Upload folder using huggingface_hub

README.md

@@ -1,3 +1,67 @@
----
-license: mit
----
+---
+library_name: transformers
+license: apache-2.0
+base_model: google/vit-base-patch16-224-in21k
+tags:
+- image-classification
+- vision
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: mango_output12
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mango_output12
+
+This model is a fine-tuned version of [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) on the Docty/Mangovariety dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3909
+- Accuracy: 0.9917
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 1337
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 85   | 1.2826          | 0.9375   |
+| No log        | 2.0   | 170  | 0.7519          | 0.975    |
+| No log        | 3.0   | 255  | 0.5236          | 0.9792   |
+| No log        | 4.0   | 340  | 0.4190          | 0.9875   |
+| No log        | 5.0   | 425  | 0.3909          | 0.9917   |
+
+
+### Framework versions
+
+- Transformers 4.51.1
+- Pytorch 2.5.1+cu124
+- Datasets 3.5.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9916666666666667,
+    "eval_loss": 0.3908880949020386,
+    "eval_runtime": 3.3275,
+    "eval_samples_per_second": 72.126,
+    "eval_steps_per_second": 4.508,
+    "total_flos": 5.269738664558592e+17,
+    "train_loss": 0.843348819508272,
+    "train_runtime": 218.539,
+    "train_samples_per_second": 31.116,
+    "train_steps_per_second": 1.945
+}

checkpoint-255/config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Dosehri",
+    "1": "Sindhri",
+    "2": "Fajri",
+    "3": "Anwar Ratool",
+    "4": "Chaunsa (White)",
+    "5": "Langra",
+    "6": "Chaunsa (Black)",
+    "7": "Chaunsa (Summer Bahisht)"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Anwar Ratool": "3",
+    "Chaunsa (Black)": "6",
+    "Chaunsa (Summer Bahisht)": "7",
+    "Chaunsa (White)": "4",
+    "Dosehri": "0",
+    "Fajri": "2",
+    "Langra": "5",
+    "Sindhri": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1"
+}

checkpoint-255/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e407b2ecaa85e4356ce4078f0a020b234be4bf6e126596c600369384411fe78
+size 343242432

checkpoint-255/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da2a50aa95dcbcfc2a0f3424d095f40e336ee772d14092e9a3986814d049de7
+size 686605754

checkpoint-255/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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": 224,
+    "width": 224
+  }
+}

checkpoint-255/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3166e63866471b9e62438729bb93242bb1dd3007c49de73466d91b151cd50e4d
+size 14308

checkpoint-255/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d63e0a704c7f2f3081c4e8d76fe00f34970cebdc99d26e2d21dd008c68d60a29
+size 1064

checkpoint-255/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_global_step": 255,
+  "best_metric": 0.5236374139785767,
+  "best_model_checkpoint": "./mango_output12/checkpoint-255",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 255,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9375,
+      "eval_loss": 1.282586693763733,
+      "eval_runtime": 3.427,
+      "eval_samples_per_second": 70.032,
+      "eval_steps_per_second": 4.377,
+      "step": 85
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.975,
+      "eval_loss": 0.7518740296363831,
+      "eval_runtime": 3.254,
+      "eval_samples_per_second": 73.755,
+      "eval_steps_per_second": 4.61,
+      "step": 170
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.5236374139785767,
+      "eval_runtime": 3.3453,
+      "eval_samples_per_second": 71.742,
+      "eval_steps_per_second": 4.484,
+      "step": 255
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 425,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 3.161843198735155e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-255/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250d06b01c5455b9ba137bb94d1e4742f2b4b253ab0e93004dd47358889e4395
+size 5304

checkpoint-340/config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Dosehri",
+    "1": "Sindhri",
+    "2": "Fajri",
+    "3": "Anwar Ratool",
+    "4": "Chaunsa (White)",
+    "5": "Langra",
+    "6": "Chaunsa (Black)",
+    "7": "Chaunsa (Summer Bahisht)"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Anwar Ratool": "3",
+    "Chaunsa (Black)": "6",
+    "Chaunsa (Summer Bahisht)": "7",
+    "Chaunsa (White)": "4",
+    "Dosehri": "0",
+    "Fajri": "2",
+    "Langra": "5",
+    "Sindhri": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1"
+}

