Upload folder using huggingface_hub

README.md

@@ -1,3 +1,58 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: apache-2.0
+base_model: PartAI/TookaBERT-Large
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: snapfood
+  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. -->
+
+# snapfood
+
+This model is a fine-tuned version of [PartAI/TookaBERT-Large](https://huggingface.co/PartAI/TookaBERT-Large) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3681
+- Accuracy: 0.8793
+
+## 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: 10
+- eval_batch_size: 8
+- seed: 42
+- 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: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.0.0.dev0
+- Pytorch 2.6.0+cu124
+- Datasets 4.4.1
+- Tokenizers 0.22.1

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8793330934388869,
+    "eval_loss": 0.36814266443252563,
+    "eval_runtime": 437.0819,
+    "eval_samples": 8337,
+    "eval_samples_per_second": 19.074,
+    "eval_steps_per_second": 2.386,
+    "total_flos": 1.4568883002906624e+17,
+    "train_loss": 0.3201524627984222,
+    "train_runtime": 31218.1999,
+    "train_samples": 52110,
+    "train_samples_per_second": 5.008,
+    "train_steps_per_second": 0.501
+}

checkpoint-10422/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 3,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "HAPPY",
+    "1": "SAD"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "HAPPY": 0,
+    "SAD": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "5.0.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 48000
+}

checkpoint-10422/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:570152b4f6618f1475c9c8a864a715f5b0d275752e76b4d44476b3f974aefe0f
+size 1412212656

checkpoint-10422/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67b1ec93309ece0c69b93368042ed1194c59ef938ac7269ee941320dc3978f66
+size 2824660205

checkpoint-10422/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa24153f31489291c0f9ea47ee9cec86b6296b009004a9e32ada3be05dacda76
+size 14244

checkpoint-10422/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d9130bb4c145fcf308e8b2729a7d3ebb81c4a003296f7afb90af4f2984dbfc0
+size 1064

checkpoint-10422/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}

checkpoint-10422/trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 10422,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09595087315294569,
+      "grad_norm": 12.811051368713379,
+      "learning_rate": 1.936160685728907e-05,
+      "loss": 0.435078857421875,
+      "step": 500
+    },
+    {
+      "epoch": 0.19190174630589138,
+      "grad_norm": 8.909839630126953,
+      "learning_rate": 1.8721934369602766e-05,
+      "loss": 0.38166162109375,
+      "step": 1000
+    },
+    {
+      "epoch": 0.28785261945883706,
+      "grad_norm": 23.91183853149414,
+      "learning_rate": 1.8082261881916462e-05,
+      "loss": 0.3671803283691406,
+      "step": 1500
+    },
+    {
+      "epoch": 0.38380349261178276,
+      "grad_norm": 13.278630256652832,
+      "learning_rate": 1.7442589394230155e-05,
+      "loss": 0.34918722534179686,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47975436576472846,
+      "grad_norm": 6.475880146026611,
+      "learning_rate": 1.680291690654385e-05,
+      "loss": 0.35130245971679686,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5757052389176741,
+      "grad_norm": 5.953056812286377,
+      "learning_rate": 1.6163244418857547e-05,
+      "loss": 0.363922607421875,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6716561120706198,
+      "grad_norm": 9.432499885559082,
+      "learning_rate": 1.5523571931171243e-05,
+      "loss": 0.37142852783203123,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7676069852235655,
+      "grad_norm": 3.409161329269409,
+      "learning_rate": 1.4883899443484937e-05,
+      "loss": 0.3608262023925781,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8635578583765112,
+      "grad_norm": 1.59526789188385,
+      "learning_rate": 1.4244226955798633e-05,
+      "loss": 0.3568770446777344,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9595087315294569,
+      "grad_norm": 4.420688629150391,
+      "learning_rate": 1.3604554468112327e-05,
+      "loss": 0.3340596923828125,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0554596046824025,
+      "grad_norm": 8.594019889831543,
+      "learning_rate": 1.2964881980426023e-05,
+      "loss": 0.3522498779296875,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1514104778353482,
+      "grad_norm": 3.242337226867676,
+      "learning_rate": 1.2325209492739718e-05,
+      "loss": 0.32486505126953125,
+      "step": 6000
+    },
+    {
+      "epoch": 1.247361350988294,
+      "grad_norm": 20.167972564697266,
+      "learning_rate": 1.1685537005053414e-05,
+      "loss": 0.3254352416992187,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3433122241412396,
+      "grad_norm": 4.983191967010498,
+      "learning_rate": 1.1045864517367108e-05,
+      "loss": 0.330927490234375,
+      "step": 7000
+    },
+    {
+      "epoch": 1.4392630972941853,
+      "grad_norm": 1.6593592166900635,
+      "learning_rate": 1.0406192029680804e-05,
+      "loss": 0.3213047485351562,
+      "step": 7500
+    },
+    {
+      "epoch": 1.535213970447131,
+      "grad_norm": 17.288793563842773,
+      "learning_rate": 9.7665195419945e-06,
+      "loss": 0.3227524719238281,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6311648436000767,
+      "grad_norm": 3.9145667552948,
+      "learning_rate": 9.126847054308194e-06,
+      "loss": 0.3189747924804687,
+      "step": 8500
+    },
+    {
+      "epoch": 1.7271157167530224,
+      "grad_norm": 3.7356808185577393,
+      "learning_rate": 8.48717456662189e-06,
+      "loss": 0.33311187744140625,
+      "step": 9000
+    },
+    {
+      "epoch": 1.8230665899059681,
+      "grad_norm": 15.458077430725098,
+      "learning_rate": 7.847502078935586e-06,
+      "loss": 0.3166582946777344,
+      "step": 9500
+    },
+    {
+      "epoch": 1.9190174630589139,
+      "grad_norm": 0.5702362060546875,
+      "learning_rate": 7.207829591249281e-06,
+      "loss": 0.3185113525390625,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15633,
+  "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": 9.712588668604416e+16,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10422/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7010d8e51577a38b5b304dc130057e792156cfd67546e35490c409c520b99664
+size 4728

