Training in progress, epoch 1

logs/events.out.tfevents.1709748697.d65e8524b0f6.5185.21

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef590dead44772f2ee831d4bc41d013aa2689aa54b55765ef13016a1f6685cd9
-size 5985
+oid sha256:6b326b8b922d402e11c9d8ccc78036e6cbe235eddea45aad933ef6fdbf25e6df
+size 7705

logs/events.out.tfevents.1709749139.d65e8524b0f6.5185.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:243e0ee847490474fd07e9ec81e31416de0c6d1a89d6c910eb380c00b962a442
+size 5313

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f76b8e9d1f67f9b433ce0b747eaefb4717964e4ff51b59ef03cffd276f3dbe
+oid sha256:44c120b54fd669f33f415ab00eadf71e828c642fcb280379e4e68323698fc046
 size 17549312

run-21/checkpoint-156/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "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-21/checkpoint-156/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8fb3e7a27c82807500b3ec68bc657387013cf10a996199e945b1f3b01c2795b
+size 17549312

run-21/checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1958680b9707519142c99a3618d9001f6c418cacd0b9605957ef05febb3cadf5
+size 35122746

run-21/checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f3f2bf3b854c592a6f1e0e90f14af49f8d742650373f022831e4b62d27ad7a2
+size 14054

run-21/checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccc1b9a873ffc927473096e4bcf6be58267e96371fc18313b8496d12cd4d5224
+size 1064

run-21/checkpoint-156/special_tokens_map.json

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

run-21/checkpoint-156/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-21/checkpoint-156/trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": 0.7504892367906066,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-104",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.939810276031494,
+      "learning_rate": 0.00013471680923458288,
+      "loss": 0.5033,
+      "step": 52
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7152641878669276,
+      "eval_f1": 0.712166172106825,
+      "eval_loss": 0.4479813575744629,
+      "eval_precision": 0.72,
+      "eval_recall": 0.7045009784735812,
+      "eval_runtime": 28.0693,
+      "eval_samples_per_second": 36.41,
+      "eval_steps_per_second": 1.14,
+      "step": 52
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.902515411376953,
+      "learning_rate": 8.981120615638859e-05,
+      "loss": 0.4475,
+      "step": 104
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7504892367906066,
+      "eval_f1": 0.7578347578347578,
+      "eval_loss": 0.42175495624542236,
+      "eval_precision": 0.7361623616236163,
+      "eval_recall": 0.7808219178082192,
+      "eval_runtime": 27.9965,
+      "eval_samples_per_second": 36.505,
+      "eval_steps_per_second": 1.143,
+      "step": 104
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.328202724456787,
+      "learning_rate": 4.4905603078194294e-05,
+      "loss": 0.4233,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7201565557729941,
+      "eval_f1": 0.6857142857142856,
+      "eval_loss": 0.415389746427536,
+      "eval_precision": 0.7819548872180451,
+      "eval_recall": 0.6105675146771037,
+      "eval_runtime": 28.1971,
+      "eval_samples_per_second": 36.245,
+      "eval_steps_per_second": 1.135,
+      "step": 156
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 707085591840.0,
+  "train_batch_size": 60,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7020704368642945,
+    "learning_rate": 0.00017962241231277718,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 60,
+    "temperature": 19
+  }
+}

run-21/checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe829315cd1ce1b368ca5aa1539a6e655572843d060f6af981de772385e9701
+size 4920

run-21/checkpoint-208/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "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-21/checkpoint-208/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa8c12b34db4caa4aa05168b916ae65ef07eec0279de7abd53e115744a573909
+size 17549312

run-21/checkpoint-208/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707810b82af2863c354b43e11120fe875bdde16840fa76be0d6f6e96e00df9f6
+size 35122746

run-21/checkpoint-208/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b6ed2075102dd75f9c18fe89ccd178319808314220b3c31c67cb30308a85909
+size 14054

run-21/checkpoint-208/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff997d3a0b6bdcde1a920243f3b68a38d81cbfb189c7690b7052ae0d3a22aa2
+size 1064

