Training in progress, epoch 1

logs/events.out.tfevents.1709876067.6c1c016b0e3e.7263.11

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01074bc52c140385b20827d95ac99b468463f9584bede1a73c48a20c3a214266
-size 5984
+oid sha256:337d8fb8036dc7ec701bc293b051a45d4e61d26794e0edc41606885d463a5112
+size 9753

logs/events.out.tfevents.1709876902.6c1c016b0e3e.7263.12

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a41ec97beb3eff654e0fb0a09947617ecd5b6e456054eda7cfcb76c4654ee9d
+size 5313

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e11add93b37646b53de44334884f87cfb9c0a7c95ac4d83cc9b3ffce33899bd
+oid sha256:19d515c8af8d6d366746314893b5983a56f378ede8e2dc8c2beaa12c1447769c
 size 17549312

run-11/checkpoint-240/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-240/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aab068cfadb3f24f49b7c40cf1c7b89bae02cd7a1f2b468386ad8f2038b8d2a
+size 17549312

run-11/checkpoint-240/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f3ea1a45e40bfb6bc221d15b46f5ef21d5f6b241dbc669deecd1a4389b587a
+size 35122746

run-11/checkpoint-240/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50026349905772a1dfd9733243744e851b7d10c36da8fae3456eba7e3606c8fb
+size 14054

run-11/checkpoint-240/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86e5bcd07a0ddd5d5ab844d428beed084b5aa82bc53c8aff546d327227991fc9
+size 1064

run-11/checkpoint-240/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-240/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-240/trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": 0.8268101761252447,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-240",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 240,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.152926206588745,
+      "learning_rate": 0.0007816128679887146,
+      "loss": 0.591,
+      "step": 48
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7524461839530333,
+      "eval_f1": 0.7944760357432982,
+      "eval_loss": 0.4880000948905945,
+      "eval_precision": 0.6791666666666667,
+      "eval_recall": 0.9569471624266145,
+      "eval_runtime": 29.551,
+      "eval_samples_per_second": 34.584,
+      "eval_steps_per_second": 0.541,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.895570278167725,
+      "learning_rate": 0.0006513440566572622,
+      "loss": 0.4603,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8199608610567515,
+      "eval_f1": 0.8286778398510243,
+      "eval_loss": 0.4088345766067505,
+      "eval_precision": 0.7904085257548845,
+      "eval_recall": 0.8708414872798435,
+      "eval_runtime": 30.3763,
+      "eval_samples_per_second": 33.645,
+      "eval_steps_per_second": 0.527,
+      "step": 96
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.8208940029144287,
+      "learning_rate": 0.0005210752453258098,
+      "loss": 0.4269,
+      "step": 144
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8140900195694716,
+      "eval_f1": 0.8327464788732395,
+      "eval_loss": 0.45197436213493347,
+      "eval_precision": 0.7568,
+      "eval_recall": 0.9256360078277887,
+      "eval_runtime": 29.5919,
+      "eval_samples_per_second": 34.536,
+      "eval_steps_per_second": 0.541,
+      "step": 144
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.270200729370117,
+      "learning_rate": 0.0003908064339943573,
+      "loss": 0.3888,
+      "step": 192
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8189823874755382,
+      "eval_f1": 0.8262910798122065,
+      "eval_loss": 0.40383195877075195,
+      "eval_precision": 0.7942238267148014,
+      "eval_recall": 0.8610567514677103,
+      "eval_runtime": 30.1222,
+      "eval_samples_per_second": 33.928,
+      "eval_steps_per_second": 0.531,
+      "step": 192
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.684295415878296,
+      "learning_rate": 0.0002605376226629049,
+      "loss": 0.3669,
+      "step": 240
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8268101761252447,
+      "eval_f1": 0.8409703504043126,
+      "eval_loss": 0.41744667291641235,
+      "eval_precision": 0.7774086378737541,
+      "eval_recall": 0.9158512720156555,
+      "eval_runtime": 29.2793,
+      "eval_samples_per_second": 34.905,
+      "eval_steps_per_second": 0.546,
+      "step": 240
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 1178475986400.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9971844266637861,
+    "learning_rate": 0.0009118816793201671,
+    "num_train_epochs": 7,
+    "temperature": 16
+  }
+}

run-11/checkpoint-240/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a283f7ca8fa712756294b7fd6d3247bcb44ee70c9bb9ae961204f34de91039c
+size 4920

run-11/checkpoint-336/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-336/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:781b0e9f5a863ad947ba1ec1f8b5889f1b610ca2b2741b252d380b561e2cd2b5
+size 17549312

