Training in progress, epoch 1

logs/events.out.tfevents.1713589743.1376c752d37a.9760.34

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bafebcf56348b29e3bcbc6b2d586d6c04d8fba5dacb044733ff85b6d28efa0c
-size 6942
+oid sha256:380678016fc339f0223f81dfd52233bcc75bb4921aefc8b555c310185ffcb394
+size 8402

logs/events.out.tfevents.1713589826.1376c752d37a.9760.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:756b72028d18b1bfceefb0f06026fe869bd79ebb2760e9a8f9ed73d4e44b6598
+size 5483

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ff2b8ab26cd043a2793efd97ce83ab086254efe8f54208ce8a4b414868070cd
+oid sha256:5dc2d648fc55094124d4764c47413294acab41353e2f467f943e98fcc2ffb79e
 size 17549312

run-34/checkpoint-856/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-34/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a7bfc68ed7792e5fa31a379d8213e1c40eb87d1819dd3a00a7e5135b645744d
+size 17549312

run-34/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb2d840c555bfc8c068e3d72761a57dfcf6bebc398c7472586b96d0ece7dc1c
+size 35123898

run-34/checkpoint-856/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057111bfbb4d541cc190a3ed4fcfe228e7425a50e4a06afd33224d43272b1a59
+size 14308

run-34/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f2b37a635fe1acedfeb98e0a847d694b9e0e57121eae017a15fb77f8b49eef2
+size 1064

run-34/checkpoint-856/special_tokens_map.json

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

run-34/checkpoint-856/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-34/checkpoint-856/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.7463386057410663,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-34/checkpoint-856",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 856,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 4.8471832275390625,
+      "learning_rate": 0.0003084590636066452,
+      "loss": 0.4895,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7041593438781488,
+      "eval_f1": 0.3631778058007566,
+      "eval_loss": 0.4574507474899292,
+      "eval_mcc": 0.25518418317792835,
+      "eval_precision": 0.6428571428571429,
+      "eval_recall": 0.2530755711775044,
+      "eval_runtime": 3.1432,
+      "eval_samples_per_second": 543.077,
+      "eval_steps_per_second": 17.18,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.93764066696167,
+      "learning_rate": 0.0002313442977049839,
+      "loss": 0.4474,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7334504979496193,
+      "eval_f1": 0.4291091593475534,
+      "eval_loss": 0.4426566958427429,
+      "eval_mcc": 0.3470390546850216,
+      "eval_precision": 0.75,
+      "eval_recall": 0.30052724077328646,
+      "eval_runtime": 3.675,
+      "eval_samples_per_second": 464.485,
+      "eval_steps_per_second": 14.694,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.0922608375549316,
+      "learning_rate": 0.0001542295318033226,
+      "loss": 0.4323,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7223198594024605,
+      "eval_f1": 0.35945945945945945,
+      "eval_loss": 0.4437848925590515,
+      "eval_mcc": 0.3145764348029479,
+      "eval_precision": 0.7777777777777778,
+      "eval_recall": 0.23374340949033393,
+      "eval_runtime": 3.1441,
+      "eval_samples_per_second": 542.917,
+      "eval_steps_per_second": 17.175,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.645482301712036,
+      "learning_rate": 7.71147659016613e-05,
+      "loss": 0.4256,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7463386057410663,
+      "eval_f1": 0.5162011173184358,
+      "eval_loss": 0.4317722022533417,
+      "eval_mcc": 0.3867634513662599,
+      "eval_precision": 0.7085889570552147,
+      "eval_recall": 0.40597539543058,
+      "eval_runtime": 3.6592,
+      "eval_samples_per_second": 466.501,
+      "eval_steps_per_second": 14.758,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2099102657760.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7948524745832855,
+    "learning_rate": 0.0003855738295083065,
+    "num_train_epochs": 5,
+    "temperature": 15
+  }
+}

run-34/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:051fab5723c44be17f791f8c45489e1552a330ef8815754068f2bb19eae15a1c
+size 5048

run-35/checkpoint-214/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": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-35/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc2d648fc55094124d4764c47413294acab41353e2f467f943e98fcc2ffb79e
+size 17549312

run-35/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6cd46296dc142e37aff4e03e545dc2b8196b5a2fc5085c387888cdcf17ba0a
+size 35123898

run-35/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7e492e6768bc7c3c01ac823da5a8177cf34fc1b175dd727fa3be969661a151
+size 14308

run-35/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672c71ea4bbf49f25143fa3e956dad5f4066566a6addd1165ca979434e94f0bb
+size 1064

run-35/checkpoint-214/special_tokens_map.json

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

run-35/checkpoint-214/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-35/checkpoint-214/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.7047451669595782,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-35/checkpoint-214",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 9.204007148742676,
+      "learning_rate": 0.00010073134118996591,
+      "loss": 0.5694,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7047451669595782,
+      "eval_f1": 0.514450867052023,
+      "eval_loss": 0.5304614901542664,
+      "eval_mcc": 0.30808910613726637,
+      "eval_precision": 0.5692963752665245,
+      "eval_recall": 0.46924428822495606,
+      "eval_runtime": 3.1372,
+      "eval_samples_per_second": 544.118,
+      "eval_steps_per_second": 17.213,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 524775664440.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9231832458790068,
+    "learning_rate": 0.00011751989805496024,
+    "num_train_epochs": 7,
+    "temperature": 10
+  }
+}

run-35/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900171b85ecd44d34036a14f92291fe4a63ad82facf0081f97b5e4401cf8a786
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051fab5723c44be17f791f8c45489e1552a330ef8815754068f2bb19eae15a1c
+oid sha256:900171b85ecd44d34036a14f92291fe4a63ad82facf0081f97b5e4401cf8a786
 size 5048