Training in progress, epoch 1

logs/events.out.tfevents.1709742338.fcc57e6e3903.3035.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e93aadbbfe3ced2c9914b0a9803b303f44e2911fe4db39dda063742b8c9f4b7e
-size 6011
+oid sha256:72b1c9a1f521f79a8f585b558a431340f9c458910554157126bd7901684ed85f
+size 11829

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af552fa481136343d3774beac1fd30a0093d67155d8bc8f0d95e720e66120b56
+size 5327

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba95c9d532c48ee17ddbdeae9c7adf668a8f0b04d554821706bfe56e3fa01c1
+oid sha256:aab0aa9983b34446d6f95907e618be8a634df8325c3943cdd00f61fce4df3c4b
 size 17549312

run-3/checkpoint-1760/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-3/checkpoint-1760/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3deaec0341a2d2aad2066f07535f34e9ca238e4eea76c268d5891af295a03e84
+size 17549312

run-3/checkpoint-1760/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44b76b9f130fccc6fd4da462011cad89360e2d2ee3c910cceaa6a4a04fe1496b
+size 35122746

run-3/checkpoint-1760/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc1538f8f3100adddc9353f02847e1c9d758136e1fee3d81c0b3db27af00e261
+size 14054

run-3/checkpoint-1760/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2596b53380928e49bab3ca06b7d0cb8ce44cff19413eb5debfcac1bdfb30f4b5
+size 1064