run-11/checkpoint-336/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22eb08cc5a9f6e5eb74dea03f4171464c6484411800fc065e81ecc333b384796
+size 35122746

run-11/checkpoint-336/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30720e851cc54860df5aa89a6892389c4264a6061ff42a4eef7ff950f504b083
+size 14054

run-11/checkpoint-336/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f23e7def1958a6a6285404bfb2e20068c880ac6cb699d408b94f4c0fb5ac33
+size 1064

run-11/checkpoint-336/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-336/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-336/trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": 0.8268101761252447,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-11/checkpoint-240",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 336,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.152926206588745,
+      "learning_rate": 0.0007816128679887146,
+      "loss": 0.591,
+      "step": 48
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7524461839530333,
+      "eval_f1": 0.7944760357432982,
+      "eval_loss": 0.4880000948905945,
+      "eval_precision": 0.6791666666666667,
+      "eval_recall": 0.9569471624266145,
+      "eval_runtime": 29.551,
+      "eval_samples_per_second": 34.584,
+      "eval_steps_per_second": 0.541,
+      "step": 48
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.895570278167725,
+      "learning_rate": 0.0006513440566572622,
+      "loss": 0.4603,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8199608610567515,
+      "eval_f1": 0.8286778398510243,
+      "eval_loss": 0.4088345766067505,
+      "eval_precision": 0.7904085257548845,
+      "eval_recall": 0.8708414872798435,
+      "eval_runtime": 30.3763,
+      "eval_samples_per_second": 33.645,
+      "eval_steps_per_second": 0.527,
+      "step": 96
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.8208940029144287,
+      "learning_rate": 0.0005210752453258098,
+      "loss": 0.4269,
+      "step": 144
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8140900195694716,
+      "eval_f1": 0.8327464788732395,
+      "eval_loss": 0.45197436213493347,
+      "eval_precision": 0.7568,
+      "eval_recall": 0.9256360078277887,
+      "eval_runtime": 29.5919,
+      "eval_samples_per_second": 34.536,
+      "eval_steps_per_second": 0.541,
+      "step": 144
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.270200729370117,
+      "learning_rate": 0.0003908064339943573,
+      "loss": 0.3888,
+      "step": 192
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8189823874755382,
+      "eval_f1": 0.8262910798122065,
+      "eval_loss": 0.40383195877075195,
+      "eval_precision": 0.7942238267148014,
+      "eval_recall": 0.8610567514677103,
+      "eval_runtime": 30.1222,
+      "eval_samples_per_second": 33.928,
+      "eval_steps_per_second": 0.531,
+      "step": 192
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.684295415878296,
+      "learning_rate": 0.0002605376226629049,
+      "loss": 0.3669,
+      "step": 240
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8268101761252447,
+      "eval_f1": 0.8409703504043126,
+      "eval_loss": 0.41744667291641235,
+      "eval_precision": 0.7774086378737541,
+      "eval_recall": 0.9158512720156555,
+      "eval_runtime": 29.2793,
+      "eval_samples_per_second": 34.905,
+      "eval_steps_per_second": 0.546,
+      "step": 240
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.6306262016296387,
+      "learning_rate": 0.00013026881133145244,
+      "loss": 0.3718,
+      "step": 288
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8189823874755382,
+      "eval_f1": 0.8378615249780893,
+      "eval_loss": 0.40002480149269104,
+      "eval_precision": 0.7587301587301587,
+      "eval_recall": 0.9354207436399217,
+      "eval_runtime": 29.4445,
+      "eval_samples_per_second": 34.709,
+      "eval_steps_per_second": 0.543,
+      "step": 288
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 2.835477828979492,
+      "learning_rate": 0.0,
+      "loss": 0.348,
+      "step": 336
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8228962818003914,
+      "eval_f1": 0.8344007319304666,
+      "eval_loss": 0.40344515442848206,
+      "eval_precision": 0.7835051546391752,
+      "eval_recall": 0.8923679060665362,
+      "eval_runtime": 29.1711,
+      "eval_samples_per_second": 35.035,
+      "eval_steps_per_second": 0.548,
+      "step": 336
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 1649866380960.0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9971844266637861,
+    "learning_rate": 0.0009118816793201671,
+    "num_train_epochs": 7,
+    "temperature": 16
+  }
+}

run-11/checkpoint-336/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a283f7ca8fa712756294b7fd6d3247bcb44ee70c9bb9ae961204f34de91039c
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a283f7ca8fa712756294b7fd6d3247bcb44ee70c9bb9ae961204f34de91039c
+oid sha256:de3788bfc8a3541ae46e22029a32017f9c59ccb7742b5f55bae39d09e3690a65
 size 4920