checkpoint-15633/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 3,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "HAPPY",
+    "1": "SAD"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "HAPPY": 0,
+    "SAD": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "5.0.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 48000
+}

checkpoint-15633/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d967b4d0ab75d579d47f05cac9a4298b0a73260e0fee3415bd9839b5b82998
+size 1412212656

checkpoint-15633/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6942464893a7c9e32df66009a1d630143ef6d2017fbd42dcda8f6567bc4361
+size 2824660205

checkpoint-15633/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3e5f9dfd67c2c16e2ff5aea81baa45050a9ae7193b31484cbfebb216b582e5
+size 14244

checkpoint-15633/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a2030a19651e57c5517d754d6ce02fd147fd15f8b0cf9227e5cf85c5e394836
+size 1064

checkpoint-15633/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}

checkpoint-15633/trainer_state.json

@@ -0,0 +1,251 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 15633,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09595087315294569,
+      "grad_norm": 12.811051368713379,
+      "learning_rate": 1.936160685728907e-05,
+      "loss": 0.435078857421875,
+      "step": 500
+    },
+    {
+      "epoch": 0.19190174630589138,
+      "grad_norm": 8.909839630126953,
+      "learning_rate": 1.8721934369602766e-05,
+      "loss": 0.38166162109375,
+      "step": 1000
+    },
+    {
+      "epoch": 0.28785261945883706,
+      "grad_norm": 23.91183853149414,
+      "learning_rate": 1.8082261881916462e-05,
+      "loss": 0.3671803283691406,
+      "step": 1500
+    },
+    {
+      "epoch": 0.38380349261178276,
+      "grad_norm": 13.278630256652832,
+      "learning_rate": 1.7442589394230155e-05,
+      "loss": 0.34918722534179686,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47975436576472846,
+      "grad_norm": 6.475880146026611,
+      "learning_rate": 1.680291690654385e-05,
+      "loss": 0.35130245971679686,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5757052389176741,
+      "grad_norm": 5.953056812286377,
+      "learning_rate": 1.6163244418857547e-05,
+      "loss": 0.363922607421875,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6716561120706198,
+      "grad_norm": 9.432499885559082,
+      "learning_rate": 1.5523571931171243e-05,
+      "loss": 0.37142852783203123,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7676069852235655,
+      "grad_norm": 3.409161329269409,
+      "learning_rate": 1.4883899443484937e-05,
+      "loss": 0.3608262023925781,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8635578583765112,
+      "grad_norm": 1.59526789188385,
+      "learning_rate": 1.4244226955798633e-05,
+      "loss": 0.3568770446777344,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9595087315294569,
+      "grad_norm": 4.420688629150391,
+      "learning_rate": 1.3604554468112327e-05,
+      "loss": 0.3340596923828125,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0554596046824025,
+      "grad_norm": 8.594019889831543,
+      "learning_rate": 1.2964881980426023e-05,
+      "loss": 0.3522498779296875,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1514104778353482,
+      "grad_norm": 3.242337226867676,
+      "learning_rate": 1.2325209492739718e-05,
+      "loss": 0.32486505126953125,
+      "step": 6000
+    },
+    {
+      "epoch": 1.247361350988294,
+      "grad_norm": 20.167972564697266,
+      "learning_rate": 1.1685537005053414e-05,
+      "loss": 0.3254352416992187,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3433122241412396,
+      "grad_norm": 4.983191967010498,
