Training in progress, epoch 1

logs/events.out.tfevents.1719239773.f94f01b9b918.2392.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a62939f990ec3434b8df72a1725c7ad7fb2c786ba42be6210293621fb01cef2
-size 8632
+oid sha256:9fbf88b7a987e4df47beafc92354d41e0c98e10f565586565950b228d0011c71
+size 9520

logs/events.out.tfevents.1719241205.f94f01b9b918.2392.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b84da5ed8de8ecc290a0d041069d2d9c15ebe11dd6c8ef83483f4c3442d033d9
+size 5428

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83991db9ad957d9888362f3ad8fafd08079dca34ec30e24008afe88a91718605
+oid sha256:f38b9ea491ce667f59ded0ccfbdfe75281aee028ae8d5466c274041caf164206
 size 17549312

run-0/checkpoint-4216/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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-0/checkpoint-4216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7e49bfe6cfd2d96a860484be039fa136e6054d9cecdbb8fbda97a759707d985
+size 17549312

run-0/checkpoint-4216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6325c8e0b4ceb30845b52ec38bc93b7ffd274b42f395494ec024deeb4de7775b
+size 35123898

run-0/checkpoint-4216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa81e5ce517ba9c6e8d8142c37e153e555c7915890f25285a025ef1610b79466
+size 14308

run-0/checkpoint-4216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b973f0b00352a0713dda5aec6e5ca7daebeb18a4763bbd29ea4b99c134e7365
+size 1064

run-0/checkpoint-4216/special_tokens_map.json

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

run-0/checkpoint-4216/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-0/checkpoint-4216/trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_metric": 0.8302752293577982,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-4216",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 4216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 16.55626678466797,
+      "learning_rate": 5.1383294230414005e-05,
+      "loss": 1.5907,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8061926605504587,
+      "eval_loss": 1.2464169263839722,
+      "eval_runtime": 2.4007,
+      "eval_samples_per_second": 363.232,
+      "eval_steps_per_second": 2.916,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": Infinity,
+      "learning_rate": 4.405675241279466e-05,
+      "loss": 0.9038,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 1.1235342025756836,
+      "eval_runtime": 2.3533,
+      "eval_samples_per_second": 370.54,
+      "eval_steps_per_second": 2.975,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 48.55740737915039,
+      "learning_rate": 3.67162818084498e-05,
+      "loss": 0.6946,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8176605504587156,
+      "eval_loss": 1.1027159690856934,
+      "eval_runtime": 2.3719,
+      "eval_samples_per_second": 367.637,
+      "eval_steps_per_second": 2.951,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 16.267213821411133,
+      "learning_rate": 2.9375811204104943e-05,
+      "loss": 0.595,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8256880733944955,
+      "eval_loss": 1.0700539350509644,
+      "eval_runtime": 2.3638,
+      "eval_samples_per_second": 368.893,
+      "eval_steps_per_second": 2.961,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 10.482604026794434,
+      "learning_rate": 2.2035340599760084e-05,
+      "loss": 0.5308,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 1.1128482818603516,
+      "eval_runtime": 2.3733,
+      "eval_samples_per_second": 367.419,
+      "eval_steps_per_second": 2.949,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 24.14480209350586,
+      "learning_rate": 1.4694869995415228e-05,
+      "loss": 0.4895,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 1.1355042457580566,
+      "eval_runtime": 2.3485,
+      "eval_samples_per_second": 371.294,
+      "eval_steps_per_second": 2.981,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 25.623193740844727,
+      "learning_rate": 7.35439939107037e-06,
+      "loss": 0.4606,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 1.1558915376663208,
+      "eval_runtime": 2.3654,
+      "eval_samples_per_second": 368.653,
+      "eval_steps_per_second": 2.959,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 11.750224113464355,
+      "learning_rate": 1.3928786725512063e-08,
+      "loss": 0.449,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8302752293577982,
+      "eval_loss": 1.155808687210083,
+      "eval_runtime": 2.3688,
+      "eval_samples_per_second": 368.125,
+      "eval_steps_per_second": 2.955,
+      "step": 4216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 64687167744780.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5167874928728581,
+    "learning_rate": 5.872376483475886e-05,
+    "num_train_epochs": 8,
+    "temperature": 5
+  }
+}

run-0/checkpoint-4216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f28149fe21091b257234d7cbe1611ee6ca88e3a7cef675e40e6d90410e6fc1a6
+size 5176

run-1/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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f38b9ea491ce667f59ded0ccfbdfe75281aee028ae8d5466c274041caf164206
+size 17549312

run-1/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a52317e8696ae2d8b8beb30e707c3986d402de61f751253103bb2f0082b56a18
+size 35123898

run-1/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9733f27bb728718f7284348156186daf975855376673d9de7e218a8cff476307
+size 14308

run-1/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b6a438bddb76984d6c62348e4db9f39c76bfd074f83c6cc6f740e3e23d57662
+size 1064

run-1/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-1/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-1/checkpoint-527/trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": 0.8153669724770642,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/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": 30.242748260498047,
+      "learning_rate": 0.000111895725910844,
+      "loss": 2.3991,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8153669724770642,
+      "eval_loss": 1.9181628227233887,
+      "eval_runtime": 2.3714,
+      "eval_samples_per_second": 367.708,
+      "eval_steps_per_second": 2.952,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8057768762220.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.051381532356201576,
+    "learning_rate": 0.0001342239322193053,
+    "num_train_epochs": 6,
+    "temperature": 23
+  }
+}

run-1/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6a7f7b16042aa90d6a482b54cde9c8a264f21ae121942f35d43fb01c1ae0eb
+size 5176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f28149fe21091b257234d7cbe1611ee6ca88e3a7cef675e40e6d90410e6fc1a6
+oid sha256:fa6a7f7b16042aa90d6a482b54cde9c8a264f21ae121942f35d43fb01c1ae0eb
 size 5176