Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:900a1823c975131af95c0710cc51c8c2da4787c7bda44b6119bb2094927dee3e
+oid sha256:d584916b6a28403dd0ada8660a0095f2a1f96e4e1f68f6e3f7f423d02b050f7b
 size 437958648

run-3/checkpoint-1684/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-1684/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a411949e8d4292b0f30e8fb7284274709f42791372a9853e2358e3806d18c03
+size 437958648

run-3/checkpoint-1684/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a74e4616f6ccf1bcfcdc8a8bc0725374fe18eb81570caa80f45b23829ac991
+size 876038394

run-3/checkpoint-1684/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8ca0d38b2d45d3c9d4918c569fbe3dd185d1f237beeb7c56db6d97122a1fd4a
+size 14244

run-3/checkpoint-1684/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18288812d86c93d5ae8d3370b70750240ef12c1f61e859310236aeebb8c94ee1
+size 1064

run-3/checkpoint-1684/special_tokens_map.json

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

run-3/checkpoint-1684/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1684/trainer_state.json

@@ -0,0 +1,45 @@
+{
+  "best_metric": 0.518348623853211,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-3/checkpoint-1684",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1684,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4919724770642202,
+      "eval_loss": 0.7082622647285461,
+      "eval_runtime": 2.331,
+      "eval_samples_per_second": 374.089,
+      "eval_steps_per_second": 23.595,
+      "step": 842
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.518348623853211,
+      "eval_loss": 0.6900007128715515,
+      "eval_runtime": 2.3364,
+      "eval_samples_per_second": 373.226,
+      "eval_steps_per_second": 23.541,
+      "step": 1684
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 2526,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.843391089618415e-07,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 19,
+    "weight_decay": 0.4905221565015579
+  }
+}

run-3/checkpoint-1684/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03cbd15701e90c2de3ae1657b496ee63f3503759e5f1b61daaf03dea07e48a0
+size 4984

run-3/checkpoint-2526/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.3,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.3,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-2526/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d584916b6a28403dd0ada8660a0095f2a1f96e4e1f68f6e3f7f423d02b050f7b
+size 437958648

run-3/checkpoint-2526/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e181d6bad118a237469ce332ce097b00c9648b521378ff206e6771a4d50b9c8c
+size 876038394

run-3/checkpoint-2526/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05f4f66d01ea05137119f6a9a7a0593671a0dd328e43a884da05f06130cdc44
+size 14244

run-3/checkpoint-2526/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66bbb09602091f38a41fbb594a4e508296c5da43ffec0f9a966d004f08bf2a44
+size 1064

run-3/checkpoint-2526/special_tokens_map.json

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

run-3/checkpoint-2526/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": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-2526/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.5321100917431193,
+  "best_model_checkpoint": "Tech-oriented/best_model_bert_uncasedbert-base-uncased-finetuned-sst2/run-3/checkpoint-2526",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2526,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4919724770642202,
+      "eval_loss": 0.7082622647285461,
+      "eval_runtime": 2.331,
+      "eval_samples_per_second": 374.089,
+      "eval_steps_per_second": 23.595,
+      "step": 842
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.518348623853211,
+      "eval_loss": 0.6900007128715515,
+      "eval_runtime": 2.3364,
+      "eval_samples_per_second": 373.226,
+      "eval_steps_per_second": 23.541,
+      "step": 1684
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5321100917431193,
+      "eval_loss": 0.6852103471755981,
+      "eval_runtime": 2.3462,
+      "eval_samples_per_second": 371.672,
+      "eval_steps_per_second": 23.443,
+      "step": 2526
+    }
+  ],
+  "logging_steps": 4209,
+  "max_steps": 2526,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.843391089618415e-07,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 19,
+    "weight_decay": 0.4905221565015579
+  }
+}

run-3/checkpoint-2526/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03cbd15701e90c2de3ae1657b496ee63f3503759e5f1b61daaf03dea07e48a0
+size 4984

runs/Mar05_15-08-53_9d72474d753b/events.out.tfevents.1709652280.9d72474d753b.33271.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de217a3dbe9d7327f93ea3f7d8490ebea328a6dd4de7812460bf77fd505de7a
-size 5072
+oid sha256:69289d8c62747093c7002127c2df059791d108b91add55e1d042682c040223cc
+size 6072