+      "learning_rate": 1.1045864517367108e-05,
+      "loss": 0.330927490234375,
+      "step": 7000
+    },
+    {
+      "epoch": 1.4392630972941853,
+      "grad_norm": 1.6593592166900635,
+      "learning_rate": 1.0406192029680804e-05,
+      "loss": 0.3213047485351562,
+      "step": 7500
+    },
+    {
+      "epoch": 1.535213970447131,
+      "grad_norm": 17.288793563842773,
+      "learning_rate": 9.7665195419945e-06,
+      "loss": 0.3227524719238281,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6311648436000767,
+      "grad_norm": 3.9145667552948,
+      "learning_rate": 9.126847054308194e-06,
+      "loss": 0.3189747924804687,
+      "step": 8500
+    },
+    {
+      "epoch": 1.7271157167530224,
+      "grad_norm": 3.7356808185577393,
+      "learning_rate": 8.48717456662189e-06,
+      "loss": 0.33311187744140625,
+      "step": 9000
+    },
+    {
+      "epoch": 1.8230665899059681,
+      "grad_norm": 15.458077430725098,
+      "learning_rate": 7.847502078935586e-06,
+      "loss": 0.3166582946777344,
+      "step": 9500
+    },
+    {
+      "epoch": 1.9190174630589139,
+      "grad_norm": 0.5702362060546875,
+      "learning_rate": 7.207829591249281e-06,
+      "loss": 0.3185113525390625,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0149683362118593,
+      "grad_norm": 20.679962158203125,
+      "learning_rate": 6.568157103562976e-06,
+      "loss": 0.29407708740234373,
+      "step": 10500
+    },
+    {
+      "epoch": 2.110919209364805,
+      "grad_norm": 1.0656015872955322,
+      "learning_rate": 5.928484615876672e-06,
+      "loss": 0.27719247436523436,
+      "step": 11000
+    },
+    {
+      "epoch": 2.2068700825177507,
+      "grad_norm": 2.5045535564422607,
+      "learning_rate": 5.288812128190367e-06,
+      "loss": 0.2760169067382813,
+      "step": 11500
+    },
+    {
+      "epoch": 2.3028209556706964,
+      "grad_norm": 0.9866521954536438,
+      "learning_rate": 4.649139640504062e-06,
+      "loss": 0.25182223510742185,
+      "step": 12000
+    },
+    {
+      "epoch": 2.398771828823642,
+      "grad_norm": 0.861988365650177,
+      "learning_rate": 4.0094671528177575e-06,
+      "loss": 0.27130630493164065,
+      "step": 12500
+    },
+    {
+      "epoch": 2.494722701976588,
+      "grad_norm": 3.025139808654785,
+      "learning_rate": 3.3697946651314527e-06,
+      "loss": 0.2797826232910156,
+      "step": 13000
+    },
+    {
+      "epoch": 2.5906735751295336,
+      "grad_norm": 5.455494403839111,
+      "learning_rate": 2.7301221774451482e-06,
+      "loss": 0.274226806640625,
+      "step": 13500
+    },
+    {
+      "epoch": 2.6866244482824793,
+      "grad_norm": 10.867804527282715,
+      "learning_rate": 2.0904496897588438e-06,
+      "loss": 0.2681912841796875,
+      "step": 14000
+    },
+    {
+      "epoch": 2.782575321435425,
+      "grad_norm": 2.9777698516845703,
+      "learning_rate": 1.4507772020725389e-06,
+      "loss": 0.2753703002929688,
+      "step": 14500
+    },
+    {
+      "epoch": 2.8785261945883707,
+      "grad_norm": 14.00378704071045,
+      "learning_rate": 8.111047143862342e-07,
+      "loss": 0.2732333984375,
+      "step": 15000
+    },
+    {
+      "epoch": 2.9744770677413164,
+      "grad_norm": 4.573943614959717,
+      "learning_rate": 1.7143222669992966e-07,
+      "loss": 0.26397906494140627,
+      "step": 15500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15633,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4568883002906624e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-15633/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7010d8e51577a38b5b304dc130057e792156cfd67546e35490c409c520b99664
+size 4728

