Training in progress, epoch 2

logs/events.out.tfevents.1709736673.fcc57e6e3903.3035.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69344581e0fcc51aa41844298fe2ff3046067d22f6971849ddf588380f63dabe
-size 6010
+oid sha256:5b078135172b0350439af60ac9244ca64ad1da002b651984ae20ef05672a4bd4
+size 9096

logs/events.out.tfevents.1709738746.fcc57e6e3903.3035.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b264f3ff29bc08479f86cee904af2cfde644ea59393644b34002bb7045c8bf
+size 6011

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be42edc346c7f56c37cff9a80b3c02409f2124ea659e9dd6917a018effc61a95
+oid sha256:1746506c121949c786023a52d18d62525be5d15306044e069e1128c586165bce
 size 17549312

run-1/checkpoint-2850/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-1/checkpoint-2850/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d935c7212a6deb6bff0572cdf085215bd443c92e021b37370453e60c287d968a
+size 17549312

run-1/checkpoint-2850/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e475cdd022c4e270259045e7fea6dedb8df380c609cc254d49be3fffb3381230
+size 35122746

run-1/checkpoint-2850/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652965c8804a6472e7215d2bf1eaef27dd5fcc81ca0a4e464e1e2245a7b3c0df
+size 14054

run-1/checkpoint-2850/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fcf549389dbc0464b07a358eaed8f9af842c18152b7acc6b4ef98f89fae0797
+size 1064

run-1/checkpoint-2850/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-2850/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-1/checkpoint-2850/trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": 0.5207920792079208,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-475",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 2850,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4949035942554474,
+      "learning_rate": 1.755924298388821e-05,
+      "loss": 0.2107,
+      "step": 475
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5207920792079208,
+      "eval_f1": 0.1597222222222222,
+      "eval_loss": 0.19466964900493622,
+      "eval_precision": 0.6388888888888888,
+      "eval_recall": 0.09126984126984126,
+      "eval_runtime": 15.6911,
+      "eval_samples_per_second": 32.184,
+      "eval_steps_per_second": 1.02,
+      "step": 475
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5680577754974365,
+      "learning_rate": 1.4047394387110566e-05,
+      "loss": 0.1957,
+      "step": 950
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_f1": 0.14685314685314682,
+      "eval_loss": 0.19141286611557007,
+      "eval_precision": 0.6176470588235294,
+      "eval_recall": 0.08333333333333333,
+      "eval_runtime": 15.1911,
+      "eval_samples_per_second": 33.243,
+      "eval_steps_per_second": 1.053,
+      "step": 950
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.45545563101768494,
+      "learning_rate": 1.0535545790332925e-05,
+      "loss": 0.1943,
+      "step": 1425
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5148514851485149,
+      "eval_f1": 0.14634146341463414,
+      "eval_loss": 0.1912413090467453,
+      "eval_precision": 0.6,
+      "eval_recall": 0.08333333333333333,
+      "eval_runtime": 15.2913,
+      "eval_samples_per_second": 33.025,
+      "eval_steps_per_second": 1.046,
+      "step": 1425
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.33228880167007446,
+      "learning_rate": 7.023697193555283e-06,
+      "loss": 0.1936,
+      "step": 1900
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_f1": 0.14685314685314682,
+      "eval_loss": 0.190897598862648,
+      "eval_precision": 0.6176470588235294,
+      "eval_recall": 0.08333333333333333,
+      "eval_runtime": 15.1905,
+      "eval_samples_per_second": 33.244,
+      "eval_steps_per_second": 1.053,
+      "step": 1900
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.3122839331626892,
+      "learning_rate": 3.5118485967776416e-06,
+      "loss": 0.1933,
+      "step": 2375
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5148514851485149,
+      "eval_f1": 0.14634146341463414,
+      "eval_loss": 0.19050733745098114,
+      "eval_precision": 0.6,
+      "eval_recall": 0.08333333333333333,
+      "eval_runtime": 15.1983,
+      "eval_samples_per_second": 33.227,
+      "eval_steps_per_second": 1.053,
+      "step": 2375
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.29782089591026306,
+      "learning_rate": 0.0,
+      "loss": 0.193,
+      "step": 2850
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.5128712871287129,
+      "eval_f1": 0.13986013986013984,
+      "eval_loss": 0.19041746854782104,
+      "eval_precision": 0.5882352941176471,
+      "eval_recall": 0.07936507936507936,
+      "eval_runtime": 15.2095,
+      "eval_samples_per_second": 33.203,
+      "eval_steps_per_second": 1.052,
+      "step": 2850
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 4667059698840.0,
+  "train_batch_size": 20,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.22818780511125447,
+    "learning_rate": 2.107109158066585e-05,
+    "num_train_epochs": 6,
+    "per_device_train_batch_size": 20,
+    "temperature": 6
+  }
+}

