Training in progress, epoch 2

logs/events.out.tfevents.1711279866.73e3a81c01ef.4225.7

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb0f2d521414d7cb178ed11d390fc92911ad31a7bf5170e90ba042d3a9c372dc
-size 5407
+oid sha256:1234833fbb14939f01e79fe87b7f9783c247ad8947df85e104c1ca7e7f16731f
+size 6137

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c902d6131ab3434d84d0e0e7f79ccbc1eb6fb0d0985a440a48036d2e4768c3
+oid sha256:e22ddc56fade1c63313df2876b26f25f9f85cf13e53de32585e381c684787a6f
 size 17549312

run-7/checkpoint-384/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-7/checkpoint-384/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e22ddc56fade1c63313df2876b26f25f9f85cf13e53de32585e381c684787a6f
+size 17549312

run-7/checkpoint-384/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9922e1d44c21628afb34e7c90b46b8907d0c1cd7206b515eb3ccce7fd8799496
+size 35122746

run-7/checkpoint-384/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2558f72cda987826e5e7caf54cc6282fe335ebecbddfed7bb83f0184d1f54cc
+size 14054

run-7/checkpoint-384/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f06855b615c714cfed91a7087e5e259ef20ba34201003dc15b021072c1fb573
+size 1064

run-7/checkpoint-384/special_tokens_map.json

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

run-7/checkpoint-384/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-7/checkpoint-384/trainer_state.json

@@ -0,0 +1,67 @@
+{
+  "best_metric": 0.761252446183953,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-7/checkpoint-384",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 384,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.15159010887146,
+      "learning_rate": 2.5124348703312046e-05,
+      "loss": 0.6503,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6908023483365949,
+      "eval_f1": 0.6623931623931624,
+      "eval_loss": 0.6152858734130859,
+      "eval_mcc": 0.38712657099283027,
+      "eval_precision": 0.7294117647058823,
+      "eval_recall": 0.6066536203522505,
+      "eval_runtime": 66.1991,
+      "eval_samples_per_second": 15.438,
+      "eval_steps_per_second": 0.483,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 6.791621208190918,
+      "learning_rate": 1.884326152748403e-05,
+      "loss": 0.5656,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.761252446183953,
+      "eval_f1": 0.7761467889908258,
+      "eval_loss": 0.5115423202514648,
+      "eval_mcc": 0.5271935842180233,
+      "eval_precision": 0.7305699481865285,
+      "eval_recall": 0.8277886497064579,
+      "eval_runtime": 66.4101,
+      "eval_samples_per_second": 15.389,
+      "eval_steps_per_second": 0.482,
+      "step": 384
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 960,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9315469293191833,
+    "learning_rate": 3.1405435879140055e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "temperature": 39
+  }
+}

run-7/checkpoint-384/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f89760f65037c9d8e099483ddc28ec2c1932369cfd91fa114c15b924cd79d07
+size 4984