distilbert-emotion-hyper

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: albert-base-v2
+base_model: lilyray/albert_emotion
 tags:
 - generated_from_trainer
 datasets:
@@ -22,7 +22,7 @@ model-index:
     metrics:
     - name: Accuracy
       type: accuracy
-      value: 0.9325
+      value: 0.9295
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -30,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # albert_emotion
 
-This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the emotion dataset.
+This model is a fine-tuned version of [lilyray/albert_emotion](https://huggingface.co/lilyray/albert_emotion) on the emotion dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.1943
-- Accuracy: 0.9325
+- Loss: 0.2391
+- Accuracy: 0.9295
 
 ## Model description
 
@@ -52,21 +52,19 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
-- train_batch_size: 8
+- learning_rate: 9.363600088100325e-06
+- train_batch_size: 4
 - eval_batch_size: 8
-- seed: 42
+- seed: 19
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 3
+- num_epochs: 1
 
 ### Training results
 
 | Training Loss | Epoch | Step | Validation Loss | Accuracy |
 |:-------------:|:-----:|:----:|:---------------:|:--------:|
-| 0.3186        | 1.0   | 2000 | 0.3021          | 0.916    |
-| 0.2018        | 2.0   | 4000 | 0.2196          | 0.934    |
-| 0.1207        | 3.0   | 6000 | 0.1971          | 0.936    |
+| 0.1744        | 1.0   | 4000 | 0.2001          | 0.938    |
 
 
 ### Framework versions

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "albert-base-v2",
+  "_name_or_path": "lilyray/albert_emotion",
   "architectures": [
     "AlbertForSequenceClassification"
   ],

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3bd7be388a3134ff3089b77cb56bbf7183b56379d3247445a3c02cb5edb4ccb
+oid sha256:6c9f4ca220fb8c8f18ad50a94a4835cce04a83390d626d73001af82f099061c9
 size 46756216

run-0/checkpoint-4000/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "lilyray/albert_emotion",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

run-0/checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9f4ca220fb8c8f18ad50a94a4835cce04a83390d626d73001af82f099061c9
+size 46756216

run-0/checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04baaddef98b9b3d10f7af173f5da9ff1ee547ec109053003b96cfd7897f02ae
+size 93528589

run-0/checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec7a852da27c217b438bad7e3dc6e4654f3e185131a6f1c6fdced0f575980260
+size 14244

run-0/checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f9ad246437bca3da1f271ab4e8c9d6670a66674291e9393e21a05eefa2c3667
+size 1064

run-0/checkpoint-4000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

run-0/checkpoint-4000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

run-0/checkpoint-4000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

run-0/checkpoint-4000/trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": 0.20014449954032898,
+  "best_model_checkpoint": "./albert_emotion/run-0/checkpoint-4000",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.5895392894744873,
+      "learning_rate": 8.193150077087784e-06,
+      "loss": 0.1782,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.041996244341135025,
+      "learning_rate": 7.022700066075244e-06,
+      "loss": 0.2179,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.02129148505628109,
+      "learning_rate": 5.852250055062703e-06,
+      "loss": 0.2007,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.011637452058494091,
+      "learning_rate": 4.6818000440501625e-06,
+      "loss": 0.1845,
+      "step": 2000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.7839567065238953,
+      "learning_rate": 3.511350033037622e-06,
+      "loss": 0.1674,
+      "step": 2500
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 21.355159759521484,
+      "learning_rate": 2.3409000220250813e-06,
+      "loss": 0.1903,
+      "step": 3000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.0020764770451933146,
+      "learning_rate": 1.1704500110125406e-06,
+      "loss": 0.1459,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.024950213730335236,
+      "learning_rate": 0.0,
+      "loss": 0.1744,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.938,
+      "eval_loss": 0.20014449954032898,
+      "eval_runtime": 23.7683,
+      "eval_samples_per_second": 84.146,
+      "eval_steps_per_second": 10.518,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 382520819712000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.363600088100325e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 19
+  }
+}

run-0/checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc54fb364a92da07bae7429ee017efe39a94ff6dde12fc714abceb63950444f4
+size 4920

run-1/checkpoint-12000/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "lilyray/albert_emotion",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

run-1/checkpoint-12000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d74e7e217204e16e12d1470df069950545a7c8e6d11c2125ef6ac811356e71e6
+size 46756216

run-1/checkpoint-12000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd6db33e57cdc795f7370fbbc9657ead92277c1830798eb20e0916ad06830536
+size 93528589

run-1/checkpoint-12000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76facf651161fc3ecb4108718251c45d084d225bbcad2b6d151a8274c5618459
+size 14244

run-1/checkpoint-12000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b178e4c67824c76c5bfa9fa17c1cb191754d2a695b44af06c37ebd566a5277e
+size 1064

run-1/checkpoint-12000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-12000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

run-1/checkpoint-12000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-12000/trainer_state.json

