Training in progress, epoch 4

logs/events.out.tfevents.1713588697.1376c752d37a.9760.20

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f2c7401a033256c69bcf37ea17db952d321d115604fd624217e534e3009c492
-size 6941
+oid sha256:c4e47e513a9d81f6b0d23c7edf4f9685eb34f208ef2f70cb9ced83851cfb8637
+size 7671

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dedc8eacffd14c78d5fb22a6124c46386440b4e8edec8dceebe1174d9855a5b1
+oid sha256:562c39c44511a9db2f4e5acbf2400b615ac9791e36d347205f292ffe7eb19c08
 size 17549312

run-20/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-20/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562c39c44511a9db2f4e5acbf2400b615ac9791e36d347205f292ffe7eb19c08
+size 17549312

run-20/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a585d1a1a30e19f47d6ea5614b6ccfbf616330329644b7a131981ef03ba9e42e
+size 35123898

run-20/checkpoint-856/rng_state.pth

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

run-20/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d481f1554c61e594fbc8432bea391ebb3de52e8d3912e6f05e10d2f0cc1c972f
+size 1064

run-20/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-20/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-20/checkpoint-856/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.7346221441124781,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-20/checkpoint-428",
+  "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": 3.5011236667633057,
+      "learning_rate": 0.00029874954647137283,
+      "loss": 0.4553,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6848271821909784,
+      "eval_f1": 0.1567398119122257,
+      "eval_loss": 0.4299508333206177,
+      "eval_mcc": 0.17036819686661997,
+      "eval_precision": 0.7246376811594203,
+      "eval_recall": 0.08787346221441125,
+      "eval_runtime": 3.1578,
+      "eval_samples_per_second": 540.559,
+      "eval_steps_per_second": 17.1,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.671453595161438,
+      "learning_rate": 0.0002489579553928107,
+      "loss": 0.4196,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7346221441124781,
+      "eval_f1": 0.4372670807453416,
+      "eval_loss": 0.4135269522666931,
+      "eval_mcc": 0.3504334189243189,
+      "eval_precision": 0.7457627118644068,
+      "eval_recall": 0.3093145869947276,
+      "eval_runtime": 3.2195,
+      "eval_samples_per_second": 530.204,
+      "eval_steps_per_second": 16.773,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.788920521736145,
+      "learning_rate": 0.00019916636431424855,
+      "loss": 0.411,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7106033977738723,
+      "eval_f1": 0.27988338192419826,
+      "eval_loss": 0.415696382522583,
+      "eval_mcc": 0.2803429374077876,
+      "eval_precision": 0.8205128205128205,
+      "eval_recall": 0.1687170474516696,
+      "eval_runtime": 3.1669,
+      "eval_samples_per_second": 539.016,
+      "eval_steps_per_second": 17.051,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.344914436340332,
+      "learning_rate": 0.00014937477323568641,
+      "loss": 0.4054,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7193907439953134,
+      "eval_f1": 0.37711313394018203,
+      "eval_loss": 0.4086741507053375,
+      "eval_mcc": 0.302678268200975,
+      "eval_precision": 0.725,
+      "eval_recall": 0.2548330404217926,
+      "eval_runtime": 3.1334,
+      "eval_samples_per_second": 544.772,
+      "eval_steps_per_second": 17.234,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 2099102657760.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7240883100721838,
+    "learning_rate": 0.000348541137549935,
+    "num_train_epochs": 7,
+    "temperature": 12
+  }
+}

run-20/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:662fbb84d6147f48949a6a39f3cf513cb104e69e1490a40da8e05519999e4ddb
+size 5048