Training in progress, epoch 5

logs/events.out.tfevents.1713514686.persepolis.29644.27

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5864f8bcef9d4df54b3b21bf029f1e23c79cb5ab9a16f43dd28c8f0164e7fc7a
-size 7081
+oid sha256:564d358cd805ac1ed93347a66efba70aa442060ab8264e2c015dfaa40971b19a
+size 7615

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16fcc328cc1db63aa396a2fa120d34eb25007db4cf579e4485c664210667eab8
+oid sha256:2f37f6197156d695ecd76d157a273df5cc01ee09927381ac509e934549b9d898
 size 54221200

run-26/checkpoint-2635/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-26/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f37f6197156d695ecd76d157a273df5cc01ee09927381ac509e934549b9d898
+size 54221200

run-26/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eee4b5aa7750d787ea32e5e9cfff2900d02c4eea0bfb69a539ed8f74fb8c8f26
+size 108564282

run-26/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f663bdb15d062023c1cf28c57849d73a5f427a71fc4ff8bd8995ab52fb854b16
+size 14308

run-26/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6b72a5a0fe3bfce22c5e65ba6a7b680a17016a680fd9843831ff4100f51c9b2
+size 1064

run-26/checkpoint-2635/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-26/checkpoint-2635/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-26/checkpoint-2635/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.9220183486238532,
+  "best_model_checkpoint": "electra-distilled-sst\\run-26\\checkpoint-2635",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2635,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 25.633333206176758,
+      "learning_rate": 5.249775471708889e-05,
+      "loss": 0.9686,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9105504587155964,
+      "eval_loss": 0.6331567168235779,
+      "eval_runtime": 1.4527,
+      "eval_samples_per_second": 600.271,
+      "eval_steps_per_second": 4.819,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 32.01615905761719,
+      "learning_rate": 4.666590043043083e-05,
+      "loss": 0.4917,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.911697247706422,
+      "eval_loss": 0.6638227105140686,
+      "eval_runtime": 1.4467,
+      "eval_samples_per_second": 602.739,
+      "eval_steps_per_second": 4.838,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 19.456010818481445,
+      "learning_rate": 4.0834046143772765e-05,
+      "loss": 0.3597,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9174311926605505,
+      "eval_loss": 0.6752657294273376,
+      "eval_runtime": 1.4552,
+      "eval_samples_per_second": 599.222,
+      "eval_steps_per_second": 4.81,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.038837432861328,
+      "learning_rate": 3.500219185711471e-05,
+      "loss": 0.2792,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9128440366972477,
+      "eval_loss": 0.6751970052719116,
+      "eval_runtime": 1.4453,
+      "eval_samples_per_second": 603.35,
+      "eval_steps_per_second": 4.843,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 17.21753692626953,
+      "learning_rate": 2.918140370762298e-05,
+      "loss": 0.2339,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9220183486238532,
+      "eval_loss": 0.6162137389183044,
+      "eval_runtime": 1.4517,
+      "eval_samples_per_second": 600.678,
+      "eval_steps_per_second": 4.822,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 936602651243304.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8150986578770638,
+    "learning_rate": 5.831854286658062e-05,
+    "num_train_epochs": 10,
+    "temperature": 30
+  }
+}

run-26/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb9930e6c9d099fd56d0aa2b7dd1403c1b4089edd722eab9834a9aa20179683
+size 5048