Training in progress, epoch 1

logs/events.out.tfevents.1711292011.73e3a81c01ef.4225.21

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e22823a4f12ab032eae8d7b7b2d1dafb781632bd507a244283116662e87af214
-size 6136
+oid sha256:97253eb32258b95522d09240d5c3d8fa5a5835e22f0904984e275717010662ac
+size 8680

logs/events.out.tfevents.1711293435.73e3a81c01ef.4225.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda397d8b1a6bac0929320e9a75322a5b463c6b85ac67a0a36532f33a2660c65
+size 5406

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af5e92537593b52f81e95815e448e183298b9ee21a343c09160eb7403ea94b7e
+oid sha256:1c85e38420810a118a901915c1e6c8002f03a50116750d4ec99cbbe24ae88076
 size 17549312

run-21/checkpoint-576/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-21/checkpoint-576/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9fbab5405319957ea637f03211967d15081d9443fe975f422172ce50c2e71a6
+size 17549312

run-21/checkpoint-576/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8937f91c68535eca8d7654b9e3cbd4e19be27e3d365773400ecd0b1da8d3c81
+size 35122746

run-21/checkpoint-576/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77649db78380b105203c3be0753a0a47e20be3ccd8ec2455a7d4db9d8ae85766
+size 14054

run-21/checkpoint-576/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8790a23883af5890e44c5225fc2a7315444f28c44171fbeb42b9c5564e9b3f24
+size 1064

run-21/checkpoint-576/special_tokens_map.json

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

run-21/checkpoint-576/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-21/checkpoint-576/trainer_state.json

@@ -0,0 +1,87 @@
+{
+  "best_metric": 0.8189823874755382,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-576",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 576,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.036266803741455,
+      "learning_rate": 7.741005485591573e-05,
+      "loss": 0.556,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.786692759295499,
+      "eval_f1": 0.8080985915492958,
+      "eval_loss": 0.4501095712184906,
+      "eval_mcc": 0.5882099387037968,
+      "eval_precision": 0.7344,
+      "eval_recall": 0.898238747553816,
+      "eval_runtime": 67.0331,
+      "eval_samples_per_second": 15.246,
+      "eval_steps_per_second": 0.477,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.937936305999756,
+      "learning_rate": 5.8057541141936786e-05,
+      "loss": 0.4586,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8082191780821918,
+      "eval_f1": 0.8161350844277674,
+      "eval_loss": 0.42737704515457153,
+      "eval_mcc": 0.6187363370477468,
+      "eval_precision": 0.7837837837837838,
+      "eval_recall": 0.8512720156555773,
+      "eval_runtime": 66.4748,
+      "eval_samples_per_second": 15.374,
+      "eval_steps_per_second": 0.481,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.516488075256348,
+      "learning_rate": 3.8705027427957864e-05,
+      "loss": 0.4308,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8189823874755382,
+      "eval_f1": 0.8291782086795938,
+      "eval_loss": 0.4247056245803833,
+      "eval_mcc": 0.6425594703081364,
+      "eval_precision": 0.784965034965035,
+      "eval_recall": 0.8786692759295499,
+      "eval_runtime": 66.8952,
+      "eval_samples_per_second": 15.278,
+      "eval_steps_per_second": 0.478,
+      "step": 576
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 960,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 707085591840.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8653499588119579,
+    "learning_rate": 9.676256856989465e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "temperature": 45
+  }
+}

run-21/checkpoint-576/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b9a69c0a84f1792b2d6d65795033f526e96e3e74b93dead0b939d20001f112
+size 4984

run-21/checkpoint-960/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": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-21/checkpoint-960/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f465b7b68f481ac2839f7e48416acdfc97584a0343349441012db285a8459f8a
+size 17549312

run-21/checkpoint-960/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe504780223ee54b36f65551b899d73618de38ce67ad5f39de8e7e3b69f21d3a
+size 35122746

run-21/checkpoint-960/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0f708bee926375ebbf58f1558008811afac316edcd7c7c1acf7807ef08c4de0
+size 14054

run-21/checkpoint-960/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da6dd0407dbd429cf0b90857ecc16370cf071edfe07f06496c234c435f3df1e
+size 1064

run-21/checkpoint-960/special_tokens_map.json

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

run-21/checkpoint-960/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-21/checkpoint-960/trainer_state.json

