Training in progress, epoch 5

logs/events.out.tfevents.1713505330.persepolis.29644.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ad063f7c7407738b654927296485f35921ba66c313dc116e1e04ba0c42b953
-size 7080
+oid sha256:33c2fe3d1d9ce03262279e5aeac953313f35998f615857365a4b46b9bb77e4ba
+size 7614

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c787dc8ca5037d7e550d974228ab209d493ebe7dd7df5247b271c12f3b734ef
+oid sha256:343d71d7cdfc34f5c4b6ddf0f28c8748b6b666e4f0442a0f29a0db4e1b1b992e
 size 54221200

run-2/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-2/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343d71d7cdfc34f5c4b6ddf0f28c8748b6b666e4f0442a0f29a0db4e1b1b992e
+size 54221200

run-2/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c273a2d9efbb7832c650a74602c51141c1d9fb89ac2a3e85610db931c2c2f5
+size 108564282

run-2/checkpoint-2635/rng_state.pth

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

run-2/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec821833935dafd6e80f5890c75a445b59330d773cf4f26bf4696aab2f51fd4
+size 1064

run-2/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-2/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-2/checkpoint-2635/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.5091743119266054,
+  "best_model_checkpoint": "electra-distilled-sst\\run-2\\checkpoint-527",
+  "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": 3.510751485824585,
+      "learning_rate": 0.0007235764985208607,
+      "loss": 4.9041,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 4.841418266296387,
+      "eval_runtime": 1.4537,
+      "eval_samples_per_second": 599.861,
+      "eval_steps_per_second": 4.815,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.5188323259353638,
+      "learning_rate": 0.0005789160983992775,
+      "loss": 4.9002,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 4.816441059112549,
+      "eval_runtime": 1.4412,
+      "eval_samples_per_second": 605.042,
+      "eval_steps_per_second": 4.857,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.3247452974319458,
+      "learning_rate": 0.00043425569827769417,
+      "loss": 4.9,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 4.82835054397583,
+      "eval_runtime": 1.4366,
+      "eval_samples_per_second": 606.994,
+      "eval_steps_per_second": 4.873,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.6336215734481812,
+      "learning_rate": 0.0002895952981561108,
+      "loss": 4.893,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 4.868070602416992,
+      "eval_runtime": 1.4415,
+      "eval_samples_per_second": 604.928,
+      "eval_steps_per_second": 4.856,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2643113136291504,
+      "learning_rate": 0.0001449348980345275,
+      "loss": 4.8991,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5091743119266054,
+      "eval_loss": 4.832038879394531,
+      "eval_runtime": 1.448,
+      "eval_samples_per_second": 602.191,
+      "eval_steps_per_second": 4.834,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 936602651243304.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.2011698337552854,
+    "learning_rate": 0.0008679624007294999,
+    "num_train_epochs": 6,
+    "temperature": 5
+  }
+}

run-2/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0abd3ad0420c43f4a6dc3c7f59acb9782deb90e9d7937e2e6b0b2fe954e1152f
+size 5048