Training in progress, step 9000, checkpoint

checkpoint-9000/config.json

@@ -0,0 +1,186 @@
+{
+  "_name_or_path": "NourFakih/Vit-GPT2-COCO2017Flickr-85k-11",
+  "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": "4.41.2"
+}

checkpoint-9000/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": "4.41.2"
+}

checkpoint-9000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abae961535f651b85f5f2d4e3c17d0f7c8709ae82f024f35d94ef55e89a83d0
+size 956835520

checkpoint-9000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:997df0099d312f0e3d52cee6ce752d7cd494b376a8ed77e7bc072b2e260a5991
+size 1909212608

checkpoint-9000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9a4be984830b96d882d05a61c873cf6c5b60799cb25345ca5bcc556a2fa0278
+size 14244

checkpoint-9000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200b9e2b053ab7df76baf353f77188cb90da3dda9e5a8adc152d4961103a7c97
+size 1064

checkpoint-9000/trainer_state.json

@@ -0,0 +1,393 @@
+{
+  "best_metric": 0.4608415365219116,
+  "best_model_checkpoint": "./Vit-GPT2-COCO2017Flickr-85k-11/checkpoint-4500",
+  "epoch": 1.6795745077913595,
+  "eval_steps": 500,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09330969487729775,
+      "grad_norm": 1.14389169216156,
+      "learning_rate": 4.8444693293517484e-05,
+      "loss": 0.378,
+      "step": 500
+    },
+    {
+      "epoch": 0.09330969487729775,
+      "eval_gen_len": 11.7725,
+      "eval_loss": 0.469292551279068,
+      "eval_rouge1": 40.2274,
+      "eval_rouge2": 15.0119,
+      "eval_rougeL": 36.4563,
+      "eval_rougeLsum": 36.4656,
+      "eval_runtime": 450.3853,
+      "eval_samples_per_second": 8.881,
+      "eval_steps_per_second": 2.22,
+      "step": 500
+    },
+    {
+      "epoch": 0.1866193897545955,
+      "grad_norm": 0.8436835408210754,
+      "learning_rate": 4.6889386587034965e-05,
+      "loss": 0.3748,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1866193897545955,
+      "eval_gen_len": 12.16675,
+      "eval_loss": 0.46400758624076843,
+      "eval_rouge1": 40.199,
+      "eval_rouge2": 15.321,
+      "eval_rougeL": 36.4279,
+      "eval_rougeLsum": 36.4457,
+      "eval_runtime": 431.1423,
+      "eval_samples_per_second": 9.278,
+      "eval_steps_per_second": 2.319,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27992908463189325,
+      "grad_norm": 0.8730084896087646,
+      "learning_rate": 4.5334079880552446e-05,
+      "loss": 0.374,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27992908463189325,
+      "eval_gen_len": 11.8,
+      "eval_loss": 0.4668748080730438,
+      "eval_rouge1": 39.9523,
+      "eval_rouge2": 15.0587,
+      "eval_rougeL": 36.3639,
+      "eval_rougeLsum": 36.375,
+      "eval_runtime": 424.8986,
+      "eval_samples_per_second": 9.414,
+      "eval_steps_per_second": 2.354,
+      "step": 1500
+    },
+    {
+      "epoch": 0.373238779509191,
+      "grad_norm": 0.8020262718200684,
+      "learning_rate": 4.3778773174069934e-05,
+      "loss": 0.3721,
+      "step": 2000
+    },
+    {
+      "epoch": 0.373238779509191,
+      "eval_gen_len": 11.2095,
+      "eval_loss": 0.46446970105171204,
+      "eval_rouge1": 40.3597,
+      "eval_rouge2": 15.2173,
+      "eval_rougeL": 36.6938,
+      "eval_rougeLsum": 36.705,
+      "eval_runtime": 410.7504,
+      "eval_samples_per_second": 9.738,
+      "eval_steps_per_second": 2.435,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4665484743864888,
+      "grad_norm": 0.8208432793617249,
+      "learning_rate": 4.222346646758741e-05,
+      "loss": 0.3673,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4665484743864888,
+      "eval_gen_len": 11.93425,
+      "eval_loss": 0.4631750285625458,
+      "eval_rouge1": 40.3875,
+      "eval_rouge2": 15.2532,
+      "eval_rougeL": 36.5923,
+      "eval_rougeLsum": 36.6182,
+      "eval_runtime": 441.242,
