Training in progress, epoch 1

logs/events.out.tfevents.1709736069.fcc57e6e3903.3035.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7426c941e8a186a93e50e210cdf9c49d765cbb0f81aa8c86b41ea40ee4aabf5
-size 5328
+oid sha256:a5eb0180a84267d1681c2c0b3fd39f12e7984a57f0547fbbe65ff859e22bd22f
+size 6365

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd4da0c5da4dba90be080e5a363696a0d7bbab9a803948305b44a9c6c748398a
+size 5327

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42648e0ba416391c7c51fc45db51a7aca0587a9e68c21ffb4f6987142a289063
+oid sha256:7792eeef88f2b040b67cfb87d16e308ac052158fc8773d47734046de06043a16
 size 17549312

run-0/checkpoint-560/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-0/checkpoint-560/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ee62e91c847faa0c99862956030fae2abb2b64e92ab735b255f842a5e559cd
+size 17549312

run-0/checkpoint-560/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be6dd70e5f0244855b79852c433db1682276835cbcc7a76d374e035b71ab44c
+size 35122746

run-0/checkpoint-560/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:460c01aa40267dca3bc567cf05b96a8a7b05346ffcb2e144c23ae574073a1638
+size 14054

run-0/checkpoint-560/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0adf33cb2d73575cdbd5d12f54ea08fda2926dad6237bd0f47f382e68d5ed029
+size 1064

run-0/checkpoint-560/special_tokens_map.json

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

run-0/checkpoint-560/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-0/checkpoint-560/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.5524752475247525,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-560",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 560,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.8820645213127136,
+      "learning_rate": 2.4523034980957572e-05,
+      "loss": 0.5259,
+      "step": 280
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.502970297029703,
+      "eval_f1": 0.07380073800738007,
+      "eval_loss": 0.5183532238006592,
+      "eval_precision": 0.5263157894736842,
+      "eval_recall": 0.03968253968253968,
+      "eval_runtime": 15.7192,
+      "eval_samples_per_second": 32.126,
+      "eval_steps_per_second": 1.018,
+      "step": 280
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.4514720439910889,
+      "learning_rate": 0.0,
+      "loss": 0.5176,
+      "step": 560
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5524752475247525,
+      "eval_f1": 0.37912087912087916,
+      "eval_loss": 0.5147280693054199,
+      "eval_precision": 0.6160714285714286,
+      "eval_recall": 0.27380952380952384,
+      "eval_runtime": 14.924,
+      "eval_samples_per_second": 33.838,
+      "eval_steps_per_second": 1.072,
+      "step": 560
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1555686566280.0,
+  "train_batch_size": 34,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6982252235036847,
+    "learning_rate": 4.9046069961915145e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 34,
+    "temperature": 6
+  }
+}

run-0/checkpoint-560/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f75fa176d41370f392dd24f34030dd3d49a9759489c62ed5d1982414e237233b
+size 4920

run-1/checkpoint-475/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-475/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7792eeef88f2b040b67cfb87d16e308ac052158fc8773d47734046de06043a16
+size 17549312

run-1/checkpoint-475/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb94e27c99f738b6eb7280bd68e529373a1a99d625455af60f3979962b94e361
+size 35122746

run-1/checkpoint-475/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c613b0b24c7efa3515e74341d356193a7a2dd5af2656f0be26c6d17211678f4a
+size 14054

run-1/checkpoint-475/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6322c64715d65f157d45c687dd9d0e79b4a107c3926183594381f1891f07f2e
+size 1064

run-1/checkpoint-475/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-475/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-475/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.5207920792079208,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-475",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 475,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2850,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 777843283140.0,
+  "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-475/training_args.bin

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

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f75fa176d41370f392dd24f34030dd3d49a9759489c62ed5d1982414e237233b
+oid sha256:6ccea265ae9122da077ff8def664c83c587f85ed26bee202b170a564116cd542
 size 4920