Training in progress, step 3000, checkpoint

checkpoint-3000/config.json

@@ -0,0 +1,188 @@
+{
+  "_name_or_path": "nlpconnect/vit-gpt2-image-captioning",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "bos_token_id": 50256,
+  "decoder": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": 50256,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "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": 50256,
+    "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": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_attn_implementation_autoset": false,
+    "_name_or_path": "",
+    "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": 50256,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 50256,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0"
+}

checkpoint-3000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 50256,
+  "decoder_start_token_id": 50256,
+  "eos_token_id": 50256,
+  "pad_token_id": 50256,
+  "transformers_version": "4.47.0"
+}

checkpoint-3000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7896081d3fe63a73f42b5e440fbb563ec215370794d64c82f48c87b010677f21
+size 956835520

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4e85e060923fc07822666a5e5bd624ac0ea59e7f9eb649bd2feba8eb761f9d
+size 1909212608

checkpoint-3000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a0ae297bee8112f02f9ed288faebac90d6a6f1d26ff8f7d2dee7dbe27dd7b6
+size 14244

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f09a75b239fc8f6ebfc29c66426173f6e56349666432cc69d0e01e13d38afe0
+size 1064

checkpoint-3000/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-3000/tokenizer_config.json

@@ -0,0 +1,28 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "max_length": 32,
+  "model_max_length": 1024,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-3000/trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_metric": 0.17945721745491028,
+  "best_model_checkpoint": "./Vit-GPT2-UCA-UCF-06/checkpoint-1500",
+  "epoch": 1.954552858771787,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3257859586251833,
+      "grad_norm": 1.1044154167175293,
+      "learning_rate": 4.456757931334203e-05,
+      "loss": 0.8073,
+      "step": 500
+    },
+    {
+      "epoch": 0.3257859586251833,
+      "eval_gen_len": 17.309,
+      "eval_loss": 0.18400029838085175,
+      "eval_rouge1": 31.5942,
+      "eval_rouge2": 9.2754,
+      "eval_rougeL": 27.0997,
+      "eval_rougeLsum": 27.4879,
+      "eval_runtime": 109.2425,
+      "eval_samples_per_second": 9.154,
+      "eval_steps_per_second": 2.288,
+      "step": 500
+    },
+    {
+      "epoch": 0.6515719172503666,
+      "grad_norm": 1.2499775886535645,
+      "learning_rate": 3.913515862668405e-05,
+      "loss": 0.6562,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6515719172503666,
+      "eval_gen_len": 16.271,
+      "eval_loss": 0.18051931262016296,
+      "eval_rouge1": 31.3758,
+      "eval_rouge2": 9.5474,
+      "eval_rougeL": 26.788,
+      "eval_rougeLsum": 27.1031,
+      "eval_runtime": 103.3774,
+      "eval_samples_per_second": 9.673,
+      "eval_steps_per_second": 2.418,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9773578758755498,
+      "grad_norm": 1.0292741060256958,
+      "learning_rate": 3.370273794002607e-05,
+      "loss": 0.6123,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9773578758755498,
+      "eval_gen_len": 16.455,
+      "eval_loss": 0.17945721745491028,
+      "eval_rouge1": 32.219,
+      "eval_rouge2": 9.7783,
+      "eval_rougeL": 27.4235,
+      "eval_rougeLsum": 27.7537,
+      "eval_runtime": 109.2209,
+      "eval_samples_per_second": 9.156,
+      "eval_steps_per_second": 2.289,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3029809415214204,
+      "grad_norm": 0.9370392560958862,
+      "learning_rate": 2.82703172533681e-05,
+      "loss": 0.5502,
+      "step": 2000
+    },
+    {
+      "epoch": 1.3029809415214204,
+      "eval_gen_len": 15.66,
+      "eval_loss": 0.1821030229330063,
+      "eval_rouge1": 31.0914,
+      "eval_rouge2": 9.2688,
+      "eval_rougeL": 26.5321,
+      "eval_rougeLsum": 26.8962,
+      "eval_runtime": 111.0421,
+      "eval_samples_per_second": 9.006,
+      "eval_steps_per_second": 2.251,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6287669001466036,
+      "grad_norm": 0.932910680770874,
+      "learning_rate": 2.2837896566710127e-05,
+      "loss": 0.5281,
+      "step": 2500
+    },
+    {
+      "epoch": 1.6287669001466036,
+      "eval_gen_len": 16.042,
+      "eval_loss": 0.18320904672145844,
+      "eval_rouge1": 31.0119,
+      "eval_rouge2": 9.0876,
+      "eval_rougeL": 26.4645,
+      "eval_rougeLsum": 26.7925,
+      "eval_runtime": 106.3482,
+      "eval_samples_per_second": 9.403,
+      "eval_steps_per_second": 2.351,
+      "step": 2500
+    },
+    {
+      "epoch": 1.954552858771787,
+      "grad_norm": 1.2116119861602783,
+      "learning_rate": 1.740547588005215e-05,
+      "loss": 0.5085,
+      "step": 3000
+    },
+    {
+      "epoch": 1.954552858771787,
+      "eval_gen_len": 16.004,
+      "eval_loss": 0.18471209704875946,
+      "eval_rouge1": 31.0869,
+      "eval_rouge2": 9.0206,
+      "eval_rougeL": 26.2838,
+      "eval_rougeLsum": 26.6729,
+      "eval_runtime": 109.0184,
+      "eval_samples_per_second": 9.173,
+      "eval_steps_per_second": 2.293,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4602,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.661544918201663e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99aa4a4803a468942fc66f2059c656e6cdc3819d96b60bae24c8862f37ef905
+size 5496