Training in progress, epoch 1

logs/events.out.tfevents.1713508880.persepolis.29644.12

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6839082c40758b72d4d9eee4c14ef9c6431526ffe75cb0a3e29712094bdd2a0b
-size 8681
+oid sha256:4ffa6bf0cb1735229a1092c7418ea9bfabe5f4aa9d75d23f7ff623cac73eac34
+size 9569

logs/events.out.tfevents.1713509874.persepolis.29644.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af9204ab812cf8dafc4804b5284c035904a217c805d08affdbb535815de9433a
+size 5479

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbfd9e98ace10eb753a7b640e5c1c5b86a827b7b84c678c4e5d80a45549abec2
+oid sha256:28f9fd400ecb4e8f808e0545ba5ea028e75d6dcf13faee8b6078f7a056b4ae90
 size 54221200

run-11/checkpoint-4216/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "google/electra-small-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-11/checkpoint-4216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a138599f33b0e0ad68feb8e561dfa7744804e409494018c866023b28962b943
+size 54221200

run-11/checkpoint-4216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d70d601f8533407618f996c4c400e3df798423b19362dfbce2b8ab79603cdb7
+size 108564282

run-11/checkpoint-4216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08136d8aabbe00c84b577a8be1629f5314ec5ca811cb1ca08ca40c08727468e9
+size 14308

run-11/checkpoint-4216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8d78b6fd9b60cc358262cb7cb3fce135f2c599ef56ccebf640e2521e0043617
+size 1064

run-11/checkpoint-4216/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-11/checkpoint-4216/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-11/checkpoint-4216/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": 0.9277522935779816,
+  "best_model_checkpoint": "electra-distilled-sst\\run-11\\checkpoint-3162",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 4216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 14.338537216186523,
+      "learning_rate": 5.0174854029835415e-05,
+      "loss": 0.5621,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 0.39338329434394836,
+      "eval_runtime": 1.4401,
+      "eval_samples_per_second": 605.519,
+      "eval_steps_per_second": 4.861,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 21.374542236328125,
+      "learning_rate": 4.302061894724029e-05,
+      "loss": 0.3067,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9185779816513762,
+      "eval_loss": 0.45042580366134644,
+      "eval_runtime": 1.461,
+      "eval_samples_per_second": 596.848,
+      "eval_steps_per_second": 4.791,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 5.032501697540283,
+      "learning_rate": 3.5852782657263795e-05,
+      "loss": 0.2271,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9208715596330275,
+      "eval_loss": 0.42918458580970764,
+      "eval_runtime": 1.4441,
+      "eval_samples_per_second": 603.85,
+      "eval_steps_per_second": 4.847,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 5.360136985778809,
+      "learning_rate": 2.868494636728731e-05,
+      "loss": 0.176,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9208715596330275,
+      "eval_loss": 0.4744165539741516,
+      "eval_runtime": 1.4509,
+      "eval_samples_per_second": 601.02,
+      "eval_steps_per_second": 4.825,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 11.912830352783203,
+      "learning_rate": 2.1517110077310823e-05,
+      "loss": 0.1486,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9185779816513762,
+      "eval_loss": 0.4420042037963867,
+      "eval_runtime": 1.4442,
+      "eval_samples_per_second": 603.815,
+      "eval_steps_per_second": 4.847,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 6.889047622680664,
+      "learning_rate": 1.4349273787334336e-05,
+      "loss": 0.1268,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9277522935779816,
+      "eval_loss": 0.4492184817790985,
+      "eval_runtime": 1.4504,
+      "eval_samples_per_second": 601.225,
+      "eval_steps_per_second": 4.826,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 15.968618392944336,
+      "learning_rate": 7.195038704739208e-06,
+      "loss": 0.1059,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9254587155963303,
+      "eval_loss": 0.47401389479637146,
+      "eval_runtime": 1.4461,
+      "eval_samples_per_second": 602.992,
+      "eval_steps_per_second": 4.841,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 5.614753246307373,
+      "learning_rate": 2.720241476271912e-08,
+      "loss": 0.0972,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9185779816513762,
+      "eval_loss": 0.4893525540828705,
+      "eval_runtime": 1.4503,
+      "eval_samples_per_second": 601.271,
+      "eval_steps_per_second": 4.827,
+      "step": 4216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 1497908425331724.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9346338538228292,
+    "learning_rate": 5.73426903198119e-05,
+    "num_train_epochs": 8,
+    "temperature": 23
+  }
+}

run-11/checkpoint-4216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e19097391429290e70a25e43cb5761ced9452a1909377e4765cbe0281d76fb
+size 5048

run-12/checkpoint-527/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "google/electra-small-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-12/checkpoint-527/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28f9fd400ecb4e8f808e0545ba5ea028e75d6dcf13faee8b6078f7a056b4ae90
+size 54221200

run-12/checkpoint-527/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3196b1a20be879baf43db92255f4e044cb075f357affd0830264b1a2e751551b
+size 108564282

run-12/checkpoint-527/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc9791cb55befa0c8b441bb05d4823eb646b6924ad858d6b339d592c0fbe5a2
+size 14308

run-12/checkpoint-527/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dde8df3521714ce34bce52a2a00f27fcc4123b95ef26ca39454bf989dd724ae
+size 1064

run-12/checkpoint-527/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-12/checkpoint-527/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-12/checkpoint-527/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 0.8990825688073395,
+  "best_model_checkpoint": "electra-distilled-sst\\run-12\\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,
+      "grad_norm": 7.509405136108398,
+      "learning_rate": 2.0402991030650117e-05,
+      "loss": 0.397,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8990825688073395,
+      "eval_loss": 0.27017587423324585,
+      "eval_runtime": 1.4468,
+      "eval_samples_per_second": 602.727,
+      "eval_steps_per_second": 4.838,
+      "step": 527
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4216,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "total_flos": 186587234208876.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9957859034199653,
+    "learning_rate": 2.3317704035028705e-05,
+    "num_train_epochs": 8,
+    "temperature": 24
+  }
+}

run-12/checkpoint-527/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b51d56043a7511b7fc0f1a70978ea32af3fd9681bc971ff2e638715cd381dee1
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e19097391429290e70a25e43cb5761ced9452a1909377e4765cbe0281d76fb
+oid sha256:b51d56043a7511b7fc0f1a70978ea32af3fd9681bc971ff2e638715cd381dee1
 size 5048