Training in progress, epoch 3

logs/events.out.tfevents.1713504727.persepolis.29644.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f67895705893a46ed007ef15c0e15e2f4b7df7ad573c8f19c8f4821594bac75
-size 6012
+oid sha256:4126951e4425ff9474387614016dbcc8f5b90569e42908879ab8af8d2cbc3c8e
+size 6546

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3e249fc0a868c1d79324cf7b54d15efe7632a7144979a4b6db19baa23f9d083
+oid sha256:b737fd34a4268f2be2f7b46ae2732c8c63f4f9b5dc1549e07a96a23a6b2750ec
 size 54221200

run-1/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-1/checkpoint-1581/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b737fd34a4268f2be2f7b46ae2732c8c63f4f9b5dc1549e07a96a23a6b2750ec
+size 54221200

run-1/checkpoint-1581/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e020b393bc2fcb05ed90dd1f1c86cd2a6db1ed72629c15056010453cb5678318
+size 108564282

run-1/checkpoint-1581/rng_state.pth

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

run-1/checkpoint-1581/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af261909df231e80d41b44505a3284bd3217e015cea7793fc189467ab579fdcd
+size 1064

run-1/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-1/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-1/checkpoint-1581/trainer_state.json

@@ -0,0 +1,74 @@
+{
+  "best_metric": 0.8910550458715596,
+  "best_model_checkpoint": "electra-distilled-sst\\run-1\\checkpoint-1054",
+  "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": 66.74252319335938,
+      "learning_rate": 0.0002000029100592468,
+      "loss": 2.5183,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.875,
+      "eval_loss": 2.3820443153381348,
+      "eval_runtime": 1.4493,
+      "eval_samples_per_second": 601.689,
+      "eval_steps_per_second": 4.83,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 67.3247299194336,
+      "learning_rate": 0.00015007323994971434,
+      "loss": 1.237,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8910550458715596,
+      "eval_loss": 2.0578901767730713,
+      "eval_runtime": 1.4579,
+      "eval_samples_per_second": 598.133,
+      "eval_steps_per_second": 4.802,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 9.862482070922852,
+      "learning_rate": 0.00010014356984018184,
+      "loss": 0.8517,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8841743119266054,
+      "eval_loss": 2.112179756164551,
+      "eval_runtime": 1.4398,
+      "eval_samples_per_second": 605.639,
+      "eval_steps_per_second": 4.862,
+      "step": 1581
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 561038813831964.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.15523880635662113,
+    "learning_rate": 0.0002496483505476624,
+    "num_train_epochs": 5,
+    "temperature": 16
+  }
+}

run-1/checkpoint-1581/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ae5bfb8dc04e1587c99a811e9f5c8e620e9e0c3708ec65e7504205f51d366f
+size 5048