checkpoint-340/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf0881be51041e498aa2319d2788a30954e907a535afa46d65f58f716f228fd
+size 343242432

checkpoint-340/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca75b15ad2406edd8d206fca927ff9f2afe74ce1f66e1107b9520214b5c71d28
+size 686605754

checkpoint-340/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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": 224,
+    "width": 224
+  }
+}

checkpoint-340/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ca2d731cdf11e61aca1efb6e04db72d6f67cdb17f46c8b32d2ca8c812b81ad7
+size 14308

checkpoint-340/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:830d8f4c72d8b3874239a7f7554ac78b06590daed1f7036d839d27316f9d0a9d
+size 1064

checkpoint-340/trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_global_step": 340,
+  "best_metric": 0.4190078675746918,
+  "best_model_checkpoint": "./mango_output12/checkpoint-340",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9375,
+      "eval_loss": 1.282586693763733,
+      "eval_runtime": 3.427,
+      "eval_samples_per_second": 70.032,
+      "eval_steps_per_second": 4.377,
+      "step": 85
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.975,
+      "eval_loss": 0.7518740296363831,
+      "eval_runtime": 3.254,
+      "eval_samples_per_second": 73.755,
+      "eval_steps_per_second": 4.61,
+      "step": 170
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.5236374139785767,
+      "eval_runtime": 3.3453,
+      "eval_samples_per_second": 71.742,
+      "eval_steps_per_second": 4.484,
+      "step": 255
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9875,
+      "eval_loss": 0.4190078675746918,
+      "eval_runtime": 3.2437,
+      "eval_samples_per_second": 73.989,
+      "eval_steps_per_second": 4.624,
+      "step": 340
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 425,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 4.2157909316468736e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-340/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250d06b01c5455b9ba137bb94d1e4742f2b4b253ab0e93004dd47358889e4395
+size 5304

checkpoint-425/config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Dosehri",
+    "1": "Sindhri",
+    "2": "Fajri",
+    "3": "Anwar Ratool",
+    "4": "Chaunsa (White)",
+    "5": "Langra",
+    "6": "Chaunsa (Black)",
+    "7": "Chaunsa (Summer Bahisht)"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Anwar Ratool": "3",
+    "Chaunsa (Black)": "6",
+    "Chaunsa (Summer Bahisht)": "7",
+    "Chaunsa (White)": "4",
+    "Dosehri": "0",
+    "Fajri": "2",
+    "Langra": "5",
+    "Sindhri": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1"
+}

checkpoint-425/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1ba25a96166f112eafa7d5ed2b9b660d010b0de4920aec57a9af26a7632496
+size 343242432

checkpoint-425/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44fcd5429b3d905b806ebac248bd2d6d9c525c823a12a480b27f82e90bb854ae
+size 686605754

checkpoint-425/preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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": 224,
+    "width": 224
+  }
+}

checkpoint-425/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f00dcf2113d82361540ad490eb86dd9ca20430f074af92174d6ace669fe763a9
+size 14308

checkpoint-425/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7162e09bdb9fa086ca895492ad389068254e6081ed80f82902ef216ad0f1506
+size 1064

checkpoint-425/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_global_step": 425,
+  "best_metric": 0.3908880949020386,
+  "best_model_checkpoint": "./mango_output12/checkpoint-425",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 425,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9375,
+      "eval_loss": 1.282586693763733,
+      "eval_runtime": 3.427,
+      "eval_samples_per_second": 70.032,
+      "eval_steps_per_second": 4.377,
+      "step": 85
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.975,
+      "eval_loss": 0.7518740296363831,
+      "eval_runtime": 3.254,
+      "eval_samples_per_second": 73.755,
+      "eval_steps_per_second": 4.61,
+      "step": 170
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.5236374139785767,
+      "eval_runtime": 3.3453,
+      "eval_samples_per_second": 71.742,
+      "eval_steps_per_second": 4.484,
+      "step": 255
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9875,
+      "eval_loss": 0.4190078675746918,
+      "eval_runtime": 3.2437,
+      "eval_samples_per_second": 73.989,
+      "eval_steps_per_second": 4.624,
+      "step": 340
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9916666666666667,
+      "eval_loss": 0.3908880949020386,
+      "eval_runtime": 3.3096,
+      "eval_samples_per_second": 72.515,
+      "eval_steps_per_second": 4.532,
+      "step": 425
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 425,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.269738664558592e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-425/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250d06b01c5455b9ba137bb94d1e4742f2b4b253ab0e93004dd47358889e4395
+size 5304

