Training in progress, step 6000, checkpoint

checkpoint-6000/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-6000/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-6000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:438231d10956ac19e5f1032435645f211ccab3e5906e478ef11e612c42a485f3
+size 956835520

checkpoint-6000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80eaaf092c1a57d01bc09ea39e897efe4f4f3718e4aac534b3d83ebcad23273b
+size 1909212608

checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4adb78bb444b06355a1cdfa18ec790a723b83f3fdf6add3690901cf286b2e3c
+size 14244

checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a8ce85872e797e4bdc165b275df9b69a2c324fd545ea3f403049fb87eb39eac
+size 1064

checkpoint-6000/trainer_state.json

@@ -0,0 +1,261 @@
+{
+  "best_metric": 0.4623475670814514,
+  "best_model_checkpoint": "./Vit-GPT2-COCO2017Flickr-80k-08/checkpoint-3500",
+  "epoch": 1.2,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "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
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.8613843321800232,
+      "learning_rate": 4e-05,
+      "loss": 0.3623,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6,
+      "eval_gen_len": 12.025,
+      "eval_loss": 0.4671708345413208,
+      "eval_rouge1": 40.1643,
+      "eval_rouge2": 14.978,
+      "eval_rougeL": 36.3002,
+      "eval_rougeLsum": 36.3232,
+      "eval_runtime": 451.1814,
+      "eval_samples_per_second": 8.866,
+      "eval_steps_per_second": 2.216,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.8106393814086914,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.3676,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7,
+      "eval_gen_len": 11.815,
+      "eval_loss": 0.4623475670814514,
+      "eval_rouge1": 40.5036,
+      "eval_rouge2": 15.3751,
+      "eval_rougeL": 36.8369,
+      "eval_rougeLsum": 36.867,
+      "eval_runtime": 458.4461,
+      "eval_samples_per_second": 8.725,
+      "eval_steps_per_second": 2.181,
+      "step": 3500
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.914828360080719,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.3613,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8,
+      "eval_gen_len": 12.054,
+      "eval_loss": 0.46470996737480164,
+      "eval_rouge1": 40.4078,
+      "eval_rouge2": 15.3105,
+      "eval_rougeL": 36.65,
+      "eval_rougeLsum": 36.6732,
+      "eval_runtime": 457.1563,
+      "eval_samples_per_second": 8.75,
+      "eval_steps_per_second": 2.187,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.8004090189933777,
+      "learning_rate": 3.5e-05,
+      "loss": 0.3539,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9,
+      "eval_gen_len": 11.904,
+      "eval_loss": 0.46335914731025696,
+      "eval_rouge1": 40.3794,
+      "eval_rouge2": 15.233,
+      "eval_rougeL": 36.7155,
+      "eval_rougeLsum": 36.7435,
+      "eval_runtime": 445.5568,
+      "eval_samples_per_second": 8.978,
+      "eval_steps_per_second": 2.244,
+      "step": 4500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.876920223236084,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.3481,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 11.738,
+      "eval_loss": 0.46441808342933655,
+      "eval_rouge1": 40.037,
+      "eval_rouge2": 14.8477,
+      "eval_rougeL": 36.3648,
+      "eval_rougeLsum": 36.3903,
+      "eval_runtime": 442.7978,
+      "eval_samples_per_second": 9.033,
+      "eval_steps_per_second": 2.258,
+      "step": 5000
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.9966852068901062,
+      "learning_rate": 3.1666666666666666e-05,
+      "loss": 0.2889,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1,
+      "eval_gen_len": 11.55,
+      "eval_loss": 0.4897365868091583,
+      "eval_rouge1": 40.1394,
+      "eval_rouge2": 14.7595,
+      "eval_rougeL": 36.4428,
+      "eval_rougeLsum": 36.4696,
+      "eval_runtime": 431.6652,
+      "eval_samples_per_second": 9.266,
+      "eval_steps_per_second": 2.317,
+      "step": 5500
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.857021152973175,
+      "learning_rate": 3e-05,
+      "loss": 0.2908,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2,
+      "eval_gen_len": 11.98225,
+      "eval_loss": 0.48649004101753235,
+      "eval_rouge1": 40.0479,
+      "eval_rouge2": 14.8181,
+      "eval_rougeL": 36.316,
+      "eval_rougeLsum": 36.3519,
+      "eval_runtime": 438.3532,
+      "eval_samples_per_second": 9.125,
+      "eval_steps_per_second": 2.281,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.7324533547532288e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6000/training_args.bin

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