,
+      "eval_rouge-l": 0.33559049640535077,
+      "eval_runtime": 49.8376,
+      "eval_samples_per_second": 15.189,
+      "eval_steps_per_second": 3.812,
+      "step": 159
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 1.912,
+      "step": 212
+    },
+    {
+      "epoch": 3.96,
+      "eval_bleu": 0.04192188158953473,
+      "eval_loss": 1.7162450551986694,
+      "eval_meteor": 0.22255287713312594,
+      "eval_rouge-l": 0.3599682615987815,
+      "eval_runtime": 50.0168,
+      "eval_samples_per_second": 15.135,
+      "eval_steps_per_second": 3.799,
+      "step": 212
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 9.5e-06,
+      "loss": 1.7459,
+      "step": 265
+    },
+    {
+      "epoch": 4.95,
+      "eval_bleu": 0.0490495203639936,
+      "eval_loss": 1.5971415042877197,
+      "eval_meteor": 0.24389844343929945,
+      "eval_rouge-l": 0.37372403459707215,
+      "eval_runtime": 49.4077,
+      "eval_samples_per_second": 15.322,
+      "eval_steps_per_second": 3.846,
+      "step": 265
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 9.4e-06,
+      "loss": 1.6256,
+      "step": 318
+    },
+    {
+      "epoch": 5.94,
+      "eval_bleu": 0.056020605839494524,
+      "eval_loss": 1.5170336961746216,
+      "eval_meteor": 0.25645713891657596,
+      "eval_rouge-l": 0.37995731200625377,
+      "eval_runtime": 50.5532,
+      "eval_samples_per_second": 14.974,
+      "eval_steps_per_second": 3.758,
+      "step": 318
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 9.3e-06,
+      "loss": 1.533,
+      "step": 371
+    },
+    {
+      "epoch": 6.93,
+      "eval_bleu": 0.06304585105562827,
+      "eval_loss": 1.4515591859817505,
+      "eval_meteor": 0.27298702738798486,
+      "eval_rouge-l": 0.38411920753146567,
+      "eval_runtime": 49.065,
+      "eval_samples_per_second": 15.429,
+      "eval_steps_per_second": 3.872,
+      "step": 371
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 1.463,
+      "step": 424
+    },
+    {
+      "epoch": 7.93,
+      "eval_bleu": 0.06671158142206053,
+      "eval_loss": 1.3997350931167603,
+      "eval_meteor": 0.27980688079271815,
+      "eval_rouge-l": 0.3945394499882324,
+      "eval_runtime": 50.5781,
+      "eval_samples_per_second": 14.967,
+      "eval_steps_per_second": 3.757,
+      "step": 424
+    },
+    {
+      "epoch": 8.92,
+      "learning_rate": 9.100000000000001e-06,
+      "loss": 1.4072,
+      "step": 477
+    },
+    {
+      "epoch": 8.92,
+      "eval_bleu": 0.07361803483343807,
+      "eval_loss": 1.3590947389602661,
+      "eval_meteor": 0.28844799537676097,
+      "eval_rouge-l": 0.4029055929345029,
+      "eval_runtime": 51.3522,
+      "eval_samples_per_second": 14.741,
+      "eval_steps_per_second": 3.7,
+      "step": 477
+    }
+  ],
+  "logging_steps": 53,
+  "max_steps": 5300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 53,
+  "total_flos": 1.0989098432282493e+19,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

tmp-checkpoint-477/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1eb7bd553d3de3e6965e7489d73b1f999a18834d8fbc904ee6bed7cd6d325bd
+size 4664