Training in progress, step 3500, checkpoint

checkpoint-3500/config.json

@@ -0,0 +1,186 @@
+{
+  "_name_or_path": "NourFakih/Vit-GPT2-COCO2017Flickr-80k-08",
+  "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-3500/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-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c91439026996dae6a4ed2abacd91a29b119825dbcb5d1cddc0a274e7bf5937
+size 956835520

checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0458a4633c5d1f3b6d2fa72857d7efaef14d60daa25a33d090f52b9c618c4706
+size 1909212608

checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d014149b6dce0d29a61ff6e40dc25441e4604621bdf8a249a753dbc9497aa342
+size 14244

checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:568dcb509ed1966a46e15fcb33f8e353b59c66e55b52270ddf3508cbfe12e125
+size 1064

checkpoint-3500/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": 0.5187843441963196,
+  "best_model_checkpoint": "./Vit-GPT2-COCO2017Flickr-85k-09/checkpoint-2500",
+  "epoch": 0.6531678641410843,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09330969487729775,
+      "grad_norm": 1.1049598455429077,
+      "learning_rate": 4.8444693293517484e-05,
+      "loss": 0.2429,
+      "step": 500
+    },
+    {
+      "epoch": 0.09330969487729775,
+      "eval_gen_len": 11.738,
+      "eval_loss": 0.5351373553276062,
+      "eval_rouge1": 39.4446,
+      "eval_rouge2": 14.1599,
+      "eval_rougeL": 35.6123,
+      "eval_rougeLsum": 35.5846,
+      "eval_runtime": 463.8252,
+      "eval_samples_per_second": 8.624,
+      "eval_steps_per_second": 2.156,
+      "step": 500
+    },
+    {
+      "epoch": 0.1866193897545955,
+      "grad_norm": 1.1426328420639038,
+      "learning_rate": 4.6889386587034965e-05,
+      "loss": 0.2537,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1866193897545955,
+      "eval_gen_len": 12.34875,
+      "eval_loss": 0.5301018357276917,
+      "eval_rouge1": 39.5332,
+      "eval_rouge2": 14.4745,
+      "eval_rougeL": 35.644,
+      "eval_rougeLsum": 35.6159,
+      "eval_runtime": 451.0336,
+      "eval_samples_per_second": 8.869,
+      "eval_steps_per_second": 2.217,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27992908463189325,
+      "grad_norm": 1.017817735671997,
+      "learning_rate": 4.5334079880552446e-05,
+      "loss": 0.2564,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27992908463189325,
+      "eval_gen_len": 12.2455,
+      "eval_loss": 0.5198264122009277,
+      "eval_rouge1": 39.8297,
+      "eval_rouge2": 14.555,
+      "eval_rougeL": 35.8598,
+      "eval_rougeLsum": 35.8344,
+      "eval_runtime": 446.7054,
+      "eval_samples_per_second": 8.954,
+      "eval_steps_per_second": 2.239,
+      "step": 1500
+    },
+    {
+      "epoch": 0.373238779509191,
+      "grad_norm": 0.9865152835845947,
+      "learning_rate": 4.3778773174069934e-05,
+      "loss": 0.2585,
+      "step": 2000
+    },
+    {
+      "epoch": 0.373238779509191,
+      "eval_gen_len": 11.8575,
+      "eval_loss": 0.5207428932189941,
+      "eval_rouge1": 39.4558,
+      "eval_rouge2": 14.0496,
+      "eval_rougeL": 35.5597,
+      "eval_rougeLsum": 35.526,
+      "eval_runtime": 441.2453,
+      "eval_samples_per_second": 9.065,
+      "eval_steps_per_second": 2.266,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4665484743864888,
+      "grad_norm": 0.9201194047927856,
+      "learning_rate": 4.222346646758741e-05,
+      "loss": 0.2579,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4665484743864888,
+      "eval_gen_len": 11.97325,
+      "eval_loss": 0.5187843441963196,
+      "eval_rouge1": 39.1359,
+      "eval_rouge2": 14.125,
+      "eval_rougeL": 35.4068,
+      "eval_rougeLsum": 35.3709,
+      "eval_runtime": 456.9413,
+      "eval_samples_per_second": 8.754,
+      "eval_steps_per_second": 2.188,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5598581692637865,
+      "grad_norm": 1.011809229850769,
+      "learning_rate": 4.066815976110489e-05,
+      "loss": 0.2588,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5598581692637865,
+      "eval_gen_len": 12.278,
+      "eval_loss": 0.5195733904838562,
+      "eval_rouge1": 39.0831,
+      "eval_rouge2": 14.0658,
+      "eval_rougeL": 35.4608,
+      "eval_rougeLsum": 35.4283,
+      "eval_runtime": 453.7444,
+      "eval_samples_per_second": 8.816,
+      "eval_steps_per_second": 2.204,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6531678641410843,
+      "grad_norm": 0.9602178931236267,
+      "learning_rate": 3.911285305462237e-05,
+      "loss": 0.2618,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6531678641410843,
+      "eval_gen_len": 11.99425,
+      "eval_loss": 0.5193876028060913,
+      "eval_rouge1": 39.751,
+      "eval_rouge2": 14.443,
+      "eval_rougeL": 36.076,
+      "eval_rougeLsum": 36.0475,
+      "eval_runtime": 451.6054,
+      "eval_samples_per_second": 8.857,
+      "eval_steps_per_second": 2.214,
+      "step": 3500
+    }
+  ],
+  "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": 1.0105977902727168e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b755cfe4fb7493d7fc142174fc67bb1ab756756d75dcea1c1afb972386bf21ce
+size 5304