Training in progress, epoch 3

logs/events.out.tfevents.1713513554.persepolis.29644.23

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d067b8998093203da8e1a6ae61dd405a7e085a1c7332e6b8028727118ce6d64c
-size 6014
+oid sha256:f704b528da702abf8d541235848516267863ac9ea0a6b394e12bf2c86d612cd4
+size 6548

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a70d41ce150a848f51170d570e5e46d9fcada2f887b070033f701e879352812
+oid sha256:807cb369b702c08db9d7773fca68c493e28c77130d0d293cc3c3dbbc9089777a
 size 54221200

run-22/checkpoint-1581/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-22/checkpoint-1581/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807cb369b702c08db9d7773fca68c493e28c77130d0d293cc3c3dbbc9089777a
+size 54221200

run-22/checkpoint-1581/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aea7d30dad15b12a9a4487883e3adaff9deea3293c17e29e0f92f4777092dbb
+size 108564282

run-22/checkpoint-1581/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911e9c586a1ec91d8affdbdd2cc5643bbb62a69cfa1f4869c228885fc8d6977d
+size 14308

run-22/checkpoint-1581/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23873f996675136e1493086c96a1018e9196b97804cfb7481b726e6a7660a4cd
+size 1064

run-22/checkpoint-1581/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-22/checkpoint-1581/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-22/checkpoint-1581/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.9162844036697247,
+  "best_model_checkpoint": "electra-distilled-sst\\run-22\\checkpoint-1581",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1581,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 13.01644229888916,
+      "learning_rate": 2.7002954057123424e-05,
+      "loss": 0.6671,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9036697247706422,
+      "eval_loss": 0.428321897983551,
+      "eval_runtime": 1.451,
+      "eval_samples_per_second": 600.984,
+      "eval_steps_per_second": 4.824,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 25.425676345825195,
+      "learning_rate": 2.4002625828554156e-05,
+      "loss": 0.3779,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9048165137614679,
+      "eval_loss": 0.40753328800201416,
+      "eval_runtime": 1.4531,
+      "eval_samples_per_second": 600.091,
+      "eval_steps_per_second": 4.817,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 7.495176792144775,
+      "learning_rate": 2.1002297599984884e-05,
+      "loss": 0.2908,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9162844036697247,
+      "eval_loss": 0.4330578148365021,
+      "eval_runtime": 1.4523,
+      "eval_samples_per_second": 600.414,
+      "eval_steps_per_second": 4.82,
+      "step": 1581
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 561038813831964.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9315044934322999,
+    "learning_rate": 3.0003282285692692e-05,
+    "num_train_epochs": 10,
+    "temperature": 20
+  }
+}

run-22/checkpoint-1581/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bfb904ef47190fb05ee3a7b704cb55aaae024d19bea395bae4002aafc84bd79
+size 5048