@@ -0,0 +1,127 @@
+{
+  "best_metric": 0.8189823874755382,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-21/checkpoint-576",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 960,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 5.036266803741455,
+      "learning_rate": 7.741005485591573e-05,
+      "loss": 0.556,
+      "step": 192
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.786692759295499,
+      "eval_f1": 0.8080985915492958,
+      "eval_loss": 0.4501095712184906,
+      "eval_mcc": 0.5882099387037968,
+      "eval_precision": 0.7344,
+      "eval_recall": 0.898238747553816,
+      "eval_runtime": 67.0331,
+      "eval_samples_per_second": 15.246,
+      "eval_steps_per_second": 0.477,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.937936305999756,
+      "learning_rate": 5.8057541141936786e-05,
+      "loss": 0.4586,
+      "step": 384
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8082191780821918,
+      "eval_f1": 0.8161350844277674,
+      "eval_loss": 0.42737704515457153,
+      "eval_mcc": 0.6187363370477468,
+      "eval_precision": 0.7837837837837838,
+      "eval_recall": 0.8512720156555773,
+      "eval_runtime": 66.4748,
+      "eval_samples_per_second": 15.374,
+      "eval_steps_per_second": 0.481,
+      "step": 384
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 4.516488075256348,
+      "learning_rate": 3.8705027427957864e-05,
+      "loss": 0.4308,
+      "step": 576
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8189823874755382,
+      "eval_f1": 0.8291782086795938,
+      "eval_loss": 0.4247056245803833,
+      "eval_mcc": 0.6425594703081364,
+      "eval_precision": 0.784965034965035,
+      "eval_recall": 0.8786692759295499,
+      "eval_runtime": 66.8952,
+      "eval_samples_per_second": 15.278,
+      "eval_steps_per_second": 0.478,
+      "step": 576
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.640265941619873,
+      "learning_rate": 1.9352513713978932e-05,
+      "loss": 0.4242,
+      "step": 768
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8111545988258317,
+      "eval_f1": 0.8214616096207216,
+      "eval_loss": 0.42209360003471375,
+      "eval_mcc": 0.6264991336111037,
+      "eval_precision": 0.7789473684210526,
+      "eval_recall": 0.8688845401174168,
+      "eval_runtime": 67.1893,
+      "eval_samples_per_second": 15.211,
+      "eval_steps_per_second": 0.476,
+      "step": 768
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 7.009722709655762,
+      "learning_rate": 0.0,
+      "loss": 0.419,
+      "step": 960
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8180039138943248,
+      "eval_f1": 0.8342245989304813,
+      "eval_loss": 0.42406341433525085,
+      "eval_mcc": 0.6485475826584332,
+      "eval_precision": 0.7659574468085106,
+      "eval_recall": 0.9158512720156555,
+      "eval_runtime": 66.6719,
+      "eval_samples_per_second": 15.329,
+      "eval_steps_per_second": 0.48,
+      "step": 960
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 960,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1178475986400.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8653499588119579,
+    "learning_rate": 9.676256856989465e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 16,
+    "temperature": 45
+  }
+}

run-21/checkpoint-960/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b9a69c0a84f1792b2d6d65795033f526e96e3e74b93dead0b939d20001f112
+size 4984

run-22/checkpoint-192/config.json

@@ -27,7 +27,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.39.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

run-22/checkpoint-192/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ab88a7ba1e5670757565c5ca4b110e9d43f3f8ae02fbdceb99d7777e9c3a913
+oid sha256:1c85e38420810a118a901915c1e6c8002f03a50116750d4ec99cbbe24ae88076
 size 17549312

