Training in progress, epoch 6

logs/events.out.tfevents.1713507864.persepolis.29644.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17467058c739fb0b7bf64145ed91b2ab4228d53620816c29e332ae4f2bb8fa48
-size 7615
+oid sha256:227de88f65817e93b6c8eb5038b54e9f9ef02aaa2acf9758649f617b5fa86369
+size 8149

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f08ddba2779c56f948281eb14a63b56c8158c791e3078730dc603d3ca8f29459
+oid sha256:9a10504331d0780496e2e1a1a679eb93252cbf8244a56fa91a92c24cea551ac1
 size 54221200

run-8/checkpoint-3162/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-8/checkpoint-3162/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a10504331d0780496e2e1a1a679eb93252cbf8244a56fa91a92c24cea551ac1
+size 54221200

run-8/checkpoint-3162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9281985881b59f81681668857125bbed459e4ef5bd98a42d050da3f27c186231
+size 108564282

run-8/checkpoint-3162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2bc2ed5c3d6e162bc02d0b7d435de20ac0a9e3adc9ebc0adf2faa333702bbf9
+size 14308

run-8/checkpoint-3162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed24cd5b747db2c5f3d99587efce82259f491efc87b2288a336a6db6cbeb90b5
+size 1064

run-8/checkpoint-3162/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-8/checkpoint-3162/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-8/checkpoint-3162/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": 0.9185779816513762,
+  "best_model_checkpoint": "electra-distilled-sst\\run-8\\checkpoint-3162",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 3162,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 25.336427688598633,
+      "learning_rate": 8.271664431386432e-05,
+      "loss": 0.94,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9036697247706422,
+      "eval_loss": 0.6703569889068604,
+      "eval_runtime": 1.4486,
+      "eval_samples_per_second": 601.968,
+      "eval_steps_per_second": 4.832,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.467299461364746,
+      "learning_rate": 7.352784339619853e-05,
+      "loss": 0.4737,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8990825688073395,
+      "eval_loss": 0.8164154887199402,
+      "eval_runtime": 1.4496,
+      "eval_samples_per_second": 601.528,
+      "eval_steps_per_second": 4.829,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 44.32056427001953,
+      "learning_rate": 6.433904247853274e-05,
+      "loss": 0.3435,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8979357798165137,
+      "eval_loss": 0.8911434412002563,
+      "eval_runtime": 1.4479,
+      "eval_samples_per_second": 602.254,
+      "eval_steps_per_second": 4.835,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.458914756774902,
+      "learning_rate": 5.515024156086696e-05,
+      "loss": 0.2599,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9151376146788991,
+      "eval_loss": 0.7757946252822876,
+      "eval_runtime": 1.446,
+      "eval_samples_per_second": 603.064,
+      "eval_steps_per_second": 4.841,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": Infinity,
+      "learning_rate": 4.5978876698073397e-05,
+      "loss": 0.2156,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9162844036697247,
+      "eval_loss": 0.7059925198554993,
+      "eval_runtime": 1.4472,
+      "eval_samples_per_second": 602.529,
+      "eval_steps_per_second": 4.837,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 26.35287857055664,
+      "learning_rate": 3.679007578040761e-05,
+      "loss": 0.1789,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9185779816513762,
+      "eval_loss": 0.6810566186904907,
+      "eval_runtime": 1.4505,
+      "eval_samples_per_second": 601.155,
+      "eval_steps_per_second": 4.826,
+      "step": 3162
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5270,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1123721737396596.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7393993567935025,
+    "learning_rate": 9.188800917665787e-05,
+    "num_train_epochs": 10,
+    "temperature": 6
+  }
+}

run-8/checkpoint-3162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:604fb470236be9b28d71629cd094f68d34075ab2ebf7a71e2d7fae152203ef0e
+size 5048