Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40ace6b7f68e491503f3f0453773bb707b735093040bcbc0a9ee9ea5f06153ff
+oid sha256:94b59fc398e3d88713bc831c3d322eb6c6838032e33415b193eac195beaf4cba
 size 267835644

run-1/checkpoint-293/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-293/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e089bbc9cd78c347a78cca9b7cad7daff21b23bc49f4c5ab4fb2b9508e40dcc9
+size 267835644

run-1/checkpoint-293/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30c3e2e45d57f41e2a5b2eab0acb03913d34e2bd46c2cd9f22d625b2194c9e0b
+size 535733434

run-1/checkpoint-293/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daaaa89b7b1bab2fa04933ded1a6c818cc3571da63e407309c74707679303d33
+size 14244

run-1/checkpoint-293/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:980b6ab963933f55655dc372963796f58a1f92aafa769f3181edf6522946ac93
+size 1064

run-1/checkpoint-293/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-293/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-293/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.714041095890411,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-1/checkpoint-293",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 293,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.714041095890411,
+      "eval_loss": 0.71292644739151,
+      "eval_runtime": 3.3595,
+      "eval_samples_per_second": 173.834,
+      "eval_steps_per_second": 11.013,
+      "step": 293
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 879,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.116164785678467e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 11
+  }
+}

run-1/checkpoint-293/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c951fa1da432f037e0328021a81b295c930330a0d41058792b4862874cfb94
+size 4984

run-1/checkpoint-586/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-586/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:199dc9cae219623137e90af9e0134b8ca72c7d66c6d0abd02baaf0042fecbbf4
+size 267835644

run-1/checkpoint-586/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82410354dffa88b880a48f305a93c193b3e36f247dbcf8127f61428fe6b92e53
+size 535733434

run-1/checkpoint-586/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b6628e791854755f9f2b46d6247d9d5042fafd6d42e4755272e8a30cdfff0a2
+size 14244

run-1/checkpoint-586/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c21792ef7165e7d4fa6a70ef1128896bdab716c6454d666c5135746cd0c4ae9
+size 1064

run-1/checkpoint-586/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-586/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-586/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": 0.75,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-1/checkpoint-586",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 586,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.714041095890411,
+      "eval_loss": 0.71292644739151,
+      "eval_runtime": 3.3595,
+      "eval_samples_per_second": 173.834,
+      "eval_steps_per_second": 11.013,
+      "step": 293
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 8.596644401550293,
+      "learning_rate": 1.7747741226076666e-06,
+      "loss": 0.7782,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5617372989654541,
+      "eval_runtime": 3.3611,
+      "eval_samples_per_second": 173.75,
+      "eval_steps_per_second": 11.008,
+      "step": 586
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 879,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 632183474186820.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.116164785678467e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 11
+  }
+}

run-1/checkpoint-586/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c951fa1da432f037e0328021a81b295c930330a0d41058792b4862874cfb94
+size 4984

run-1/checkpoint-879/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-1/checkpoint-879/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b59fc398e3d88713bc831c3d322eb6c6838032e33415b193eac195beaf4cba
+size 267835644

run-1/checkpoint-879/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e09203973554802fd5663fb46c9b32c1402d6bb832a85a9cc95560b8f05e798
+size 535733434

run-1/checkpoint-879/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37466f5d0f5e1ddd6f1c1ea4fe863461db3862cf0a56198d957c7514ea828769
+size 14244

run-1/checkpoint-879/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3eff53e78e4c5d0b0a3a5df45af77f298cf98e1db52ef5bd0e487fd519be0a99
+size 1064

run-1/checkpoint-879/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-879/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-879/trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": 0.7585616438356164,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-SA/run-1/checkpoint-879",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 879,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.714041095890411,
+      "eval_loss": 0.71292644739151,
+      "eval_runtime": 3.3595,
+      "eval_samples_per_second": 173.834,
+      "eval_steps_per_second": 11.013,
+      "step": 293
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 8.596644401550293,
+      "learning_rate": 1.7747741226076666e-06,
+      "loss": 0.7782,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5617372989654541,
+      "eval_runtime": 3.3611,
+      "eval_samples_per_second": 173.75,
+      "eval_steps_per_second": 11.008,
+      "step": 586
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7585616438356164,
+      "eval_loss": 0.5336253643035889,
+      "eval_runtime": 3.3416,
+      "eval_samples_per_second": 174.767,
+      "eval_steps_per_second": 11.073,
+      "step": 879
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 879,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 632183474186820.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.116164785678467e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 11
+  }
+}

run-1/checkpoint-879/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c951fa1da432f037e0328021a81b295c930330a0d41058792b4862874cfb94
+size 4984

runs/Apr02_02-49-58_ef019a3ab26d/events.out.tfevents.1712026805.ef019a3ab26d.26.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec652e58d96532eb529b9b5da262d87b63ae7fc73fb84894d0db146033e977f
+size 6191

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdece1721090c1972a91e9dd9fe47f1498680c26311f0caf5e2ae7f7706cee28
+oid sha256:81c951fa1da432f037e0328021a81b295c930330a0d41058792b4862874cfb94
 size 4984