Training in progress, epoch 1

logs/events.out.tfevents.1714702553.e992b94a7c88.3982.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d7661869f18a5132d83708030d33c72b952e4c398cc98c54c86b50cc67c545
-size 6212
+oid sha256:6e5fc6bc86dd45e6e33eb4d75f2f489b44928b0442df8adb6e60ecb3a6cb41e9
+size 8756

logs/events.out.tfevents.1714703163.e992b94a7c88.3982.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:622d23ecb31c3c9f432588185f5cadec59ab635d2cfe61e4f8be507480470d45
+size 5483

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54cae4a356dd6935c825d2e765958a8c24277dc6f07b541039e7ee4b608de14b
+oid sha256:1ffc21295743b1bbb38ccf041e123e738453cffcc8bb5fd48a7121ac96528248
 size 17549312

run-4/checkpoint-7940/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-7940/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4debdc75e7230ef6e31984fe895a0c3100cd8f8f0ae5df41f726220459f316d3
+size 17549312

run-4/checkpoint-7940/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41741af73fad9b88067fbf971f7f8c36ca77b23b8b9f74d1bd89ef37090ac058
+size 35123898

run-4/checkpoint-7940/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e5cb82ace4bc5550730013f2f55899e553faa8158559784776b5e6d30fbc5b
+size 14308

run-4/checkpoint-7940/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caea1de499bd4654b427b13467be32d55985b9b94ee5b76d8b810b4407187baa
+size 1064

run-4/checkpoint-7940/special_tokens_map.json

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

run-4/checkpoint-7940/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-4/checkpoint-7940/trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": 0.6521328506217535,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-1588",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 7940,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.15466690063476562,
+      "learning_rate": 0.00028711293555461854,
+      "loss": 0.047,
+      "step": 1588
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6521328506217535,
+      "eval_f1": 0.006741573033707866,
+      "eval_loss": 0.043082475662231445,
+      "eval_mcc": -0.07334683954324206,
+      "eval_precision": 0.06976744186046512,
+      "eval_recall": 0.0035419126328217238,
+      "eval_runtime": 23.3677,
+      "eval_samples_per_second": 543.742,
+      "eval_steps_per_second": 17.032,
+      "step": 1588
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2909219563007355,
+      "learning_rate": 0.0002153347016659639,
+      "loss": 0.0437,
+      "step": 3176
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6499291673225248,
+      "eval_f1": 0.010676156583629894,
+      "eval_loss": 0.04202444478869438,
+      "eval_mcc": -0.07414646393220078,
+      "eval_precision": 0.09195402298850575,
+      "eval_recall": 0.005667060212514758,
+      "eval_runtime": 23.3008,
+      "eval_samples_per_second": 545.304,
+      "eval_steps_per_second": 17.081,
+      "step": 3176
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.4530297815799713,
+      "learning_rate": 0.00014355646777730927,
+      "loss": 0.0429,
+      "step": 4764
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6510310089721392,
+      "eval_f1": 0.007165248544558891,
+      "eval_loss": 0.04164046049118042,
+      "eval_mcc": -0.07622110191236336,
+      "eval_precision": 0.06926406926406926,
+      "eval_recall": 0.0037780401416765055,
+      "eval_runtime": 23.5928,
+      "eval_samples_per_second": 538.553,
+      "eval_steps_per_second": 16.87,
+      "step": 4764
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.12990067899227142,
+      "learning_rate": 7.177823388865464e-05,
+      "loss": 0.0424,
+      "step": 6352
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.651188414922084,
+      "eval_f1": 0.006723442402510086,
+      "eval_loss": 0.041306350380182266,
+      "eval_mcc": -0.0764573922901941,
+      "eval_precision": 0.06607929515418502,
+      "eval_recall": 0.0035419126328217238,
+      "eval_runtime": 23.6051,
+      "eval_samples_per_second": 538.273,
+      "eval_steps_per_second": 16.861,
+      "step": 6352
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.14243847131729126,
+      "learning_rate": 0.0,
+      "loss": 0.042,
+      "step": 7940
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6503226821973871,
+      "eval_f1": 0.010247271107150813,
+      "eval_loss": 0.04123334959149361,
+      "eval_mcc": -0.0735498736578602,
+      "eval_precision": 0.09055118110236221,
+      "eval_recall": 0.005430932703659976,
+      "eval_runtime": 23.3153,
+      "eval_samples_per_second": 544.964,
+      "eval_steps_per_second": 17.07,
+      "step": 7940
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 7940,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 19544470381500.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.05479484259344969,
+    "learning_rate": 0.0003588911694432732,
+    "num_train_epochs": 5,
+    "temperature": 13
+  }
+}

run-4/checkpoint-7940/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ab3734b7423107abd637ac862db62e156f9bf16c674909b3c1b4d20c8200e7
+size 4984

run-5/checkpoint-1588/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": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-5/checkpoint-1588/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ffc21295743b1bbb38ccf041e123e738453cffcc8bb5fd48a7121ac96528248
+size 17549312

run-5/checkpoint-1588/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e952448b9e74b7f720744b8a50c1bc72f2f6b0b158ba5370aaadfc253e89083
+size 35123898

run-5/checkpoint-1588/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937f4e47675de5e7170e218630c85dd36f459549fb8994b62c13ea83fc7a261c
+size 14308

run-5/checkpoint-1588/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b897e349c091501a6dd9ef235a93d6ef1dd0dd66fbdb7cf1064cc8d88041fd5
+size 1064

run-5/checkpoint-1588/special_tokens_map.json

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

run-5/checkpoint-1588/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-5/checkpoint-1588/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.6491421375728003,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/checkpoint-1588",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1588,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.13218343257904053,
+      "learning_rate": 0.00015920412041008642,
+      "loss": 0.0241,
+      "step": 1588
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6491421375728003,
+      "eval_f1": 0.01109139307897072,
+      "eval_loss": 0.01951172575354576,
+      "eval_mcc": -0.07598752829291255,
+      "eval_precision": 0.09157509157509157,
+      "eval_recall": 0.0059031877213695395,
+      "eval_runtime": 23.3183,
+      "eval_samples_per_second": 544.893,
+      "eval_steps_per_second": 17.068,
+      "step": 1588
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14292,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 3908894076300.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.020625425582708967,
+    "learning_rate": 0.00017910463546134722,
+    "num_train_epochs": 9,
+    "temperature": 19
+  }
+}

run-5/checkpoint-1588/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27eca5e3e9bbc0403ee1098eac38014906ea12051fd82ed05dbef5c621663d0
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ab3734b7423107abd637ac862db62e156f9bf16c674909b3c1b4d20c8200e7
+oid sha256:c27eca5e3e9bbc0403ee1098eac38014906ea12051fd82ed05dbef5c621663d0
 size 4984