Training in progress, epoch 5

logs/events.out.tfevents.1713521079.persepolis.29644.50

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ddfe9e532f25f5bcea739b961672717ee3bf224f770b780346758498b5c395f
-size 7079
+oid sha256:3f1f418b0bdc1a9a126d05ee92d2acd736735e44262bccd1e4daf16027a2cc1b
+size 7967

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1c152c35409858f294f58a959f9b4086a3ca8bdbe5795a4b9002dcd278d58f
+oid sha256:df5c79ee37d8b50423f191bba660ae720e4e4b52426b167e143a2e06b75405d2
 size 54221200

run-49/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-49/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df5c79ee37d8b50423f191bba660ae720e4e4b52426b167e143a2e06b75405d2
+size 54221200

run-49/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bb52188b82e000deab439481b6b1ca352aef1dd2dcd463103755a6ce827a8bc
+size 108564282

run-49/checkpoint-2635/rng_state.pth

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

run-49/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c33891bf9f9e1abcb83625471a2feeb43cb7885ca57f8a29ce316b4df24128d
+size 1064

run-49/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-49/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-49/checkpoint-2635/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.9243119266055045,
+  "best_model_checkpoint": "electra-distilled-sst\\run-49\\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": 8.770561218261719,
+      "learning_rate": 4.952771397331368e-05,
+      "loss": 0.3762,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.908256880733945,
+      "eval_loss": 0.28651162981987,
+      "eval_runtime": 1.4488,
+      "eval_samples_per_second": 601.892,
+      "eval_steps_per_second": 4.832,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.216989517211914,
+      "learning_rate": 3.714578547998526e-05,
+      "loss": 0.2105,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9048165137614679,
+      "eval_loss": 0.3472459316253662,
+      "eval_runtime": 1.4467,
+      "eval_samples_per_second": 602.769,
+      "eval_steps_per_second": 4.839,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.215942621231079,
+      "learning_rate": 2.476385698665684e-05,
+      "loss": 0.1566,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9243119266055045,
+      "eval_loss": 0.30982208251953125,
+      "eval_runtime": 1.448,
+      "eval_samples_per_second": 602.203,
+      "eval_steps_per_second": 4.834,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 7.901008129119873,
+      "learning_rate": 1.238192849332842e-05,
+      "loss": 0.1221,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9174311926605505,
+      "eval_loss": 0.3680877685546875,
+      "eval_runtime": 1.4488,
+      "eval_samples_per_second": 601.891,
+      "eval_steps_per_second": 4.832,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.315232753753662,
+      "learning_rate": 0.0,
+      "loss": 0.1029,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9174311926605505,
+      "eval_loss": 0.37717682123184204,
+      "eval_runtime": 1.4394,
+      "eval_samples_per_second": 605.794,
+      "eval_steps_per_second": 4.863,
+      "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": 0.982936133975336,
+    "learning_rate": 6.19096424666421e-05,
+    "num_train_epochs": 5,
+    "temperature": 22
+  }
+}

run-49/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5e86a5a59e0cfb3592389f7dec57e9a5a5e77f88db7273203448bb5a35411eb
+size 5048