checkpoint-5211/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 3,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "HAPPY",
+    "1": "SAD"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "HAPPY": 0,
+    "SAD": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "5.0.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 48000
+}

checkpoint-5211/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54a3674be785ff96c3dc6a9c15c440a73466da3d4a866e70f3d82230d94a416e
+size 1412212656

checkpoint-5211/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf780085c2962571d3082a65276a5f305a79509e570593b2f510964c579c9c3
+size 2824660205

checkpoint-5211/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e18830d2e1b32b5415909b9f213b785b54d311c702e4a81e63c36ee0999346
+size 14244

checkpoint-5211/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d467fbe9fcf92f32237bcdf9a6a80ac02d3f9dd0dbc5dc7c9bb09695101e739
+size 1064

checkpoint-5211/tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}

checkpoint-5211/trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5211,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09595087315294569,
+      "grad_norm": 12.811051368713379,
+      "learning_rate": 1.936160685728907e-05,
+      "loss": 0.435078857421875,
+      "step": 500
+    },
+    {
+      "epoch": 0.19190174630589138,
+      "grad_norm": 8.909839630126953,
+      "learning_rate": 1.8721934369602766e-05,
+      "loss": 0.38166162109375,
+      "step": 1000
+    },
+    {
+      "epoch": 0.28785261945883706,
+      "grad_norm": 23.91183853149414,
+      "learning_rate": 1.8082261881916462e-05,
+      "loss": 0.3671803283691406,
+      "step": 1500
+    },
+    {
+      "epoch": 0.38380349261178276,
+      "grad_norm": 13.278630256652832,
+      "learning_rate": 1.7442589394230155e-05,
+      "loss": 0.34918722534179686,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47975436576472846,
+      "grad_norm": 6.475880146026611,
+      "learning_rate": 1.680291690654385e-05,
+      "loss": 0.35130245971679686,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5757052389176741,
+      "grad_norm": 5.953056812286377,
+      "learning_rate": 1.6163244418857547e-05,
+      "loss": 0.363922607421875,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6716561120706198,
+      "grad_norm": 9.432499885559082,
+      "learning_rate": 1.5523571931171243e-05,
+      "loss": 0.37142852783203123,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7676069852235655,
+      "grad_norm": 3.409161329269409,
+      "learning_rate": 1.4883899443484937e-05,
+      "loss": 0.3608262023925781,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8635578583765112,
+      "grad_norm": 1.59526789188385,
+      "learning_rate": 1.4244226955798633e-05,
+      "loss": 0.3568770446777344,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9595087315294569,
+      "grad_norm": 4.420688629150391,
+      "learning_rate": 1.3604554468112327e-05,
+      "loss": 0.3340596923828125,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15633,
+  "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": 4.856294334302208e+16,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5211/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7010d8e51577a38b5b304dc130057e792156cfd67546e35490c409c520b99664
+size 4728

