Training in progress, epoch 5

logs/events.out.tfevents.1713515930.persepolis.29644.31

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b81a3df65706f99fcee15c7953bc9498d2bf0f60f01a5dca9c5351faf55c07
-size 7080
+oid sha256:bf42017b0a0feec408e0504af60d4ebe957a74e40c0dcb01963584803d3cfd75
+size 7614

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:483235e630243389cbbdc5c86c8ee879e65e59791f4ad657bf9e3ed64040c9da
+oid sha256:f785784151d5055842fa2396d0dda79bbe0d25d61a04afda95b1eecdf8e20491
 size 54221200

run-30/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-30/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f785784151d5055842fa2396d0dda79bbe0d25d61a04afda95b1eecdf8e20491
+size 54221200

run-30/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81bfd1fe4915f769f3e4e75c41504fd4d1af35a13830aa58c13b5c94615461e4
+size 108564282

run-30/checkpoint-2635/rng_state.pth

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

run-30/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635961d511b982f43526dbf37b20d5727b818c93999a7d742e8bd82aaa1069c7
+size 1064

run-30/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-30/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-30/checkpoint-2635/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.9197247706422018,
+  "best_model_checkpoint": "electra-distilled-sst\\run-30\\checkpoint-1581",
+  "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": 26.225385665893555,
+      "learning_rate": 6.561713559027068e-05,
+      "loss": 0.6075,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9139908256880734,
+      "eval_loss": 0.47316521406173706,
+      "eval_runtime": 1.4499,
+      "eval_samples_per_second": 601.43,
+      "eval_steps_per_second": 4.828,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 13.330994606018066,
+      "learning_rate": 5.741499364148685e-05,
+      "loss": 0.3214,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8956422018348624,
+      "eval_loss": 0.6051578521728516,
+      "eval_runtime": 1.4493,
+      "eval_samples_per_second": 601.653,
+      "eval_steps_per_second": 4.83,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 10.15234661102295,
+      "learning_rate": 4.9212851692703006e-05,
+      "loss": 0.2348,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9197247706422018,
+      "eval_loss": 0.4945127069950104,
+      "eval_runtime": 1.4486,
+      "eval_samples_per_second": 601.961,
+      "eval_steps_per_second": 4.832,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": Infinity,
+      "learning_rate": 4.1026273580634136e-05,
+      "loss": 0.1824,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 0.5778486728668213,
+      "eval_runtime": 1.4513,
+      "eval_samples_per_second": 600.822,
+      "eval_steps_per_second": 4.823,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 21.25727653503418,
+      "learning_rate": 3.28241316318503e-05,
+      "loss": 0.1498,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.911697247706422,
+      "eval_loss": 0.515268087387085,
+      "eval_runtime": 1.4401,
+      "eval_samples_per_second": 605.529,
+      "eval_steps_per_second": 4.861,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 936602651243304.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9134230134636561,
+    "learning_rate": 7.381927753905452e-05,
+    "num_train_epochs": 9,
+    "temperature": 18
+  }
+}

run-30/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45cc19cb2ba4d5f655568724a8069d9e57ef8b6fd47d6d510514ad88cab0815d
+size 5048