End of training

last-checkpoint/config.json

@@ -1,171 +0,0 @@
-{
-  "_name_or_path": "microsoft/trocr-small-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,
-    "bos_token_id": 0,
-    "chunk_size_feed_forward": 0,
-    "classifier_dropout": 0.0,
-    "cross_attention_hidden_size": 384,
-    "d_model": 256,
-    "decoder_attention_heads": 8,
-    "decoder_ffn_dim": 1024,
-    "decoder_layerdrop": 0.0,
-    "decoder_layers": 6,
-    "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,
-    "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": true,
-    "length_penalty": 1.0,
-    "max_length": 20,
-    "max_position_embeddings": 512,
-    "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,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "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": "4.17.0",
-    "typical_p": 1.0,
-    "use_bfloat16": false,
-    "use_cache": false,
-    "use_learned_position_embeddings": true,
-    "vocab_size": 64044
-  },
-  "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,
-    "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,
-    "finetuning_task": null,
-    "forced_bos_token_id": null,
-    "forced_eos_token_id": null,
-    "hidden_act": "gelu",
-    "hidden_dropout_prob": 0.0,
-    "hidden_size": 384,
-    "id2label": {
-      "0": "LABEL_0",
-      "1": "LABEL_1"
-    },
-    "image_size": 384,
-    "initializer_range": 0.02,
-    "intermediate_size": 1536,
-    "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": "deit",
-    "no_repeat_ngram_size": 0,
-    "num_attention_heads": 6,
-    "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,
-    "task_specific_params": null,
-    "temperature": 1.0,
-    "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": "4.17.0",
-    "typical_p": 1.0,
-    "use_bfloat16": false
-  },
-  "eos_token_id": 2,
-  "is_encoder_decoder": true,
-  "length_penalty": 2.0,
-  "max_length": 64,
-  "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": 64044
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2ab4be5a77350763ddc4318155d668a7ca0d648a5c920554a4fcf87b3afa15a0
-size 491800161

last-checkpoint/preprocessor_config.json

@@ -1,17 +0,0 @@
-{
-  "do_normalize": true,
-  "do_resize": true,
-  "feature_extractor_type": "ViTFeatureExtractor",
-  "image_mean": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "image_std": [
-    0.5,
-    0.5,
-    0.5
-  ],
-  "resample": 2,
-  "size": 384
-}

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ee7f6bd27287cfbc78e254ce73f3f7d0a952d152b5603e7eb0cf1545e1b54b9c
-size 246531565

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:60db868db25d79a4a49d93a4ff950747420ee055dbacbef348e39ff3bd92b0bc
-size 14439

last-checkpoint/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9c839c3d694d8ceeeac85645a8e358f96300e44574d363a151fc00c07558d8d4
-size 559

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7a41d885b6e3951e39aa87ba36fccfeddb0170f9fbad0973e185208b29a2329b
-size 623

last-checkpoint/trainer_state.json

@@ -1,31 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.14338973329509608,
-  "global_step": 1000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.14,
-      "learning_rate": 4.762451008507791e-05,
-      "loss": 3.6363,
-      "step": 1000
-    },
-    {
-      "epoch": 0.14,
-      "eval_cer": 0.9369978858350951,
-      "eval_loss": 2.759432792663574,
-      "eval_runtime": 76.0129,
-      "eval_samples_per_second": 0.658,
-      "eval_steps_per_second": 0.658,
-      "step": 1000
-    }
-  ],
-  "max_steps": 20922,
-  "num_train_epochs": 3,
-  "total_flos": 1.19624687419392e+17,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:63c9d1e0fe7cc0380936724fc86865955016b860e61c849267a10b3d1b7b2c68
-size 3183

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee7f6bd27287cfbc78e254ce73f3f7d0a952d152b5603e7eb0cf1545e1b54b9c
+oid sha256:85788c495f6587db89caa56c0923de4211fbc4b46431bf5f291b3db0741fa55f
 size 246531565

runs/Mar21_09-18-11_087c1ea6372a/events.out.tfevents.1647854315.087c1ea6372a.76.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82a10eb0e873a25b549bef2655bf0b4cdf005662c64faafbb888dd07fc8fa369
-size 7801
+oid sha256:dd995ea15697e5d38cc23c1bea20018dec9c97c05e11714a2c82bd5facf86cef
+size 17222