Delete checkpoint-180

checkpoint-180/config.json

@@ -1,180 +0,0 @@
-{
-  "_commit_hash": "c8ec879716f6b8c2d782c3bd88686a5bec37102d",
-  "_name_or_path": "microsoft/trocr-base-stage1",
-  "architectures": [
-    "VisionEncoderDecoderModel"
-  ],
-  "decoder": {
-    "_name_or_path": "",
-    "activation_dropout": 0.0,
-    "activation_function": "relu",
-    "add_cross_attention": true,
-    "architectures": null,
-    "attention_dropout": 0.0,
-    "bad_words_ids": null,
-    "begin_suppress_tokens": null,
-    "bos_token_id": 0,
-    "chunk_size_feed_forward": 0,
-    "classifier_dropout": 0.0,
-    "cross_attention_hidden_size": 768,
-    "d_model": 1024,
-    "decoder_attention_heads": 16,
-    "decoder_ffn_dim": 4096,
-    "decoder_layerdrop": 0.0,
-    "decoder_layers": 12,
-    "decoder_start_token_id": 2,
-    "diversity_penalty": 0.0,
-    "do_sample": false,
-    "dropout": 0.1,
-    "early_stopping": false,
-    "encoder_no_repeat_ngram_size": 0,
-    "eos_token_id": 2,
-    "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"
-    },
-    "init_std": 0.02,
-    "is_decoder": true,
-    "is_encoder_decoder": false,
-    "label2id": {
-      "LABEL_0": 0,
-      "LABEL_1": 1
-    },
-    "layernorm_embedding": false,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 1024,
-    "min_length": 0,
-    "model_type": "trocr",
-    "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": 1,
-    "prefix": null,
-    "problem_type": null,
-    "pruned_heads": {},
-    "remove_invalid_values": false,
-    "repetition_penalty": 1.0,
-    "return_dict": true,
-    "return_dict_in_generate": false,
-    "scale_embedding": true,
-    "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": false,
-    "tokenizer_class": null,
-    "top_k": 50,
-    "top_p": 1.0,
-    "torch_dtype": null,
-    "torchscript": false,
-    "transformers_version": "4.27.4",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": false,
-    "use_learned_position_embeddings": false,
-    "vocab_size": 50265
-  },
-  "decoder_start_token_id": 0,
-  "early_stopping": true,
-  "encoder": {
-    "_name_or_path": "",
-    "add_cross_attention": false,
-    "architectures": null,
-    "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": 384,
-    "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": false,
-    "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,
-    "transformers_version": "4.27.4",
-    "typical_p": 1.0,
-    "use_bfloat16": false
-  },
-  "eos_token_id": 2,
-  "is_encoder_decoder": true,
-  "length_penalty": 2.0,
-  "max_length": 25,
-  "model_type": "vision-encoder-decoder",
-  "no_repeat_ngram_size": 3,
-  "num_beams": 4,
-  "pad_token_id": 1,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": null,
-  "vocab_size": 50265
-}

checkpoint-180/generation_config.json

@@ -1,13 +0,0 @@
-{
-  "bos_token_id": 0,
-  "decoder_start_token_id": 0,
-  "early_stopping": true,
-  "eos_token_id": 2,
-  "length_penalty": 2.0,
-  "max_length": 25,
-  "no_repeat_ngram_size": 3,
-  "num_beams": 4,
-  "pad_token_id": 1,
-  "transformers_version": "4.27.4",
-  "use_cache": false
-}

checkpoint-180/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0dc419dab2072c86ba7db4c4e8bfffe1adfae4efd6893041ec1d22f39e831ce0
-size 3074459717

checkpoint-180/preprocessor_config.json

@@ -1,22 +0,0 @@
-{
-  "do_normalize": true,
-  "do_rescale": true,
-  "do_resize": true,
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_processor_type": "ViTImageProcessor",
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "resample": 2,
-  "rescale_factor": 0.00392156862745098,
-  "size": {
-    "height": 384,
-    "width": 384
-  }
-}

checkpoint-180/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:76ad2f81fe629f870a1d44be06b058c4fb284eda95ab6d79c090e77135c97c68
-size 1539618953

checkpoint-180/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f91f5d4545cc6b436bf40d8b2200ffd99059ad78783ce772d08997ced40541b7
-size 13553

checkpoint-180/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:93370859a32524141e70ecd87308ad7517dad70e01d91f181fb43bdf428001ca
-size 627

