Training in progress, epoch 4

logs/events.out.tfevents.1713589257.1376c752d37a.9760.28

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:497d729fd45a39ec44b635c7183fd676282fa7b4970d33f08d0c06ac5a3a9eb9
-size 6942
+oid sha256:3a57d150a03a0872a073e3fcb5e2731ef686084ac337d5e260a5fd771a0ca5de
+size 7672

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ca595cc670ef51e0d815caf64f58511399a614473526a0c9e07f4c06b673734
+oid sha256:8a7ae44849da575c981fe5610535725205cb65a2797025b3f15e830a86b4ad6e
 size 17549312

run-28/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-28/checkpoint-856/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a7ae44849da575c981fe5610535725205cb65a2797025b3f15e830a86b4ad6e
+size 17549312

run-28/checkpoint-856/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659bc0134a561c5be27d4ed4c23abdf9de4fafc718a6a1092bc6625f9e376d3f
+size 35123898

run-28/checkpoint-856/rng_state.pth

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

run-28/checkpoint-856/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:135eb12cc2b4a58a2a7e8cc32d4f68a872ccbf0b3390ba1a6468aa2f85a182ea
+size 1064

run-28/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-28/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-28/checkpoint-856/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.7428236672524897,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-28/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": 5.574616432189941,
+      "learning_rate": 0.00036655879725586745,
+      "loss": 0.5539,
+      "step": 214
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7287639132981839,
+      "eval_f1": 0.43742405832320774,
+      "eval_loss": 0.5075973272323608,
+      "eval_mcc": 0.3328904757496092,
+      "eval_precision": 0.7086614173228346,
+      "eval_recall": 0.3163444639718805,
+      "eval_runtime": 3.1198,
+      "eval_samples_per_second": 547.147,
+      "eval_steps_per_second": 17.309,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 2.6217339038848877,
+      "learning_rate": 0.00031419325479074356,
+      "loss": 0.498,
+      "step": 428
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7428236672524897,
+      "eval_f1": 0.5364308342133052,
+      "eval_loss": 0.4864349961280823,
+      "eval_mcc": 0.38309619293082,
+      "eval_precision": 0.671957671957672,
+      "eval_recall": 0.44639718804920914,
+      "eval_runtime": 3.1068,
+      "eval_samples_per_second": 549.439,
+      "eval_steps_per_second": 17.381,
+      "step": 428
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.2401552200317383,
+      "learning_rate": 0.0002618277123256196,
+      "loss": 0.4809,
+      "step": 642
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7275922671353251,
+      "eval_f1": 0.3638850889192886,
+      "eval_loss": 0.49476319551467896,
+      "eval_mcc": 0.33497438544889974,
+      "eval_precision": 0.8209876543209876,
+      "eval_recall": 0.23374340949033393,
+      "eval_runtime": 3.1348,
+      "eval_samples_per_second": 544.536,
+      "eval_steps_per_second": 17.226,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.4504497051239014,
+      "learning_rate": 0.0002094621698604957,
+      "loss": 0.4708,
+      "step": 856
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7322788517867604,
+      "eval_f1": 0.4041720990873533,
+      "eval_loss": 0.4818381667137146,
+      "eval_mcc": 0.34539738763177463,
+      "eval_precision": 0.7828282828282829,
+      "eval_recall": 0.27240773286467485,
+      "eval_runtime": 3.1686,
+      "eval_samples_per_second": 538.731,
+      "eval_steps_per_second": 17.042,
+      "step": 856
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1712,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 2099102657760.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9057585906996103,
+    "learning_rate": 0.0004189243397209914,
+    "num_train_epochs": 8,
+    "temperature": 28
+  }
+}

run-28/checkpoint-856/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:958d2eb44240d1dcf28e632e2052856986195085c97b366e1fc6588f903c1326
+size 5048