Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:884af16d84b89cb06eea70faae60faad6a3558e8e0f7a3bb5a7c5bb43f13296b
+oid sha256:0c84327d2f34d0aabb099e33ec19322ae4e3b524037c27c164a5849098c07c6a
 size 98470112

run-2/checkpoint-428/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "MobileBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
+  "vocab_size": 30522
+}

run-2/checkpoint-428/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aefa0dba0709f284a1ed2b9126aa98619040139734c19863cdf945454a4e133c
+size 98470112

run-2/checkpoint-428/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9beffc9bbc3bd4a7751cc1d7403a05e2ab3894cd2b32345c590b16174c17e8df
+size 197593757

run-2/checkpoint-428/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf7165d7bc3dc4fbc35a777f680022b8d03c0c94a7ef25837abf0db14c439a1b
+size 14244

run-2/checkpoint-428/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe441be73df37559032d5092a02e48a7882d54449f68e06c1c31cd4e9ca99abc
+size 1064

run-2/checkpoint-428/special_tokens_map.json

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

run-2/checkpoint-428/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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-428/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": 0.28645918324628383,
+  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-2/checkpoint-428",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 428,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6210973262786865,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.6225,
+      "eval_samples_per_second": 397.71,
+      "eval_steps_per_second": 25.167,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5920795798301697,
+      "eval_matthews_correlation": 0.21064445407191215,
+      "eval_runtime": 2.632,
+      "eval_samples_per_second": 396.273,
+      "eval_steps_per_second": 25.076,
+      "step": 214
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5994917154312134,
+      "eval_matthews_correlation": 0.19960461390161852,
+      "eval_runtime": 2.6454,
+      "eval_samples_per_second": 394.269,
+      "eval_steps_per_second": 24.949,
+      "step": 321
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6307967901229858,
+      "eval_matthews_correlation": 0.28645918324628383,
+      "eval_runtime": 2.6297,
+      "eval_samples_per_second": 396.623,
+      "eval_steps_per_second": 25.098,
+      "step": 428
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 535,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.824155428115656e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 1
+  }
+}

run-2/checkpoint-428/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0926346707a8d66976e74089ae692911018b9e10991497cdb1023e38ec538cc
+size 4920

run-2/checkpoint-535/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "MobileBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
+  "vocab_size": 30522
+}

run-2/checkpoint-535/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c84327d2f34d0aabb099e33ec19322ae4e3b524037c27c164a5849098c07c6a
+size 98470112

run-2/checkpoint-535/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15057bdf2b678b6f37b5da4d0efafb57a18a94f24e1dda599a1584cbd5a553db
+size 197593757

run-2/checkpoint-535/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f32ffd881fd9fac83f9730e1c2eae00e5cc2aca185560d8dba9bb612b6252aa
+size 14244

run-2/checkpoint-535/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8ba6eb815fab6bdc40c048cff3aa700391dc196ee605326670389c606d7c39
+size 1064

run-2/checkpoint-535/special_tokens_map.json

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

run-2/checkpoint-535/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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-535/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_metric": 0.28645918324628383,
+  "best_model_checkpoint": "mobilebert-uncased-finetuned-cola/run-2/checkpoint-428",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 535,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6210973262786865,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.6225,
+      "eval_samples_per_second": 397.71,
+      "eval_steps_per_second": 25.167,
+      "step": 107
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5920795798301697,
+      "eval_matthews_correlation": 0.21064445407191215,
+      "eval_runtime": 2.632,
+      "eval_samples_per_second": 396.273,
+      "eval_steps_per_second": 25.076,
+      "step": 214
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5994917154312134,
+      "eval_matthews_correlation": 0.19960461390161852,
+      "eval_runtime": 2.6454,
+      "eval_samples_per_second": 394.269,
+      "eval_steps_per_second": 24.949,
+      "step": 321
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6307967901229858,
+      "eval_matthews_correlation": 0.28645918324628383,
+      "eval_runtime": 2.6297,
+      "eval_samples_per_second": 396.623,
+      "eval_steps_per_second": 25.098,
+      "step": 428
+    },
+    {
+      "epoch": 4.67,
+      "grad_norm": 6.2872796058654785,
+      "learning_rate": 2.5017839249354755e-06,
+      "loss": 26656.036,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.7777205109596252,
+      "eval_matthews_correlation": 0.2712686505720511,
+      "eval_runtime": 2.6436,
+      "eval_samples_per_second": 394.536,
+      "eval_steps_per_second": 24.966,
+      "step": 535
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 535,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 9158383522080.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 3.824155428115656e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "seed": 1
+  }
+}

run-2/checkpoint-535/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0926346707a8d66976e74089ae692911018b9e10991497cdb1023e38ec538cc
+size 4920

runs/Mar07_08-06-39_49d4a3166cad/events.out.tfevents.1709799960.49d4a3166cad.3288.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4488071e32d523c3c9c7b3c0693b5a7cc826461e9c719a2bfc5383793d966ce
-size 5873
+oid sha256:390b9282224a09b32e6804d4f932ad17e081030884eca53b363cea1f21fc66eb
+size 7108