Training in progress, epoch 1

logs/events.out.tfevents.1699908581.b18f42e49ba4.3021.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01fb47627551744b98d8404b1cb58d9034767a9ead06b7c694b5ddfd32a8be33
-size 5254
+oid sha256:4257761ddf7ea1738bd988ed95d73a1db98e36cb329ee4dc72b5a9da53133414
+size 7654

logs/events.out.tfevents.1699909051.b18f42e49ba4.3021.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42fccdc180a9cc6f0bb2e83ce3e465fa9d45377ecd0bb4246df2d394017bfbf
+size 4774

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb73b9e6782a4091a7f3dd066b5e81789695727a6aa16c4a0fd209d4e3fe39bf
+oid sha256:adad808ce1729e5a7caf4ef257e78eb771c1349afdfb566b8b8fc097264bb745
 size 17549312

run-13/checkpoint-3162/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-13/checkpoint-3162/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70ee32c698bde9faed4952cca7ffc902356c8c01a2a1d5654acddf8abad07e2d
+size 17549312

run-13/checkpoint-3162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c78857e5f37ed31697fe181c1054983b3a0ef569eccd6017a6162484a4abbc
+size 35123898

run-13/checkpoint-3162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4a805f5b31aed4614530263d37ef452339ef59079ff627a6dd75bd82ccc8197
+size 14308

run-13/checkpoint-3162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c854c9a59ed0122581357a17cd26cf579b734d1c608962b46be26a6781ff386
+size 1064

run-13/checkpoint-3162/special_tokens_map.json

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

run-13/checkpoint-3162/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-13/checkpoint-3162/trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": 0.8291284403669725,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-13/checkpoint-1054",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 3162,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001229918736660078,
+      "loss": 1.6529,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8096330275229358,
+      "eval_loss": 1.4444859027862549,
+      "eval_runtime": 0.8333,
+      "eval_samples_per_second": 1046.416,
+      "eval_steps_per_second": 8.4,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00010249970881555375,
+      "loss": 0.8071,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8291284403669725,
+      "eval_loss": 1.4974411725997925,
+      "eval_runtime": 0.8304,
+      "eval_samples_per_second": 1050.135,
+      "eval_steps_per_second": 8.43,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 8.200754396509972e-05,
+      "loss": 0.6025,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 1.5275564193725586,
+      "eval_runtime": 0.838,
+      "eval_samples_per_second": 1040.545,
+      "eval_steps_per_second": 8.353,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.151537911464568e-05,
+      "loss": 0.4998,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 1.5258437395095825,
+      "eval_runtime": 0.8347,
+      "eval_samples_per_second": 1044.633,
+      "eval_steps_per_second": 8.386,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.102321426419165e-05,
+      "loss": 0.4261,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 1.6046433448791504,
+      "eval_runtime": 0.8407,
+      "eval_samples_per_second": 1037.208,
+      "eval_steps_per_second": 8.326,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2.0531049413737625e-05,
+      "loss": 0.3866,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 1.5880481004714966,
+      "eval_runtime": 0.8358,
+      "eval_samples_per_second": 1043.321,
+      "eval_steps_per_second": 8.375,
+      "step": 3162
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3689,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 48509902416420.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.37689567573511473,
+    "learning_rate": 0.00014344515395317822,
+    "num_train_epochs": 7,
+    "temperature": 21
+  }
+}

run-13/checkpoint-3162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e49f40aff2ec7cb96f539cb403f7d52e030045e5f77b8ed81730e241b115f997
+size 4600

run-14/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": "4.35.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-14/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adad808ce1729e5a7caf4ef257e78eb771c1349afdfb566b8b8fc097264bb745
+size 17549312

run-14/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780c1186379a3e28d9b3dbcd87af2f2b3935a216f1c8a6b9029caaf80064d47c
+size 35123898

run-14/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ababcbf30496eb4976cce44a5faf0cf605467f452ba655745eb60d884a0042d8
+size 14308

run-14/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f2a2627149414d0f3f18369bfbbbeb62b8c07e07792df825e45db2c5b8ce1b
+size 1064

run-14/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-14/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-14/checkpoint-527/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 0.8107798165137615,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-14/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": 0.00010317356130055849,
+      "loss": 2.0283,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8107798165137615,
+      "eval_loss": 1.6509921550750732,
+      "eval_runtime": 0.8261,
+      "eval_samples_per_second": 1055.546,
+      "eval_steps_per_second": 8.473,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 8117476690260.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.14932769169050555,
+    "learning_rate": 0.00011604273209593286,
+    "num_train_epochs": 9,
+    "temperature": 7
+  }
+}

run-14/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a549b24996639a9d6d22a725e933f19e20d6ce242486e15b2b9ab359427b8d2f
+size 4600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e49f40aff2ec7cb96f539cb403f7d52e030045e5f77b8ed81730e241b115f997
+oid sha256:a549b24996639a9d6d22a725e933f19e20d6ce242486e15b2b9ab359427b8d2f
 size 4600