Training in progress, epoch 1

logs/events.out.tfevents.1709450841.49ae8f4e8e7b.1647.11

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96a2ca27ff8d6c43d8d72f85c42295e380007abce7133865596e9bbe8c224024
-size 5180
+oid sha256:b321b8fc2eac9129da59e226d92eae582e7dc4c4b4b64384d6c17f629327c04d
+size 6068

logs/events.out.tfevents.1709451254.49ae8f4e8e7b.1647.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed01508493ce26139221707a4f2174eef34a2b2104ffa46872da1f34c351e73f
+size 5180

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d5bad654032c3f7546dc4c95b7a06cc9a624f3cdab5078481ab0e1f215bc6d
+oid sha256:27c1f29c7f2b45e0ba2e3aadb7f1badec1deb0295c804b916459266fbd4ecb44
 size 17549312

run-10/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-10/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6bb122613b32de2b5ce453d27d4bf26df0d40f7e4ce450b328504e84efe7da
+size 17549312

run-10/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03a978264f3533379950c9617a50926cc4cea289b227d9d20cddb0cc11be04a0
+size 35123898

run-10/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b242219066ee20691234b53c3eb9b8da10cd3bc00e333f52e39e5b4d6628c98
+size 14308

run-10/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc37a554b9d4226892ded544e6d6f46f797f578296bb70064b379dd5a0b2b146
+size 1064

run-10/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-10/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-10/checkpoint-1054/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.8256880733944955,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-10/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,
+      "grad_norm": 14.234737396240234,
+      "learning_rate": 7.828321466767788e-05,
+      "loss": 1.9973,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8165137614678899,
+      "eval_loss": 1.6924320459365845,
+      "eval_runtime": 2.8153,
+      "eval_samples_per_second": 309.737,
+      "eval_steps_per_second": 2.486,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 18.908693313598633,
+      "learning_rate": 1.482636641433293e-07,
+      "loss": 1.0258,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 1.6462146043777466,
+      "eval_runtime": 2.8215,
+      "eval_samples_per_second": 309.061,
+      "eval_steps_per_second": 2.481,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1054,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 16141525436100.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.015302977727103428,
+    "learning_rate": 0.00015626990200706908,
+    "num_train_epochs": 2,
+    "temperature": 5
+  }
+}

run-10/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c813937f5361535904236d6226bb7c636462c8c71d2d084fc9c0254deb40861a
+size 4984

run-11/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c1f29c7f2b45e0ba2e3aadb7f1badec1deb0295c804b916459266fbd4ecb44
+size 17549312

run-11/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fee684e21f936ebe0b6d688887badffcbf1bd851564fbd0335f8dbbf436e66a
+size 35123898

run-11/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a32291cb0c1329fbb9596dcc47c5d9b0d1f71ecc09dad1791e0b193314659e4
+size 14308

run-11/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e867f8112f6eae6411f9f883c9355ad36ae5a9695b53866966c27aaac4fcff
+size 1064

run-11/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-11/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-11/checkpoint-527/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.8256880733944955,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/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,
+      "grad_norm": 6.5331573486328125,
+      "learning_rate": 0.00014562243502675204,
+      "loss": 0.547,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 0.5717546343803406,
+      "eval_runtime": 2.8071,
+      "eval_samples_per_second": 310.639,
+      "eval_steps_per_second": 2.494,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9318516048675823,
+    "learning_rate": 0.00016642564003057375,
+    "num_train_epochs": 8,
+    "temperature": 23
+  }
+}

run-11/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ab451f50de4ed3d9e5dd09fa9222aca4567e2ff71c45b746c8f3a6f98f8b58
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c813937f5361535904236d6226bb7c636462c8c71d2d084fc9c0254deb40861a
+oid sha256:02ab451f50de4ed3d9e5dd09fa9222aca4567e2ff71c45b746c8f3a6f98f8b58
 size 4984