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 3,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "HAPPY",
+    "1": "SAD"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "HAPPY": 0,
+    "SAD": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "5.0.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 48000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.8793330934388869,
+    "eval_loss": 0.36814266443252563,
+    "eval_runtime": 437.0819,
+    "eval_samples": 8337,
+    "eval_samples_per_second": 19.074,
+    "eval_steps_per_second": 2.386
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d967b4d0ab75d579d47f05cac9a4298b0a73260e0fee3415bd9839b5b82998
+size 1412212656

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "additional_special_tokens": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "is_local": false,
+  "mask_token": "<mask>",
+  "max_length": null,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.4568883002906624e+17,
+    "train_loss": 0.3201524627984222,
+    "train_runtime": 31218.1999,
+    "train_samples": 52110,
+    "train_samples_per_second": 5.008,
+    "train_steps_per_second": 0.501
+}

trainer_state.json

@@ -0,0 +1,260 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 15633,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09595087315294569,
+      "grad_norm": 12.811051368713379,
+      "learning_rate": 1.936160685728907e-05,
+      "loss": 0.435078857421875,
+      "step": 500
+    },
+    {
+      "epoch": 0.19190174630589138,
+      "grad_norm": 8.909839630126953,
+      "learning_rate": 1.8721934369602766e-05,
+      "loss": 0.38166162109375,
+      "step": 1000
+    },
+    {
+      "epoch": 0.28785261945883706,
+      "grad_norm": 23.91183853149414,
+      "learning_rate": 1.8082261881916462e-05,
+      "loss": 0.3671803283691406,
+      "step": 1500
+    },
+    {
+      "epoch": 0.38380349261178276,
+      "grad_norm": 13.278630256652832,
+      "learning_rate": 1.7442589394230155e-05,
+      "loss": 0.34918722534179686,
+      "step": 2000
+    },
+    {
+      "epoch": 0.47975436576472846,
+      "grad_norm": 6.475880146026611,
+      "learning_rate": 1.680291690654385e-05,
+      "loss": 0.35130245971679686,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5757052389176741,
+      "grad_norm": 5.953056812286377,
+      "learning_rate": 1.6163244418857547e-05,
+      "loss": 0.363922607421875,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6716561120706198,
+      "grad_norm": 9.432499885559082,
+      "learning_rate": 1.5523571931171243e-05,
+      "loss": 0.37142852783203123,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7676069852235655,
+      "grad_norm": 3.409161329269409,
+      "learning_rate": 1.4883899443484937e-05,
+      "loss": 0.3608262023925781,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8635578583765112,
+      "grad_norm": 1.59526789188385,
+      "learning_rate": 1.4244226955798633e-05,
+      "loss": 0.3568770446777344,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9595087315294569,
+      "grad_norm": 4.420688629150391,
+      "learning_rate": 1.3604554468112327e-05,
+      "loss": 0.3340596923828125,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0554596046824025,
+      "grad_norm": 8.594019889831543,
+      "learning_rate": 1.2964881980426023e-05,
+      "loss": 0.3522498779296875,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1514104778353482,
+      "grad_norm": 3.242337226867676,
+      "learning_rate": 1.2325209492739718e-05,
+      "loss": 0.32486505126953125,
+      "step": 6000
+    },
+    {
+      "epoch": 1.247361350988294,
+      "grad_norm": 20.167972564697266,
+      "learning_rate": 1.1685537005053414e-05,
+      "loss": 0.3254352416992187,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3433122241412396,
+      "grad_norm": 4.983191967010498,
+      "learning_rate": 1.1045864517367108e-05,
