Training in progress, epoch 2

logs/events.out.tfevents.1706196200.A-FVFFG2C4Q05P.18450.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b33c54d05ee0e72b3ad04a32dc40448bf1c1c65597a97ff3edeb33a16ee5c9
-size 4915
+oid sha256:00996ac2e26a9ba61d96ffe89b5b8299ebe0f1aae0cd9f3c9859ad31c1005f5e
+size 5395

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb8aa05f92c3e3e3100697f91476432307ef227d91e417e359f633516f53ade
+oid sha256:20c6f535ff7be2c32349e826fe4e9a8cc287c32c8820afae128deea5181c2150
 size 17549312

run-4/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": "4.37.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-4/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20c6f535ff7be2c32349e826fe4e9a8cc287c32c8820afae128deea5181c2150
+size 17549312

run-4/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c42a6d4115678935afbe3322d04346d54ad920b4d8af3469ef4fffc40c25904
+size 35122373

run-4/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260bdbb59b5e150f75450cd4e9defbf6deeda9a4e5690f5284bcc9395a60f0af
+size 13617

run-4/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13fa567cd3084439c813b316cb3b270769df865bd04bc00c706ae02b30a85c60
+size 627

run-4/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-4/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-4/checkpoint-1054/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_metric": 0.8256880733944955,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-1054",
+  "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": 8.185589369281136e-05,
+      "loss": 1.3236,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 1.107783555984497,
+      "eval_runtime": 7.0372,
+      "eval_samples_per_second": 123.913,
+      "eval_steps_per_second": 0.995,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.162390698120995e-05,
+      "loss": 0.686,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 1.0679908990859985,
+      "eval_runtime": 6.9855,
+      "eval_samples_per_second": 124.83,
+      "eval_steps_per_second": 1.002,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 16162868129520.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6484108691726712,
+    "learning_rate": 9.208788040441279e-05,
+    "num_train_epochs": 9,
+    "temperature": 16
+  }
+}

run-4/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a802a6ef5b6f7d1deb28aafada439e905b1de2242376315c4a5c34f1077a137d
+size 4283