Training in progress, epoch 1

logs/events.out.tfevents.1709745191.fcc57e6e3903.3035.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af552fa481136343d3774beac1fd30a0093d67155d8bc8f0d95e720e66120b56
-size 5327
+oid sha256:1020effd00d5f6642bc927254a617fcdab478bdeed7cc0d80804e7ea8f74e883
+size 6364

logs/events.out.tfevents.1709745782.fcc57e6e3903.3035.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ab33152ed8c69711a43e6af58760a58a0f863521355679184782a2570d95c1
+size 5328

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8126c5e9d8f528419f3cf2c096893bd141890d3d774bcaab6d2d9778da55e758
+oid sha256:88897c69a27883e0e75cc0e981dd7f8ceb2bfb9768219bab1aeea0c1961aeb72
 size 17549312

run-4/checkpoint-544/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-4/checkpoint-544/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdbf4edf38d9f02b0e520a4aaffe6cbdc3ac35cc7f1970148772874eb02ca6dc
+size 17549312

run-4/checkpoint-544/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a929c56cf2ef3c437b0dd58e6f12f354e9c37b5859dccd19898657c1903487cf
+size 35122746

run-4/checkpoint-544/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b73a4854e890e3ebbccf8c4e0f55dab278b3f08531bd8a4767f6f2eea3a6b694
+size 14054

run-4/checkpoint-544/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b9c8d6e001db0001a1f98bdc28133750187c1ae1b986cad74907d6722849c5
+size 1064

run-4/checkpoint-544/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-544/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-544/trainer_state.json

@@ -0,0 +1,65 @@
+{
+  "best_metric": 0.5148514851485149,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-272",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 544,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.47601568698883057,
+      "learning_rate": 0.0001813549979293713,
+      "loss": 0.2628,
+      "step": 272
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5148514851485149,
+      "eval_f1": 0.16382252559726962,
+      "eval_loss": 0.2552995979785919,
+      "eval_precision": 0.5853658536585366,
+      "eval_recall": 0.09523809523809523,
+      "eval_runtime": 15.0762,
+      "eval_samples_per_second": 33.496,
+      "eval_steps_per_second": 1.061,
+      "step": 272
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5183939337730408,
+      "learning_rate": 0.0,
+      "loss": 0.2543,
+      "step": 544
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5148514851485149,
+      "eval_f1": 0.14634146341463414,
+      "eval_loss": 0.25203588604927063,
+      "eval_precision": 0.6,
+      "eval_recall": 0.08333333333333333,
+      "eval_runtime": 15.0271,
+      "eval_samples_per_second": 33.606,
+      "eval_steps_per_second": 1.065,
+      "step": 544
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 544,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 1555686566280.0,
+  "train_batch_size": 35,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.31055615469788644,
+    "learning_rate": 0.0003627099958587426,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 35,
+    "temperature": 4
+  }
+}

run-4/checkpoint-544/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405af738f99e59daf4704c52ea47cf54f43ffbbec4109525f674b98c77917035
+size 4920

run-5/checkpoint-198/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-5/checkpoint-198/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88897c69a27883e0e75cc0e981dd7f8ceb2bfb9768219bab1aeea0c1961aeb72
+size 17549312

run-5/checkpoint-198/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77307dc841982588882b928f47fd7da06a179343686187a15b408b290d4b9766
+size 35122746

run-5/checkpoint-198/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c052656684e3002a12f3d856dee1ef9ae62f4c6d8e6038e524b5201448043c4b
+size 14054

run-5/checkpoint-198/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26340f5e855540e8942a23d4d39c95dfbe47a0ea7ec105330f558ebb6be53fa3
+size 1064

run-5/checkpoint-198/special_tokens_map.json

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

run-5/checkpoint-198/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-5/checkpoint-198/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.5108910891089109,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-5/checkpoint-198",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 198,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.14785648882389069,
+      "learning_rate": 0.0003571920745148284,
+      "loss": 0.0528,
+      "step": 198
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5108910891089109,
+      "eval_f1": 0.13333333333333333,
+      "eval_loss": 0.04301260784268379,
+      "eval_precision": 0.5757575757575758,
+      "eval_recall": 0.07539682539682539,
+      "eval_runtime": 15.1939,
+      "eval_samples_per_second": 33.237,
+      "eval_steps_per_second": 1.053,
+      "step": 198
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1980,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 777843283140.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.04173399039600034,
+    "learning_rate": 0.0003968800827942538,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 48,
+    "temperature": 11
+  }
+}

run-5/checkpoint-198/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d01e2bf0e73fdbed582c60f36735fc786a4b6ef0e80eba37e34c67dae9d5508
+size 4920

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 31,
+    "max_length": 33,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fc0c138c932c086ad949bc38e18b3ac6fe3a128253e2b1f521aa8c2d349d81b
+oid sha256:3d01e2bf0e73fdbed582c60f36735fc786a4b6ef0e80eba37e34c67dae9d5508
 size 4920