run-21/checkpoint-208/special_tokens_map.json

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

run-21/checkpoint-208/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-21/checkpoint-208/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": 0.7906066536203522,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-208",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 208,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.939810276031494,
+      "learning_rate": 0.00013471680923458288,
+      "loss": 0.5033,
+      "step": 52
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7152641878669276,
+      "eval_f1": 0.712166172106825,
+      "eval_loss": 0.4479813575744629,
+      "eval_precision": 0.72,
+      "eval_recall": 0.7045009784735812,
+      "eval_runtime": 28.0693,
+      "eval_samples_per_second": 36.41,
+      "eval_steps_per_second": 1.14,
+      "step": 52
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.902515411376953,
+      "learning_rate": 8.981120615638859e-05,
+      "loss": 0.4475,
+      "step": 104
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7504892367906066,
+      "eval_f1": 0.7578347578347578,
+      "eval_loss": 0.42175495624542236,
+      "eval_precision": 0.7361623616236163,
+      "eval_recall": 0.7808219178082192,
+      "eval_runtime": 27.9965,
+      "eval_samples_per_second": 36.505,
+      "eval_steps_per_second": 1.143,
+      "step": 104
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.328202724456787,
+      "learning_rate": 4.4905603078194294e-05,
+      "loss": 0.4233,
+      "step": 156
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7201565557729941,
+      "eval_f1": 0.6857142857142856,
+      "eval_loss": 0.415389746427536,
+      "eval_precision": 0.7819548872180451,
+      "eval_recall": 0.6105675146771037,
+      "eval_runtime": 28.1971,
+      "eval_samples_per_second": 36.245,
+      "eval_steps_per_second": 1.135,
+      "step": 156
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.079658508300781,
+      "learning_rate": 0.0,
+      "loss": 0.4193,
+      "step": 208
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7906066536203522,
+      "eval_f1": 0.8007448789571694,
+      "eval_loss": 0.4070701003074646,
+      "eval_precision": 0.7637655417406749,
+      "eval_recall": 0.8414872798434442,
+      "eval_runtime": 27.9567,
+      "eval_samples_per_second": 36.557,
+      "eval_steps_per_second": 1.145,
+      "step": 208
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 208,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 942780789120.0,
+  "train_batch_size": 60,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7020704368642945,
+    "learning_rate": 0.00017962241231277718,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 60,
+    "temperature": 19
+  }
+}

run-21/checkpoint-208/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe829315cd1ce1b368ca5aa1539a6e655572843d060f6af981de772385e9701
+size 4920

run-22/checkpoint-73/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "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-22/checkpoint-73/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c120b54fd669f33f415ab00eadf71e828c642fcb280379e4e68323698fc046
+size 17549312

run-22/checkpoint-73/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611ef02219b5048bf7d76ef651f30f7843251339392e4c484c0e4a579cf0d056
+size 35122746

run-22/checkpoint-73/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c42846858a5e0d6a622704e299ce8fbbbb35d1bc8a006bfa388d93deb44fa1
+size 14054

run-22/checkpoint-73/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2553c8ee13b391e83f4e8036597f099a9b8867f2315b9a912ebba86609070a
+size 1064

run-22/checkpoint-73/special_tokens_map.json

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

run-22/checkpoint-73/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-22/checkpoint-73/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.538160469667319,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-73",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 73,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7895054817199707,
+      "learning_rate": 4.53929460427656e-05,
+      "loss": 0.592,
+      "step": 73
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.538160469667319,
+      "eval_f1": 0.1945392491467577,
+      "eval_loss": 0.5740381479263306,
+      "eval_precision": 0.76,
+      "eval_recall": 0.11154598825831702,
+      "eval_runtime": 28.0661,
+      "eval_samples_per_second": 36.414,
+      "eval_steps_per_second": 1.14,
+      "step": 73
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 219,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 42,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8218865571627406,
+    "learning_rate": 6.80894190641484e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 42,
+    "temperature": 18
+  }
+}

run-22/checkpoint-73/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af01c8cc931e90be8609f6f102e02c380f096eaceeec5ba79858d8a3dfed157c
+size 4920

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 33,
+    "max_length": 31,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32f042525736aa17960ee8344101391e82f28237778df28fde71ca14364b664f
+oid sha256:af01c8cc931e90be8609f6f102e02c380f096eaceeec5ba79858d8a3dfed157c
 size 4920