checkpoint-180/trainer_state.json

@@ -1,178 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 2.8125,
-  "global_step": 180,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.16,
-      "learning_rate": 4.739583333333333e-05,
-      "loss": 0.2329,
-      "step": 10
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 4.4791666666666673e-05,
-      "loss": 0.0657,
-      "step": 20
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 4.21875e-05,
-      "loss": 0.0442,
-      "step": 30
-    },
-    {
-      "epoch": 0.47,
-      "eval_cer": 0.09341614906832298,
-      "eval_loss": 0.03504600375890732,
-      "eval_runtime": 433.0095,
-      "eval_samples_per_second": 1.18,
-      "eval_steps_per_second": 0.037,
-      "step": 30
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 3.958333333333333e-05,
-      "loss": 0.0327,
-      "step": 40
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 3.697916666666667e-05,
-      "loss": 0.0316,
-      "step": 50
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 3.4375e-05,
-      "loss": 0.0242,
-      "step": 60
-    },
-    {
-      "epoch": 0.94,
-      "eval_cer": 0.02981366459627329,
-      "eval_loss": 0.02102348767220974,
-      "eval_runtime": 445.6571,
-      "eval_samples_per_second": 1.147,
-      "eval_steps_per_second": 0.036,
-      "step": 60
-    },
-    {
-      "epoch": 1.09,
-      "learning_rate": 3.177083333333333e-05,
-      "loss": 0.0252,
-      "step": 70
-    },
-    {
-      "epoch": 1.25,
-      "learning_rate": 2.916666666666667e-05,
-      "loss": 0.0208,
-      "step": 80
-    },
-    {
-      "epoch": 1.41,
-      "learning_rate": 2.6562500000000002e-05,
-      "loss": 0.0203,
-      "step": 90
-    },
-    {
-      "epoch": 1.41,
-      "eval_cer": 0.01937888198757764,
-      "eval_loss": 0.018760638311505318,
-      "eval_runtime": 489.631,
-      "eval_samples_per_second": 1.044,
-      "eval_steps_per_second": 0.033,
-      "step": 90
-    },
-    {
-      "epoch": 1.56,
-      "learning_rate": 2.3958333333333334e-05,
-      "loss": 0.02,
-      "step": 100
-    },
-    {
-      "epoch": 1.72,
-      "learning_rate": 2.1354166666666666e-05,
-      "loss": 0.0178,
-      "step": 110
-    },
-    {
-      "epoch": 1.88,
-      "learning_rate": 1.8750000000000002e-05,
-      "loss": 0.0169,
-      "step": 120
-    },
-    {
-      "epoch": 1.88,
-      "eval_cer": 0.010186335403726708,
-      "eval_loss": 0.01577191799879074,
-      "eval_runtime": 572.6491,
-      "eval_samples_per_second": 0.892,
-      "eval_steps_per_second": 0.028,
-      "step": 120
-    },
-    {
-      "epoch": 2.03,
-      "learning_rate": 1.6145833333333334e-05,
-      "loss": 0.0161,
-      "step": 130
-    },
-    {
-      "epoch": 2.19,
-      "learning_rate": 1.3541666666666666e-05,
-      "loss": 0.0151,
-      "step": 140
-    },
-    {
-      "epoch": 2.34,
-      "learning_rate": 1.09375e-05,
-      "loss": 0.0151,
-      "step": 150
-    },
-    {
-      "epoch": 2.34,
-      "eval_cer": 0.0084472049689441,
-      "eval_loss": 0.014565763995051384,
-      "eval_runtime": 618.7531,
-      "eval_samples_per_second": 0.826,
-      "eval_steps_per_second": 0.026,
-      "step": 150
-    },
-    {
-      "epoch": 2.5,
-      "learning_rate": 8.333333333333334e-06,
-      "loss": 0.015,
-      "step": 160
-    },
-    {
-      "epoch": 2.66,
-      "learning_rate": 5.729166666666667e-06,
-      "loss": 0.0139,
-      "step": 170
-    },
-    {
-      "epoch": 2.81,
-      "learning_rate": 3.125e-06,
-      "loss": 0.0133,
-      "step": 180
-    },
-    {
-      "epoch": 2.81,
-      "eval_cer": 0.007950310559006211,
-      "eval_loss": 0.014070576056838036,
-      "eval_runtime": 564.3264,
-      "eval_samples_per_second": 0.906,
-      "eval_steps_per_second": 0.028,
-      "step": 180
-    }
-  ],
-  "max_steps": 192,
-  "num_train_epochs": 3,
-  "total_flos": 5.084609259497325e+18,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-180/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:13731dc01b37599b9b0f3d5fd0906ad0d86914ef40c4ea694dddf1b5ccc9e924
-size 3643