@@ -0,0 +1,221 @@
+{
+  "best_metric": 0.24552112817764282,
+  "best_model_checkpoint": "./albert_emotion/run-1/checkpoint-4000",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 12000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.027287261560559273,
+      "learning_rate": 1.1966787450728162e-06,
+      "loss": 0.0943,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.007144883740693331,
+      "learning_rate": 1.158076204909177e-06,
+      "loss": 0.1192,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.017046278342604637,
+      "learning_rate": 1.1194736647455377e-06,
+      "loss": 0.1077,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 20.33992576599121,
+      "learning_rate": 1.0808711245818985e-06,
+      "loss": 0.145,
+      "step": 2000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.004928311333060265,
+      "learning_rate": 1.0422685844182593e-06,
+      "loss": 0.1311,
+      "step": 2500
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.009308135136961937,
+      "learning_rate": 1.00366604425462e-06,
+      "loss": 0.1226,
+      "step": 3000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.002149054082110524,
+      "learning_rate": 9.650635040909807e-07,
+      "loss": 0.1444,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0062008146196603775,
+      "learning_rate": 9.264609639273415e-07,
+      "loss": 0.1587,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.937,
+      "eval_loss": 0.24552112817764282,
+      "eval_runtime": 23.8526,
+      "eval_samples_per_second": 83.848,
+      "eval_steps_per_second": 10.481,
+      "step": 4000
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 22.703540802001953,
+      "learning_rate": 8.878584237637023e-07,
+      "loss": 0.1139,
+      "step": 4500
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.018092291429638863,
+      "learning_rate": 8.492558836000631e-07,
+      "loss": 0.1361,
+      "step": 5000
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.011323424987494946,
+      "learning_rate": 8.106533434364239e-07,
+      "loss": 0.123,
+      "step": 5500
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.003476408077403903,
+      "learning_rate": 7.720508032727847e-07,
+      "loss": 0.12,
+      "step": 6000
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.026127604767680168,
+      "learning_rate": 7.334482631091454e-07,
+      "loss": 0.1196,
+      "step": 6500
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 32.6096076965332,
+      "learning_rate": 6.948457229455062e-07,
+      "loss": 0.1199,
+      "step": 7000
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.0031733482610434294,
+      "learning_rate": 6.562431827818669e-07,
+      "loss": 0.1074,
+      "step": 7500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.014037689194083214,
+      "learning_rate": 6.176406426182277e-07,
+      "loss": 0.1336,
+      "step": 8000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9335,
+      "eval_loss": 0.2784283757209778,
+      "eval_runtime": 23.8236,
+      "eval_samples_per_second": 83.95,
+      "eval_steps_per_second": 10.494,
+      "step": 8000
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.0019384464249014854,
+      "learning_rate": 5.790381024545885e-07,
+      "loss": 0.1199,
+      "step": 8500
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.007850521244108677,
+      "learning_rate": 5.404355622909492e-07,
+      "loss": 0.1195,
+      "step": 9000
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.3905338943004608,
+      "learning_rate": 5.0183302212731e-07,
+      "loss": 0.1143,
+      "step": 9500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.0038829813711345196,
+      "learning_rate": 4.6323048196367076e-07,
+      "loss": 0.1005,
+      "step": 10000
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.0025081851053982973,
+      "learning_rate": 4.2462794180003157e-07,
+      "loss": 0.1006,
+      "step": 10500
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.0029693343676626682,
+      "learning_rate": 3.8602540163639233e-07,
+      "loss": 0.1055,
+      "step": 11000
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.0075212884694337845,
+      "learning_rate": 3.474228614727531e-07,
+      "loss": 0.0892,
+      "step": 11500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.01758272759616375,
+      "learning_rate": 3.0882032130911386e-07,
+      "loss": 0.1181,
+      "step": 12000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.934,
+      "eval_loss": 0.29778438806533813,
+      "eval_runtime": 23.8749,
+      "eval_samples_per_second": 83.77,
+      "eval_steps_per_second": 10.471,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 16000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1147562459136000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2352812852364554e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 18
+  }
+}

run-1/checkpoint-12000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21bcd66d0c63173564964a8f0cb271364f443120673a2d61a746bc1cac25c2f
+size 4920

run-1/checkpoint-16000/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "lilyray/albert_emotion",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

run-1/checkpoint-16000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6f0627e728caaff09e615dd0c91be7b23e6b74b1b84009e1b5df84057bed1f
+size 46756216

run-1/checkpoint-16000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d761d19c54c268cfe5c7d62cd792066265268e25f4cf4dcdbeb27de274299ef
+size 93528589

run-1/checkpoint-16000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e09177cb571c6fc30997814a2cc2e51b7c69366f36ffb4f05beb9832aec029
+size 14244

run-1/checkpoint-16000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b72072762b71d361472d5bd69dc1c822ad8870128e9f33e92009a7fafeca88c
+size 1064

run-1/checkpoint-16000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-16000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

run-1/checkpoint-16000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-16000/trainer_state.json

