Training in progress, epoch 1

logs/events.out.tfevents.1700284300.bdba95a6283e.570.6

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74461ffff0bafda97b49bb6f62ea3ffa629c742dca66dfcdae16afed1f796a99
-size 5289
+oid sha256:fdf1047747c153b76aeb32dea9d402477c9eddce3cc638a6596e145e62232478
+size 7083

logs/events.out.tfevents.1700285285.bdba95a6283e.570.7

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5d31a16baff08f5dd59ea33391489ef84275615930962fb5fd29f836519590b
+size 4809

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c278a628352fb8bf5850dde4f4b4d6cdb6dc073b5418cf5b21ca7cc9dfca83c
+oid sha256:bec741eb50ca966021fc5eb858b611d56bfab0d2542f2e7b6771c1c2678f2b30
 size 17549312

run-3/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": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-3/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6a4ac60d81bb5d18289635a6ebd44f28394dd8729a99b81aa6c1cea981ee38c
+size 17549312

run-3/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dc6b8a0dbdea1e4b3984ef802feac4c4f810c105991bcfcb7a4a41df63fe098
+size 35123898

run-3/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f498ecc7f86f66da16efa58519f2ba6628266b779089c9aa7803bfb118cc80d
+size 14308

run-3/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a22bd0520e335ace48e4678949a0539204ab15a7fcf7347659405cf32876838d
+size 1064

run-3/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-3/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-3/checkpoint-2635/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 0.8176605504587156,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-3/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": 0.00041526386683348685,
+      "loss": 0.4613,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.805045871559633,
+      "eval_loss": 0.6051546335220337,
+      "eval_runtime": 2.7198,
+      "eval_samples_per_second": 320.613,
+      "eval_steps_per_second": 2.574,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00031144790012511514,
+      "loss": 0.2397,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 0.7534372806549072,
+      "eval_runtime": 2.6979,
+      "eval_samples_per_second": 323.215,
+      "eval_steps_per_second": 2.595,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.00020763193341674343,
+      "loss": 0.1642,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8084862385321101,
+      "eval_loss": 0.8909904360771179,
+      "eval_runtime": 2.7271,
+      "eval_samples_per_second": 319.755,
+      "eval_steps_per_second": 2.567,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.00010381596670837171,
+      "loss": 0.1212,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7993119266055045,
+      "eval_loss": 0.8523622751235962,
+      "eval_runtime": 2.6921,
+      "eval_samples_per_second": 323.909,
+      "eval_steps_per_second": 2.6,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.096,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8004587155963303,
+      "eval_loss": 0.9526763558387756,
+      "eval_runtime": 2.6932,
+      "eval_samples_per_second": 323.783,
+      "eval_steps_per_second": 2.599,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 40418309418180.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9238940809632088,
+    "learning_rate": 0.0005190798335418586,
+    "num_train_epochs": 5,
+    "temperature": 22
+  }
+}

run-3/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7347a6a4d2a64a7d635c666aa8a0b2a3bdfe634a3e64aa55460c04f9d49a1f45
+size 4664

run-4/checkpoint-527/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-4/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec741eb50ca966021fc5eb858b611d56bfab0d2542f2e7b6771c1c2678f2b30
+size 17549312

run-4/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f272c40ca9a596ef85b742cbc7dd2b64b84f6f9f3b2a1225d9ed6d1951804f96
+size 35123898

run-4/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df95bce5c5c16e60e49eb22753b34dbfa7966d22f239bd4ae61a5f9a0e6ccf0d
+size 14308

run-4/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78c60eddb49dae5d29de17871120ad123d503bdea0c8e6c55c6a06bd0e924316
+size 1064

run-4/checkpoint-527/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-527/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-527/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.8245412844036697,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-4/checkpoint-527",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 527,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00026263729264372335,
+      "loss": 0.3473,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 0.4497273862361908,
+      "eval_runtime": 2.7322,
+      "eval_samples_per_second": 319.158,
+      "eval_steps_per_second": 2.562,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1054,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 8117476690260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9886564369229293,
+    "learning_rate": 0.0005252745852874467,
+    "num_train_epochs": 2,
+    "temperature": 23
+  }
+}

run-4/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:104618e22d255edd417a8506be527da66f3b1071557d7321cb32843026f9257f
+size 4664

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7347a6a4d2a64a7d635c666aa8a0b2a3bdfe634a3e64aa55460c04f9d49a1f45
+oid sha256:104618e22d255edd417a8506be527da66f3b1071557d7321cb32843026f9257f
 size 4664