run-22/checkpoint-192/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8e45d284b5cb9382e32a864816648879685ff5f3245670e66996a1632c64ff
+oid sha256:9a9bc63d6ad32e58510ec88b1d5ff0c31b47b075efc601b22f29b1c20bc0c165
 size 35122746

run-22/checkpoint-192/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
+oid sha256:ee09ea0d216727b799a80771850b95d7d61b646360702c64b2ec889cdc725399
 size 14054

run-22/checkpoint-192/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b33db83dddee49c21963d58255d32a3cecda813dd0f6c82cb872bb26af7fdf
+oid sha256:db67c5b678126350da081ac477535a95999cdb486050565381a604f97218b3ea
 size 1064

run-22/checkpoint-192/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.7984344422700587,
+  "best_metric": 0.7896281800391389,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-22/checkpoint-192",
-  "epoch": 2.0,
+  "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 192,
   "is_hyper_param_search": true,
@@ -10,55 +10,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 2.464465618133545,
-      "learning_rate": 0.0001794635836369996,
-      "loss": 0.565,
-      "step": 96
-    },
-    {
-      "epoch": 1.0,
-      "eval_accuracy": 0.7788649706457925,
-      "eval_f1": 0.8078231292517007,
-      "eval_loss": 0.4691426157951355,
-      "eval_precision": 0.7142857142857143,
-      "eval_recall": 0.9295499021526419,
-      "eval_runtime": 25.0337,
-      "eval_samples_per_second": 40.825,
-      "eval_steps_per_second": 1.278,
-      "step": 96
-    },
-    {
-      "epoch": 2.0,
-      "grad_norm": 4.053184509277344,
-      "learning_rate": 0.00015703063568237466,
-      "loss": 0.4676,
+      "grad_norm": 4.364559650421143,
+      "learning_rate": 0.0002529924510479742,
+      "loss": 0.5381,
       "step": 192
     },
     {
-      "epoch": 2.0,
-      "eval_accuracy": 0.7984344422700587,
-      "eval_f1": 0.8170515097690941,
-      "eval_loss": 0.4367915391921997,
-      "eval_precision": 0.7479674796747967,
-      "eval_recall": 0.9001956947162426,
-      "eval_runtime": 25.2941,
-      "eval_samples_per_second": 40.405,
-      "eval_steps_per_second": 1.265,
+      "epoch": 1.0,
+      "eval_accuracy": 0.7896281800391389,
+      "eval_f1": 0.8071748878923767,
+      "eval_loss": 0.45070555806159973,
+      "eval_mcc": 0.5890946801852007,
+      "eval_precision": 0.7450331125827815,
+      "eval_recall": 0.8806262230919765,
+      "eval_runtime": 67.3745,
+      "eval_samples_per_second": 15.169,
+      "eval_steps_per_second": 0.475,
       "step": 192
     }
   ],
   "logging_steps": 500,
-  "max_steps": 864,
+  "max_steps": 768,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 9,
+  "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 471390394560.0,
-  "train_batch_size": 32,
+  "total_flos": 235695197280.0,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8956145079239534,
-    "learning_rate": 0.00020189653159162458,
-    "num_train_epochs": 9,
-    "temperature": 8
+    "alpha": 0.885980659186716,
+    "learning_rate": 0.0003373232680639656,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 16,
+    "temperature": 44
   }
 }

run-22/checkpoint-192/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59435df03122e4e47861365c1b2756f99313581e8b38e82a031f16aa354557d
-size 4920
+oid sha256:8c24fdecf1c90c419bf77f10ab570330e1370392bd9d70f58780b22b36367b96
+size 4984

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f62d580257060cdaf08ca2f6bebff447fe36fd6a4ed09c360f3a936d71824ec
-size 4920
+oid sha256:8c24fdecf1c90c419bf77f10ab570330e1370392bd9d70f58780b22b36367b96
+size 4984