Training in progress, step 2500, checkpoint

checkpoint-2500/config.json

@@ -0,0 +1,186 @@
+{
+  "_name_or_path": "nlpconnect/vit-gpt2-image-captioning",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "bos_token_id": 50256,
+  "decoder": {
+    "_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": {
+    "_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": "4.39.3"
+}

checkpoint-2500/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": "4.39.3"
+}

checkpoint-2500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2880e07dd16d1ff8f96ddb2c3db209c7cfc32ae6129bd9b629f3f723ecbfcd
+size 956835520

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9014638d83b3e41e6ded7f3ef34fb1d85d2cced373f982ea9f2e4ad99f2e27a
+size 1909212608

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86a8cf2c0b0902b925a40b8fe77afeca55aaad6d2168d0a628dec63a8b956cd
+size 14244

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b889028bc08b928851d38c15be1cde56bbc3640556ee89d4444bfeb832ab0582
+size 1064

checkpoint-2500/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": 0.4677760601043701,
+  "best_model_checkpoint": "./Vit-GPT2-COCO2017Flickr-80k-08/checkpoint-2000",
+  "epoch": 0.5,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.9981909990310669,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.3691,
+      "step": 500
+    },
+    {
+      "epoch": 0.1,
+      "eval_gen_len": 11.77575,
+      "eval_loss": 0.4729623794555664,
+      "eval_rouge1": 39.8086,
+      "eval_rouge2": 14.7674,
+      "eval_rougeL": 36.1546,
+      "eval_rougeLsum": 36.1739,
+      "eval_runtime": 459.5392,
+      "eval_samples_per_second": 8.704,
+      "eval_steps_per_second": 2.176,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8220647573471069,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.3706,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "eval_gen_len": 11.59775,
+      "eval_loss": 0.47387805581092834,
+      "eval_rouge1": 39.8972,
+      "eval_rouge2": 14.9064,
+      "eval_rougeL": 36.1193,
+      "eval_rougeLsum": 36.138,
+      "eval_runtime": 446.0956,
+      "eval_samples_per_second": 8.967,
+      "eval_steps_per_second": 2.242,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.052058219909668,
+      "learning_rate": 4.5e-05,
+      "loss": 0.3709,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3,
+      "eval_gen_len": 11.71025,
+      "eval_loss": 0.47592678666114807,
+      "eval_rouge1": 39.9874,
+      "eval_rouge2": 14.8528,
+      "eval_rougeL": 36.3155,
+      "eval_rougeLsum": 36.3317,
+      "eval_runtime": 466.5502,
+      "eval_samples_per_second": 8.574,
+      "eval_steps_per_second": 2.143,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.8642559051513672,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.3721,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4,
+      "eval_gen_len": 12.175,
+      "eval_loss": 0.4677760601043701,
+      "eval_rouge1": 39.7192,
+      "eval_rouge2": 14.5844,
+      "eval_rougeL": 35.8447,
+      "eval_rougeLsum": 35.8728,
+      "eval_runtime": 455.6895,
+      "eval_samples_per_second": 8.778,
+      "eval_steps_per_second": 2.194,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8769400715827942,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.3655,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5,
+      "eval_gen_len": 11.90025,
+      "eval_loss": 0.4683643877506256,
+      "eval_rouge1": 40.3132,
+      "eval_rouge2": 15.1157,
+      "eval_rougeL": 36.5749,
+      "eval_rougeLsum": 36.5823,
+      "eval_runtime": 449.7304,
+      "eval_samples_per_second": 8.894,
+      "eval_steps_per_second": 2.224,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7.21855564480512e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac3275bd5e74e49ac44a7270cea631cfc64b9085f7b8c623d9dad5ebdd62887a
+size 5112