@@ -0,0 +1,286 @@
+{
+  "best_metric": 0.24552112817764282,
+  "best_model_checkpoint": "./albert_emotion/run-1/checkpoint-4000",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 16000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.027287261560559273,
+      "learning_rate": 1.1966787450728162e-06,
+      "loss": 0.0943,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.007144883740693331,
+      "learning_rate": 1.158076204909177e-06,
+      "loss": 0.1192,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.017046278342604637,
+      "learning_rate": 1.1194736647455377e-06,
+      "loss": 0.1077,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 20.33992576599121,
+      "learning_rate": 1.0808711245818985e-06,
+      "loss": 0.145,
+      "step": 2000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.004928311333060265,
+      "learning_rate": 1.0422685844182593e-06,
+      "loss": 0.1311,
+      "step": 2500
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.009308135136961937,
+      "learning_rate": 1.00366604425462e-06,
+      "loss": 0.1226,
+      "step": 3000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.002149054082110524,
+      "learning_rate": 9.650635040909807e-07,
+      "loss": 0.1444,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0062008146196603775,
+      "learning_rate": 9.264609639273415e-07,
+      "loss": 0.1587,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.937,
+      "eval_loss": 0.24552112817764282,
+      "eval_runtime": 23.8526,
+      "eval_samples_per_second": 83.848,
+      "eval_steps_per_second": 10.481,
+      "step": 4000
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 22.703540802001953,
+      "learning_rate": 8.878584237637023e-07,
+      "loss": 0.1139,
+      "step": 4500
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.018092291429638863,
+      "learning_rate": 8.492558836000631e-07,
+      "loss": 0.1361,
+      "step": 5000
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.011323424987494946,
+      "learning_rate": 8.106533434364239e-07,
+      "loss": 0.123,
+      "step": 5500
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.003476408077403903,
+      "learning_rate": 7.720508032727847e-07,
+      "loss": 0.12,
+      "step": 6000
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.026127604767680168,
+      "learning_rate": 7.334482631091454e-07,
+      "loss": 0.1196,
+      "step": 6500
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 32.6096076965332,
+      "learning_rate": 6.948457229455062e-07,
+      "loss": 0.1199,
+      "step": 7000
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.0031733482610434294,
+      "learning_rate": 6.562431827818669e-07,
+      "loss": 0.1074,
+      "step": 7500
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.014037689194083214,
+      "learning_rate": 6.176406426182277e-07,
+      "loss": 0.1336,
+      "step": 8000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9335,
+      "eval_loss": 0.2784283757209778,
+      "eval_runtime": 23.8236,
+      "eval_samples_per_second": 83.95,
+      "eval_steps_per_second": 10.494,
+      "step": 8000
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.0019384464249014854,
+      "learning_rate": 5.790381024545885e-07,
+      "loss": 0.1199,
+      "step": 8500
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.007850521244108677,
+      "learning_rate": 5.404355622909492e-07,
+      "loss": 0.1195,
+      "step": 9000
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.3905338943004608,
+      "learning_rate": 5.0183302212731e-07,
+      "loss": 0.1143,
+      "step": 9500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.0038829813711345196,
+      "learning_rate": 4.6323048196367076e-07,
+      "loss": 0.1005,
+      "step": 10000
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.0025081851053982973,
+      "learning_rate": 4.2462794180003157e-07,
+      "loss": 0.1006,
+      "step": 10500
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.0029693343676626682,
+      "learning_rate": 3.8602540163639233e-07,
+      "loss": 0.1055,
+      "step": 11000
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.0075212884694337845,
+      "learning_rate": 3.474228614727531e-07,
+      "loss": 0.0892,
+      "step": 11500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.01758272759616375,
+      "learning_rate": 3.0882032130911386e-07,
+      "loss": 0.1181,
+      "step": 12000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.934,
+      "eval_loss": 0.29778438806533813,
+      "eval_runtime": 23.8749,
+      "eval_samples_per_second": 83.77,
+      "eval_steps_per_second": 10.471,
+      "step": 12000
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 0.0022781568113714457,
+      "learning_rate": 2.702177811454746e-07,
+      "loss": 0.0989,
+      "step": 12500
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.2688106596469879,
+      "learning_rate": 2.3161524098183538e-07,
+      "loss": 0.1176,
+      "step": 13000
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 0.0026019506622105837,
+      "learning_rate": 1.9301270081819617e-07,
+      "loss": 0.0959,
+      "step": 13500
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 121.57093048095703,
+      "learning_rate": 1.5441016065455693e-07,
+      "loss": 0.0767,
+      "step": 14000
+    },
+    {
+      "epoch": 3.62,
+      "grad_norm": 0.005118395667523146,
+      "learning_rate": 1.1580762049091769e-07,
+      "loss": 0.0944,
+      "step": 14500
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.005758533254265785,
+      "learning_rate": 7.720508032727846e-08,
+      "loss": 0.0803,
+      "step": 15000
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 0.005111873149871826,
+      "learning_rate": 3.860254016363923e-08,
+      "loss": 0.0794,
+      "step": 15500
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.011210494674742222,
+      "learning_rate": 0.0,
+      "loss": 0.1173,
+      "step": 16000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.932,
+      "eval_loss": 0.31061089038848877,
+      "eval_runtime": 23.8961,
+      "eval_samples_per_second": 83.696,
+      "eval_steps_per_second": 10.462,
+      "step": 16000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 16000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 1530083278848000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2352812852364554e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 18
+  }
+}

