Training in progress, epoch 2

logs/events.out.tfevents.1713519714.persepolis.29644.45

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c9a57320486e77e5e046963cbf56ecb3c699412abde2139354bc1fa835fc166
-size 5477
+oid sha256:d3219b44fb17c4e0661961f3cc074fb3aef2bae03046c2c8148bcd3345864ccd
+size 6365

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f916af1d0f22901d6ca99b00c7dd680c46080734c5d6eeb46c77b30f2a65739
+oid sha256:7098240a958e05dd0135bc20eed78c4d844fbe774c00dcdb2c583de64a144d01
 size 54221200

run-44/checkpoint-1054/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-44/checkpoint-1054/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7098240a958e05dd0135bc20eed78c4d844fbe774c00dcdb2c583de64a144d01
+size 54221200

run-44/checkpoint-1054/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02645ad52d89701259737e90a37f82cd2afa3e37d78054dbc2c6fe975bdc7ca8
+size 108564282

run-44/checkpoint-1054/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085ca35ec4dc671993a68ae04b5c8903d6f41b040217020fac4d4514df1e6c6e
+size 14308

run-44/checkpoint-1054/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7928fc232ea77911044e8e73f2883b74eae31b343bcd6780f2ce034876e7567a
+size 1064

run-44/checkpoint-1054/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-44/checkpoint-1054/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-44/checkpoint-1054/trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": 0.9059633027522935,
+  "best_model_checkpoint": "electra-distilled-sst\\run-44\\checkpoint-1054",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1054,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 47.874210357666016,
+      "learning_rate": 2.4172863288960017e-05,
+      "loss": 3.4781,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8922018348623854,
+      "eval_loss": 1.7304165363311768,
+      "eval_runtime": 1.4497,
+      "eval_samples_per_second": 601.489,
+      "eval_steps_per_second": 4.828,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 82.40401458740234,
+      "learning_rate": 1.3682752805071707e-07,
+      "loss": 1.7274,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9059633027522935,
+      "eval_loss": 1.6832726001739502,
+      "eval_runtime": 1.4506,
+      "eval_samples_per_second": 601.151,
+      "eval_steps_per_second": 4.826,
+      "step": 1054
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1054,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 373776249469380.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.12166614132948814,
+    "learning_rate": 4.80720715218186e-05,
+    "num_train_epochs": 2,
+    "temperature": 24
+  }
+}

run-44/checkpoint-1054/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:117384d9d02efc6e9df11684e43bccddee1cab2d316f94e8e5d7dd368732f85f
+size 5048