Training in progress, epoch 3

logs/events.out.tfevents.1699953931.45c71320b2c6.349.26

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79667a66e60cf1004d1eb8f451dffdd00a7bef973652cc947c1fde8b71d9d5e2
-size 5253
+oid sha256:0f79896d6010ce79ce49836693254d2110e9374e90bc27ea02f3f5f0d383f83a
+size 5733

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47c4f5f59c8abf7e0ce90ae572cb038cf7a1bc060604885ca41997a428b05de7
+oid sha256:0d7edea989e47b744311bd2a9f63558806737b6798ce25ae0fa9eb3038360df4
 size 17549312

run-25/checkpoint-1581/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-25/checkpoint-1581/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d7edea989e47b744311bd2a9f63558806737b6798ce25ae0fa9eb3038360df4
+size 17549312

run-25/checkpoint-1581/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f337cfb9a266905da94a381cc95c0e716db64f1a0e02f2003416963b7fbd51c6
+size 35123898

run-25/checkpoint-1581/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0145a794c4550fd779295bb332661a545e0c28f08ca5060bf05d2337c4c7b4d2
+size 14308

run-25/checkpoint-1581/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b7407d62025c767bc812e5660df11ff89c9979553b3f5808e56834914352396
+size 1064

run-25/checkpoint-1581/special_tokens_map.json

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

run-25/checkpoint-1581/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-25/checkpoint-1581/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.8268348623853211,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-25/checkpoint-1054",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1581,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00030840574817073114,
+      "loss": 0.7856,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 0.905726432800293,
+      "eval_runtime": 0.8561,
+      "eval_samples_per_second": 1018.603,
+      "eval_steps_per_second": 8.177,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002313043111280483,
+      "loss": 0.3819,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 1.0662744045257568,
+      "eval_runtime": 0.9245,
+      "eval_samples_per_second": 943.203,
+      "eval_steps_per_second": 7.572,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00015420287408536557,
+      "loss": 0.2635,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 1.2598687410354614,
+      "eval_runtime": 0.8478,
+      "eval_samples_per_second": 1028.489,
+      "eval_steps_per_second": 8.256,
+      "step": 1581
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 24280106603460.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7300210545838287,
+    "learning_rate": 0.0003855071852134139,
+    "num_train_epochs": 5,
+    "temperature": 27
+  }
+}

run-25/checkpoint-1581/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c120fe0a7190dccfe34d9b787af846ba411afe9a129ad0196a03fad1b953f49d
+size 4664