+      "loss": 0.330927490234375,
+      "step": 7000
+    },
+    {
+      "epoch": 1.4392630972941853,
+      "grad_norm": 1.6593592166900635,
+      "learning_rate": 1.0406192029680804e-05,
+      "loss": 0.3213047485351562,
+      "step": 7500
+    },
+    {
+      "epoch": 1.535213970447131,
+      "grad_norm": 17.288793563842773,
+      "learning_rate": 9.7665195419945e-06,
+      "loss": 0.3227524719238281,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6311648436000767,
+      "grad_norm": 3.9145667552948,
+      "learning_rate": 9.126847054308194e-06,
+      "loss": 0.3189747924804687,
+      "step": 8500
+    },
+    {
+      "epoch": 1.7271157167530224,
+      "grad_norm": 3.7356808185577393,
+      "learning_rate": 8.48717456662189e-06,
+      "loss": 0.33311187744140625,
+      "step": 9000
+    },
+    {
+      "epoch": 1.8230665899059681,
+      "grad_norm": 15.458077430725098,
+      "learning_rate": 7.847502078935586e-06,
+      "loss": 0.3166582946777344,
+      "step": 9500
+    },
+    {
+      "epoch": 1.9190174630589139,
+      "grad_norm": 0.5702362060546875,
+      "learning_rate": 7.207829591249281e-06,
+      "loss": 0.3185113525390625,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0149683362118593,
+      "grad_norm": 20.679962158203125,
+      "learning_rate": 6.568157103562976e-06,
+      "loss": 0.29407708740234373,
+      "step": 10500
+    },
+    {
+      "epoch": 2.110919209364805,
+      "grad_norm": 1.0656015872955322,
+      "learning_rate": 5.928484615876672e-06,
+      "loss": 0.27719247436523436,
+      "step": 11000
+    },
+    {
+      "epoch": 2.2068700825177507,
+      "grad_norm": 2.5045535564422607,
+      "learning_rate": 5.288812128190367e-06,
+      "loss": 0.2760169067382813,
+      "step": 11500
+    },
+    {
+      "epoch": 2.3028209556706964,
+      "grad_norm": 0.9866521954536438,
+      "learning_rate": 4.649139640504062e-06,
+      "loss": 0.25182223510742185,
+      "step": 12000
+    },
+    {
+      "epoch": 2.398771828823642,
+      "grad_norm": 0.861988365650177,
+      "learning_rate": 4.0094671528177575e-06,
+      "loss": 0.27130630493164065,
+      "step": 12500
+    },
+    {
+      "epoch": 2.494722701976588,
+      "grad_norm": 3.025139808654785,
+      "learning_rate": 3.3697946651314527e-06,
+      "loss": 0.2797826232910156,
+      "step": 13000
+    },
+    {
+      "epoch": 2.5906735751295336,
+      "grad_norm": 5.455494403839111,
+      "learning_rate": 2.7301221774451482e-06,
+      "loss": 0.274226806640625,
+      "step": 13500
+    },
+    {
+      "epoch": 2.6866244482824793,
+      "grad_norm": 10.867804527282715,
+      "learning_rate": 2.0904496897588438e-06,
+      "loss": 0.2681912841796875,
+      "step": 14000
+    },
+    {
+      "epoch": 2.782575321435425,
+      "grad_norm": 2.9777698516845703,
+      "learning_rate": 1.4507772020725389e-06,
+      "loss": 0.2753703002929688,
+      "step": 14500
+    },
+    {
+      "epoch": 2.8785261945883707,
+      "grad_norm": 14.00378704071045,
+      "learning_rate": 8.111047143862342e-07,
+      "loss": 0.2732333984375,
+      "step": 15000
+    },
+    {
+      "epoch": 2.9744770677413164,
+      "grad_norm": 4.573943614959717,
+      "learning_rate": 1.7143222669992966e-07,
+      "loss": 0.26397906494140627,
+      "step": 15500
+    },
+    {
+      "epoch": 3.0,
+      "step": 15633,
+      "total_flos": 1.4568883002906624e+17,
+      "train_loss": 0.3201524627984222,
+      "train_runtime": 31218.1999,
+      "train_samples_per_second": 5.008,
+      "train_steps_per_second": 0.501
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15633,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4568883002906624e+17,
+  "train_batch_size": 10,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7010d8e51577a38b5b304dc130057e792156cfd67546e35490c409c520b99664
+size 4728