run-1/checkpoint-2850/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ccea265ae9122da077ff8def664c83c587f85ed26bee202b170a564116cd542
+size 4920

run-2/checkpoint-1188/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-2/checkpoint-1188/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1746506c121949c786023a52d18d62525be5d15306044e069e1128c586165bce
+size 17549312

run-2/checkpoint-1188/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:506eb862ac3c79dfbe5f19b5dd60ebcf7f4b2203515ef7cd1144a02be39ac3f8
+size 35122746

run-2/checkpoint-1188/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:865773625f26ecda8e97fa43648969305f39e463edd0c59be1bc7918cd43e824
+size 14054

run-2/checkpoint-1188/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53173d76cd09cf6ecec24b991f35d8b6cf3149896d7bbb2d766f313c45699265
+size 1064

run-2/checkpoint-1188/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-1188/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-2/checkpoint-1188/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.5168316831683168,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-1188",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1188,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7887440323829651,
+      "learning_rate": 0.00015586356006012654,
+      "loss": 0.3246,
+      "step": 594
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5148514851485149,
+      "eval_f1": 0.16382252559726962,
+      "eval_loss": 0.3221835792064667,
+      "eval_precision": 0.5853658536585366,
+      "eval_recall": 0.09523809523809523,
+      "eval_runtime": 15.4228,
+      "eval_samples_per_second": 32.744,
+      "eval_steps_per_second": 1.037,
+      "step": 594
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6338050961494446,
+      "learning_rate": 0.00013854538672011249,
+      "loss": 0.3178,
+      "step": 1188
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_f1": 0.17006802721088435,
+      "eval_loss": 0.31132203340530396,
+      "eval_precision": 0.5952380952380952,
+      "eval_recall": 0.0992063492063492,
+      "eval_runtime": 15.3986,
+      "eval_samples_per_second": 32.795,
+      "eval_steps_per_second": 1.039,
+      "step": 1188
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5940,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1555686566280.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.39860510957002215,
+    "learning_rate": 0.0001731817334001406,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 16,
+    "temperature": 4
+  }
+}

run-2/checkpoint-1188/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8767ee43a8087c968cdc0eed2d700fdcfad08ca8672daf6f805917fe63cbe37
+size 4920

run-2/checkpoint-594/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-2/checkpoint-594/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07ac356b8b2a20268b7ebcf811e6e76fb50d0907cebd76b4b97951d03a7883a2
+size 17549312

run-2/checkpoint-594/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0a000da5dfae4ecc03bdcd0560ad40eca3b2a9776151e2114fb2776bb98c342
+size 35122746

run-2/checkpoint-594/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9593aa7b268a99b44b1c4305fd3c5fb8820f0dfb804b9c95c1c1b40dbaeb2963
+size 14054

run-2/checkpoint-594/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9833b67d53cb68178f11d0e83e382bfc933a82bfeb6c8b386345826d25703649
+size 1064

run-2/checkpoint-594/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-594/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-2/checkpoint-594/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.5148514851485149,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-594",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 594,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.7887440323829651,
+      "learning_rate": 0.00015586356006012654,
+      "loss": 0.3246,
+      "step": 594
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5148514851485149,
+      "eval_f1": 0.16382252559726962,
+      "eval_loss": 0.3221835792064667,
+      "eval_precision": 0.5853658536585366,
+      "eval_recall": 0.09523809523809523,
+      "eval_runtime": 15.4228,
+      "eval_samples_per_second": 32.744,
+      "eval_steps_per_second": 1.037,
+      "step": 594
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5940,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 777843283140.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.39860510957002215,
+    "learning_rate": 0.0001731817334001406,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 16,
+    "temperature": 4
+  }
+}

run-2/checkpoint-594/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8767ee43a8087c968cdc0eed2d700fdcfad08ca8672daf6f805917fe63cbe37
+size 4920

tokenizer.json

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d331d6ed8525f4be242c97947207e536b712d3292c8dd8422ceaeeaa5722a2ab
+oid sha256:e8767ee43a8087c968cdc0eed2d700fdcfad08ca8672daf6f805917fe63cbe37
 size 4920