Training in progress, epoch 5

logs/events.out.tfevents.1713520454.persepolis.29644.49

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8700edcedf46d37404cdb93383ec02b69273e03de5c1a24b4a8c5c25b5109fe
-size 7080
+oid sha256:a83eabfbd919b596a08e6ea129783285c0b948b50add569e5d840bf65389e151
+size 7968

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:862c42b16cdf466e046a4c1dfd41df63ccda74fe5c1f8eca9528c6a768c551e8
+oid sha256:2db2f5960097eeda8091bd585ee8cb6b6ec8af55272333240593a73e7c83bfc6
 size 54221200

run-48/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-48/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2db2f5960097eeda8091bd585ee8cb6b6ec8af55272333240593a73e7c83bfc6
+size 54221200

run-48/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e58e6b05ea97dca4a7a6ae033b0ddab39b53da457ac9ad6127e49adbc285e87
+size 108564282

run-48/checkpoint-2635/rng_state.pth

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

run-48/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc412aedf9e8b0a43c806fd2510db101b993a1bbbc60405ed405c6cbd879121
+size 1064

run-48/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-48/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-48/checkpoint-2635/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.9208715596330275,
+  "best_model_checkpoint": "electra-distilled-sst\\run-48\\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": 8.276034355163574,
+      "learning_rate": 4.888681242124731e-05,
+      "loss": 0.3265,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9036697247706422,
+      "eval_loss": 0.2659453749656677,
+      "eval_runtime": 1.4511,
+      "eval_samples_per_second": 600.924,
+      "eval_steps_per_second": 4.824,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 7.019628524780273,
+      "learning_rate": 3.6665109315935477e-05,
+      "loss": 0.1866,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9059633027522935,
+      "eval_loss": 0.29601141810417175,
+      "eval_runtime": 1.4476,
+      "eval_samples_per_second": 602.36,
+      "eval_steps_per_second": 4.835,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.9231150150299072,
+      "learning_rate": 2.4443406210623653e-05,
+      "loss": 0.1398,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9208715596330275,
+      "eval_loss": 0.27852392196655273,
+      "eval_runtime": 1.4489,
+      "eval_samples_per_second": 601.827,
+      "eval_steps_per_second": 4.831,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 6.364706039428711,
+      "learning_rate": 1.2221703105311827e-05,
+      "loss": 0.1103,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9162844036697247,
+      "eval_loss": 0.31632736325263977,
+      "eval_runtime": 1.4507,
+      "eval_samples_per_second": 601.084,
+      "eval_steps_per_second": 4.825,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 5.227040767669678,
+      "learning_rate": 0.0,
+      "loss": 0.094,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9197247706422018,
+      "eval_loss": 0.3277532458305359,
+      "eval_runtime": 1.4468,
+      "eval_samples_per_second": 602.714,
+      "eval_steps_per_second": 4.838,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 936602651243304.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9947666589577905,
+    "learning_rate": 6.110851552655913e-05,
+    "num_train_epochs": 5,
+    "temperature": 22
+  }
+}

run-48/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3caa05c6962a1831c0317e3a36e73212c131ddc84b1881835f1c66c0199090fa
+size 5048