Training in progress, epoch 2

logs/events.out.tfevents.1700287858.bdba95a6283e.570.10

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d8f4966d07dad50e0b993d1e4de6d7a4502ffe6605f2332719e7d5e8621136c
-size 4809
+oid sha256:4ca5aa95eb84ef9a751612f1abe24a875cddef154006bf8c892a536799edb81e
+size 5643

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:101fab7ec669fd9fb846b889cbb21299658f149354e9eae68052411cfa0e95d9
+oid sha256:f3e8037b47fb45d5785b27cd0255cddaad8adee9ec60e1a9108724c038f1ba71
 size 17549312

run-7/checkpoint-1054/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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-7/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e8037b47fb45d5785b27cd0255cddaad8adee9ec60e1a9108724c038f1ba71
+size 17549312

run-7/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fd83e271103ed107aa4b9adca62257bd05ce07b6245542f232a35ea4989f40a
+size 35123898

run-7/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257145d19710cbf39344544002ce35377faa97e289b8c6f1104c9033e98d4161
+size 14308

run-7/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:394efc951ca7da3fca85efdb63a1175e846c0a25b999e7cc85838728a26f2484
+size 1064

run-7/checkpoint-1054/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-1054/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-1054/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8245412844036697,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-7/checkpoint-527",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1054,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0002311708626753604,
+      "loss": 0.7695,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 0.8910682201385498,
+      "eval_runtime": 2.688,
+      "eval_samples_per_second": 324.402,
+      "eval_steps_per_second": 2.604,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0,
+      "loss": 0.3593,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 1.0504357814788818,
+      "eval_runtime": 2.7537,
+      "eval_samples_per_second": 316.669,
+      "eval_steps_per_second": 2.542,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1054,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 16194449161860.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7241762523239178,
+    "learning_rate": 0.0004623417253507208,
+    "num_train_epochs": 2,
+    "temperature": 25
+  }
+}

run-7/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91355f49061dada60414203196dc17a78e09c3b3e01aea9391457ad8a40d58e9
+size 4664