+      "eval_samples_per_second": 9.065,
+      "eval_steps_per_second": 2.266,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5598581692637865,
+      "grad_norm": 0.807547926902771,
+      "learning_rate": 4.066815976110489e-05,
+      "loss": 0.365,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5598581692637865,
+      "eval_gen_len": 12.26475,
+      "eval_loss": 0.4623391330242157,
+      "eval_rouge1": 39.9395,
+      "eval_rouge2": 15.0315,
+      "eval_rougeL": 36.1682,
+      "eval_rougeLsum": 36.1781,
+      "eval_runtime": 440.5083,
+      "eval_samples_per_second": 9.08,
+      "eval_steps_per_second": 2.27,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6531678641410843,
+      "grad_norm": 0.6434993147850037,
+      "learning_rate": 3.911285305462237e-05,
+      "loss": 0.3652,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6531678641410843,
+      "eval_gen_len": 11.8965,
+      "eval_loss": 0.4611285328865051,
+      "eval_rouge1": 39.8792,
+      "eval_rouge2": 14.9961,
+      "eval_rougeL": 36.2488,
+      "eval_rougeLsum": 36.2734,
+      "eval_runtime": 429.9024,
+      "eval_samples_per_second": 9.304,
+      "eval_steps_per_second": 2.326,
+      "step": 3500
+    },
+    {
+      "epoch": 0.746477559018382,
+      "grad_norm": 0.8740318417549133,
+      "learning_rate": 3.755754634813985e-05,
+      "loss": 0.3601,
+      "step": 4000
+    },
+    {
+      "epoch": 0.746477559018382,
+      "eval_gen_len": 12.0545,
+      "eval_loss": 0.4625248610973358,
+      "eval_rouge1": 40.57,
+      "eval_rouge2": 15.2972,
+      "eval_rougeL": 36.8012,
+      "eval_rougeLsum": 36.8227,
+      "eval_runtime": 431.0422,
+      "eval_samples_per_second": 9.28,
+      "eval_steps_per_second": 2.32,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8397872538956798,
+      "grad_norm": 0.7394187450408936,
+      "learning_rate": 3.600223964165734e-05,
+      "loss": 0.3574,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8397872538956798,
+      "eval_gen_len": 11.72875,
+      "eval_loss": 0.4608415365219116,
+      "eval_rouge1": 40.3276,
+      "eval_rouge2": 15.1742,
+      "eval_rougeL": 36.7679,
+      "eval_rougeLsum": 36.7575,
+      "eval_runtime": 467.6774,
+      "eval_samples_per_second": 8.553,
+      "eval_steps_per_second": 2.138,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9330969487729776,
+      "grad_norm": 0.841187059879303,
+      "learning_rate": 3.444693293517482e-05,
+      "loss": 0.351,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9330969487729776,
+      "eval_gen_len": 11.76625,
+      "eval_loss": 0.4650140404701233,
+      "eval_rouge1": 40.7345,
+      "eval_rouge2": 15.5295,
+      "eval_rougeL": 37.0769,
+      "eval_rougeLsum": 37.0911,
+      "eval_runtime": 475.4278,
+      "eval_samples_per_second": 8.413,
+      "eval_steps_per_second": 2.103,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0264066436502752,
+      "grad_norm": 0.8910800814628601,
+      "learning_rate": 3.28916262286923e-05,
+      "loss": 0.3322,
+      "step": 5500
+    },
+    {
+      "epoch": 1.0264066436502752,
+      "eval_gen_len": 12.06,
+      "eval_loss": 0.48306143283843994,
+      "eval_rouge1": 40.5582,
+      "eval_rouge2": 15.2954,
+      "eval_rougeL": 36.6682,
+      "eval_rougeLsum": 36.6694,
+      "eval_runtime": 444.1346,
+      "eval_samples_per_second": 9.006,
+      "eval_steps_per_second": 2.252,
+      "step": 5500
+    },
+    {
+      "epoch": 1.119716338527573,
+      "grad_norm": 0.9060000777244568,
+      "learning_rate": 3.1336319522209783e-05,
+      "loss": 0.2914,
+      "step": 6000
+    },
+    {
+      "epoch": 1.119716338527573,
+      "eval_gen_len": 11.8405,
+      "eval_loss": 0.4901696741580963,
+      "eval_rouge1": 40.054,
+      "eval_rouge2": 15.019,
+      "eval_rougeL": 36.5476,