run-1/checkpoint-16000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21bcd66d0c63173564964a8f0cb271364f443120673a2d61a746bc1cac25c2f
+size 4920

run-1/checkpoint-4000/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "lilyray/albert_emotion",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

run-1/checkpoint-4000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:156fcaf3367f7c541456accd7fef964e69c0f4257da2fcef3d580cd52b6b8399
+size 46756216

run-1/checkpoint-4000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be4c2acf3369aa065e68e4ab27b59e1920e75ac29bad862ee9ef76fae05f986f
+size 93528589

run-1/checkpoint-4000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb2c6a03442be17a3db9eb719b0b8bbb044bc088befa9c99aaa534d072e20c7d
+size 14244

run-1/checkpoint-4000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b63d5c23eb8f6fcf166011a4c23ed4426dc8ebe53b8492ed0deebb7a7161c72b
+size 1064

run-1/checkpoint-4000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-4000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289

run-1/checkpoint-4000/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-4000/trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_metric": 0.24552112817764282,
+  "best_model_checkpoint": "./albert_emotion/run-1/checkpoint-4000",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.027287261560559273,
+      "learning_rate": 1.1966787450728162e-06,
+      "loss": 0.0943,
+      "step": 500
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.007144883740693331,
+      "learning_rate": 1.158076204909177e-06,
+      "loss": 0.1192,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.017046278342604637,
+      "learning_rate": 1.1194736647455377e-06,
+      "loss": 0.1077,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 20.33992576599121,
+      "learning_rate": 1.0808711245818985e-06,
+      "loss": 0.145,
+      "step": 2000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.004928311333060265,
+      "learning_rate": 1.0422685844182593e-06,
+      "loss": 0.1311,
+      "step": 2500
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.009308135136961937,
+      "learning_rate": 1.00366604425462e-06,
+      "loss": 0.1226,
+      "step": 3000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.002149054082110524,
+      "learning_rate": 9.650635040909807e-07,
+      "loss": 0.1444,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0062008146196603775,
+      "learning_rate": 9.264609639273415e-07,
+      "loss": 0.1587,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.937,
+      "eval_loss": 0.24552112817764282,
+      "eval_runtime": 23.8526,
+      "eval_samples_per_second": 83.848,
+      "eval_steps_per_second": 10.481,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 16000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 382520819712000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2352812852364554e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 18
+  }
+}

run-1/checkpoint-4000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21bcd66d0c63173564964a8f0cb271364f443120673a2d61a746bc1cac25c2f
+size 4920

run-1/checkpoint-8000/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "lilyray/albert_emotion",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

run-1/checkpoint-8000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:068474bcd6bb43ca5976ef5255229e83f258e79232f717aaa948eb613cc053f9
+size 46756216

run-1/checkpoint-8000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b377e267df21a9617e41ec2f5dafe299ed22741e515eb243ef412039f2bbfba4
+size 93528589

run-1/checkpoint-8000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f536c4fc51ba22c8463ac798baed56358909f7916ff76c65faf7c7ab5fae3b7e
+size 14244

run-1/checkpoint-8000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66df00838ae5a810d2c870ea68518f1032da528e2df9a2c35bd7cd9142aa7c55
+size 1064

run-1/checkpoint-8000/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-8000/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
+size 760289