Training in progress, epoch 5

logs/events.out.tfevents.1699912014.b18f42e49ba4.3021.31

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a43e04e1f4cf5621646b30e2cd433535c859c245c4d18e856d44209cf5a6be01
-size 6214
+oid sha256:0eb9c0d1e88d6e21b0521e3fc0663c1952f47da11ebf2729e04d920729f74d24
+size 6694

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb94cbf3b137008e9838d25c1d7753d1bd91c73ce2fcaeaf4875c1a207acafae
+oid sha256:f78940eb96f19f8a480436139f22b359b4fec0c90232d57c76b90ca53f1ae656
 size 17549312

run-30/checkpoint-2635/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-30/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f78940eb96f19f8a480436139f22b359b4fec0c90232d57c76b90ca53f1ae656
+size 17549312

run-30/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd87c222bb2d17babcfa12edcc4af19c3cf06265d7e6e2b26f114cfb69a5fd09
+size 35123898

run-30/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6495712c0480e33150a9e840df89cfbd7359c197e00213528d6031351fe6bf56
+size 14308

run-30/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fe25014022f955a8b1a577c484cae603f982b8f22e4e36cf765f7550dc97c57
+size 1064

run-30/checkpoint-2635/special_tokens_map.json

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

run-30/checkpoint-2635/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-30/checkpoint-2635/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 0.8291284403669725,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-30/checkpoint-1054",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2635,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00012672332329282998,
+      "loss": 1.5289,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 1.3494598865509033,
+      "eval_runtime": 0.837,
+      "eval_samples_per_second": 1041.754,
+      "eval_steps_per_second": 8.363,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00011088666420453937,
+      "loss": 0.7504,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 1.4124162197113037,
+      "eval_runtime": 0.8502,
+      "eval_samples_per_second": 1025.666,
+      "eval_steps_per_second": 8.234,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 9.505000511624881e-05,
+      "loss": 0.5592,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8222477064220184,
+      "eval_loss": 1.4369428157806396,
+      "eval_runtime": 0.8713,
+      "eval_samples_per_second": 1000.779,
+      "eval_steps_per_second": 8.034,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 7.921334602795821e-05,
+      "loss": 0.459,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 1.444379210472107,
+      "eval_runtime": 0.8371,
+      "eval_samples_per_second": 1041.641,
+      "eval_steps_per_second": 8.362,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 6.337668693966762e-05,
+      "loss": 0.3861,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 1.5430625677108765,
+      "eval_runtime": 0.8752,
+      "eval_samples_per_second": 996.353,
+      "eval_steps_per_second": 7.998,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 40418309418180.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.44199314752934615,
+    "learning_rate": 0.00014252993179461525,
+    "num_train_epochs": 9,
+    "temperature": 19
+  }
+}

run-30/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d67ba77b95e8ae0f8074c50b63c9f0ecd721c6f94b6ab155bf1c6a999bea86e3
+size 4600