+      "eval_rougeLsum": 36.556,
+      "eval_runtime": 432.4768,
+      "eval_samples_per_second": 9.249,
+      "eval_steps_per_second": 2.312,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2130260334048708,
+      "grad_norm": 0.9239944219589233,
+      "learning_rate": 2.978101281572726e-05,
+      "loss": 0.2945,
+      "step": 6500
+    },
+    {
+      "epoch": 1.2130260334048708,
+      "eval_gen_len": 11.84225,
+      "eval_loss": 0.48632147908210754,
+      "eval_rouge1": 40.3126,
+      "eval_rouge2": 15.3154,
+      "eval_rougeL": 36.61,
+      "eval_rougeLsum": 36.6146,
+      "eval_runtime": 433.2065,
+      "eval_samples_per_second": 9.233,
+      "eval_steps_per_second": 2.308,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3063357282821686,
+      "grad_norm": 0.9310933351516724,
+      "learning_rate": 2.8225706109244742e-05,
+      "loss": 0.2845,
+      "step": 7000
+    },
+    {
+      "epoch": 1.3063357282821686,
+      "eval_gen_len": 12.0445,
+      "eval_loss": 0.48827481269836426,
+      "eval_rouge1": 40.228,
+      "eval_rouge2": 15.0904,
+      "eval_rougeL": 36.3179,
+      "eval_rougeLsum": 36.3086,
+      "eval_runtime": 445.7913,
+      "eval_samples_per_second": 8.973,
+      "eval_steps_per_second": 2.243,
+      "step": 7000
+    },
+    {
+      "epoch": 1.3996454231594662,
+      "grad_norm": 0.8383007645606995,
+      "learning_rate": 2.6670399402762224e-05,
+      "loss": 0.2879,
+      "step": 7500
+    },
+    {
+      "epoch": 1.3996454231594662,
+      "eval_gen_len": 11.93575,
+      "eval_loss": 0.4833485782146454,
+      "eval_rouge1": 40.6501,
+      "eval_rouge2": 15.5682,
+      "eval_rougeL": 36.8945,
+      "eval_rougeLsum": 36.8823,
+      "eval_runtime": 438.3851,
+      "eval_samples_per_second": 9.124,
+      "eval_steps_per_second": 2.281,
+      "step": 7500
+    },
+    {
+      "epoch": 1.492955118036764,
+      "grad_norm": 0.8517706990242004,
+      "learning_rate": 2.5115092696279708e-05,
+      "loss": 0.2859,
+      "step": 8000
+    },
+    {
+      "epoch": 1.492955118036764,
+      "eval_gen_len": 12.17425,
+      "eval_loss": 0.4833007752895355,
+      "eval_rouge1": 40.3187,
+      "eval_rouge2": 15.0418,
+      "eval_rougeL": 36.3561,
+      "eval_rougeLsum": 36.3582,
+      "eval_runtime": 441.1227,
+      "eval_samples_per_second": 9.068,
+      "eval_steps_per_second": 2.267,
+      "step": 8000
+    },
+    {
+      "epoch": 1.5862648129140617,
+      "grad_norm": 0.951680064201355,
+      "learning_rate": 2.355978598979719e-05,
+      "loss": 0.2844,
+      "step": 8500
+    },
+    {
+      "epoch": 1.5862648129140617,
+      "eval_gen_len": 12.17025,
+      "eval_loss": 0.48842066526412964,
+      "eval_rouge1": 40.2896,
+      "eval_rouge2": 15.1032,
+      "eval_rougeL": 36.4039,
+      "eval_rougeLsum": 36.3862,
+      "eval_runtime": 458.4907,
+      "eval_samples_per_second": 8.724,
+      "eval_steps_per_second": 2.181,
+      "step": 8500
+    },
+    {
+      "epoch": 1.6795745077913595,
+      "grad_norm": 0.6958986520767212,
+      "learning_rate": 2.200447928331467e-05,
+      "loss": 0.2838,
+      "step": 9000
+    },
+    {
+      "epoch": 1.6795745077913595,
+      "eval_gen_len": 11.95875,
+      "eval_loss": 0.49017783999443054,
+      "eval_rouge1": 40.3419,
+      "eval_rouge2": 15.1863,
+      "eval_rougeL": 36.4631,
+      "eval_rougeLsum": 36.4728,
+      "eval_runtime": 462.8508,
+      "eval_samples_per_second": 8.642,
+      "eval_steps_per_second": 2.161,
+      "step": 9000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 16074,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.598643939351619e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-9000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee93f1655f97fbc3e4106c899d4549ddbe6f5e76e96df535e06a99bce9a661a6
+size 5304