run-3/checkpoint-1760/special_tokens_map.json

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

run-3/checkpoint-1760/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-3/checkpoint-1760/trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_metric": 0.5148514851485149,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-176",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1760,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5431386232376099,
+      "learning_rate": 0.00012088388613301416,
+      "loss": 0.2133,
+      "step": 176
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5148514851485149,
+      "eval_f1": 0.14035087719298245,
+      "eval_loss": 0.20053359866142273,
+      "eval_precision": 0.6060606060606061,
+      "eval_recall": 0.07936507936507936,
+      "eval_runtime": 15.0376,
+      "eval_samples_per_second": 33.582,
+      "eval_steps_per_second": 1.064,
+      "step": 176
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2198910117149353,
+      "learning_rate": 0.00010745234322934593,
+      "loss": 0.2028,
+      "step": 352
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5069306930693069,
+      "eval_f1": 0.1263157894736842,
+      "eval_loss": 0.20091117918491364,
+      "eval_precision": 0.5454545454545454,
+      "eval_recall": 0.07142857142857142,
+      "eval_runtime": 14.9354,
+      "eval_samples_per_second": 33.812,
+      "eval_steps_per_second": 1.071,
+      "step": 352
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5269190669059753,
+      "learning_rate": 9.402080032567768e-05,
+      "loss": 0.2015,
+      "step": 528
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5128712871287129,
+      "eval_f1": 0.15172413793103445,
+      "eval_loss": 0.20115335285663605,
+      "eval_precision": 0.5789473684210527,
+      "eval_recall": 0.0873015873015873,
+      "eval_runtime": 15.3006,
+      "eval_samples_per_second": 33.005,
+      "eval_steps_per_second": 1.046,
+      "step": 528
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6160932183265686,
+      "learning_rate": 8.058925742200945e-05,
+      "loss": 0.2007,
+      "step": 704
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5128712871287129,
+      "eval_f1": 0.15753424657534246,
+      "eval_loss": 0.20070397853851318,
+      "eval_precision": 0.575,
+      "eval_recall": 0.09126984126984126,
+      "eval_runtime": 15.3305,
+      "eval_samples_per_second": 32.941,
+      "eval_steps_per_second": 1.044,
+      "step": 704
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.17378416657447815,
+      "learning_rate": 6.71577145183412e-05,
+      "loss": 0.2004,
+      "step": 880
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5089108910891089,
+      "eval_f1": 0.1267605633802817,
+      "eval_loss": 0.19792087376117706,
+      "eval_precision": 0.5625,
+      "eval_recall": 0.07142857142857142,
+      "eval_runtime": 15.059,
+      "eval_samples_per_second": 33.535,
+      "eval_steps_per_second": 1.062,
+      "step": 880
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.18278618156909943,
+      "learning_rate": 5.3726171614672966e-05,
+      "loss": 0.1992,
+      "step": 1056
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.504950495049505,
+      "eval_f1": 0.13194444444444445,
+      "eval_loss": 0.19790016114711761,
+      "eval_precision": 0.5277777777777778,
+      "eval_recall": 0.07539682539682539,
+      "eval_runtime": 14.8776,
+      "eval_samples_per_second": 33.944,
+      "eval_steps_per_second": 1.075,
+      "step": 1056
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.32294225692749023,
+      "learning_rate": 4.029462871100472e-05,
+      "loss": 0.1985,
+      "step": 1232
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.5108910891089109,
+      "eval_f1": 0.13937282229965156,
+      "eval_loss": 0.19708825647830963,
+      "eval_precision": 0.5714285714285714,
+      "eval_recall": 0.07936507936507936,
+      "eval_runtime": 15.1516,
+      "eval_samples_per_second": 33.33,
+      "eval_steps_per_second": 1.056,
+      "step": 1232
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.24637407064437866,
+      "learning_rate": 2.6863085807336483e-05,
+      "loss": 0.1984,
+      "step": 1408
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.5108910891089109,
+      "eval_f1": 0.13937282229965156,
+      "eval_loss": 0.19653446972370148,
+      "eval_precision": 0.5714285714285714,
+      "eval_recall": 0.07936507936507936,
+      "eval_runtime": 14.8734,
+      "eval_samples_per_second": 33.953,
+      "eval_steps_per_second": 1.076,
+      "step": 1408
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.2087116688489914,
+      "learning_rate": 1.3431542903668242e-05,
+      "loss": 0.198,
+      "step": 1584
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.5108910891089109,
+      "eval_f1": 0.13937282229965156,
+      "eval_loss": 0.19648496806621552,
+      "eval_precision": 0.5714285714285714,
+      "eval_recall": 0.07936507936507936,
+      "eval_runtime": 15.3381,
+      "eval_samples_per_second": 32.925,
+      "eval_steps_per_second": 1.043,
+      "step": 1584
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.36322712898254395,
+      "learning_rate": 0.0,
+      "loss": 0.1975,
+      "step": 1760
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.5108910891089109,
+      "eval_f1": 0.13937282229965156,
+      "eval_loss": 0.19634994864463806,
+      "eval_precision": 0.5714285714285714,
+      "eval_recall": 0.07936507936507936,
+      "eval_runtime": 14.8929,
+      "eval_samples_per_second": 33.909,
+      "eval_steps_per_second": 1.074,
+      "step": 1760
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1760,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 7778432831400.0,
+  "train_batch_size": 54,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.239256796645401,
+    "learning_rate": 0.0001343154290366824,
+    "num_train_epochs": 10,
+    "per_device_train_batch_size": 54,
+    "temperature": 13
+  }
+}

run-3/checkpoint-1760/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e3fa9f35ba1a109d4dbcaa99a0da7b79ffac3932fc22f17787de76b9701cac
+size 4920

run-4/checkpoint-272/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-272/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aab0aa9983b34446d6f95907e618be8a634df8325c3943cdd00f61fce4df3c4b
+size 17549312

run-4/checkpoint-272/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7c6a8013716dcac44bce6feaad0711f556dffee75283b7a789af4c586446f43
+size 35122746

run-4/checkpoint-272/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d74a98f8e02a3a5b3d09204f5a09de3425262ec2e951a99c07e510e5f7960d57
+size 14054

run-4/checkpoint-272/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd9bf91f2de6ad1e68f24af8095d8175824a858d3bdff6cf895137d9acf6ce7
+size 1064

run-4/checkpoint-272/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-272/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-272/trainer_state.json

@@ -0,0 +1,46 @@
+{
+  "best_metric": 0.5148514851485149,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-272",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 272,
+  "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
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 544,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 777843283140.0,
+  "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-272/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405af738f99e59daf4704c52ea47cf54f43ffbbec4109525f674b98c77917035
+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:d326c5fe515888a81989fed6d26dc1aadeb6fd6bd4401805f0cf726489091eb5
+oid sha256:405af738f99e59daf4704c52ea47cf54f43ffbbec4109525f674b98c77917035
 size 4920