config.json

@@ -0,0 +1,46 @@
+{
+  "architectures": [
+    "ViTForImageClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "encoder_stride": 16,
+  "finetuning_task": "image-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Dosehri",
+    "1": "Sindhri",
+    "2": "Fajri",
+    "3": "Anwar Ratool",
+    "4": "Chaunsa (White)",
+    "5": "Langra",
+    "6": "Chaunsa (Black)",
+    "7": "Chaunsa (Summer Bahisht)"
+  },
+  "image_size": 224,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Anwar Ratool": "3",
+    "Chaunsa (Black)": "6",
+    "Chaunsa (Summer Bahisht)": "7",
+    "Chaunsa (White)": "4",
+    "Dosehri": "0",
+    "Fajri": "2",
+    "Langra": "5",
+    "Sindhri": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "model_type": "vit",
+  "num_attention_heads": 12,
+  "num_channels": 3,
+  "num_hidden_layers": 12,
+  "patch_size": 16,
+  "pooler_act": "tanh",
+  "pooler_output_size": 768,
+  "problem_type": "single_label_classification",
+  "qkv_bias": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.1"
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9916666666666667,
+    "eval_loss": 0.3908880949020386,
+    "eval_runtime": 3.3275,
+    "eval_samples_per_second": 72.126,
+    "eval_steps_per_second": 4.508
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af1ba25a96166f112eafa7d5ed2b9b660d010b0de4920aec57a9af26a7632496
+size 343242432

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_convert_rgb": null,
+  "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": 224,
+    "width": 224
+  }
+}

runs/Apr14_01-40-09_77dd292560cf/events.out.tfevents.1744594812.77dd292560cf.339.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ec829dbd6b06e7a2d774c274499fbec36bdc0bbb6d75c5dcdbd855d9e546a02
+size 7316

runs/Apr14_01-40-09_77dd292560cf/events.out.tfevents.1744595035.77dd292560cf.339.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f63a14fe9c04c0e07ecab9ba7a5d98eab9274465f920bd7d5644f01ac3e33be
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 5.269738664558592e+17,
+    "train_loss": 0.843348819508272,
+    "train_runtime": 218.539,
+    "train_samples_per_second": 31.116,
+    "train_steps_per_second": 1.945
+}

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_global_step": 425,
+  "best_metric": 0.3908880949020386,
+  "best_model_checkpoint": "./mango_output12/checkpoint-425",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 425,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9375,
+      "eval_loss": 1.282586693763733,
+      "eval_runtime": 3.427,
+      "eval_samples_per_second": 70.032,
+      "eval_steps_per_second": 4.377,
+      "step": 85
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.975,
+      "eval_loss": 0.7518740296363831,
+      "eval_runtime": 3.254,
+      "eval_samples_per_second": 73.755,
+      "eval_steps_per_second": 4.61,
+      "step": 170
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9791666666666666,
+      "eval_loss": 0.5236374139785767,
+      "eval_runtime": 3.3453,
+      "eval_samples_per_second": 71.742,
+      "eval_steps_per_second": 4.484,
+      "step": 255
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9875,
+      "eval_loss": 0.4190078675746918,
+      "eval_runtime": 3.2437,
+      "eval_samples_per_second": 73.989,
+      "eval_steps_per_second": 4.624,
+      "step": 340
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9916666666666667,
+      "eval_loss": 0.3908880949020386,
+      "eval_runtime": 3.3096,
+      "eval_samples_per_second": 72.515,
+      "eval_steps_per_second": 4.532,
+      "step": 425
+    },
+    {
+      "epoch": 5.0,
+      "step": 425,
+      "total_flos": 5.269738664558592e+17,
+      "train_loss": 0.843348819508272,
+      "train_runtime": 218.539,
+      "train_samples_per_second": 31.116,
+      "train_steps_per_second": 1.945
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 425,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.269738664558592e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250d06b01c5455b9ba137bb94d1e4742f2b4b253ab0e93004dd47358889e4395
+size 5304