Training in progress, epoch 8

logs/events.out.tfevents.1713510100.persepolis.29644.14

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:605ff5d3a23736506a4fcdf3e1bc3ec1d3ed166780db2b2499219c56bebab17f
-size 8682
+oid sha256:71145009a55ffdd472fe60f800397f6d2ab30c62b5a608aa01b8a1624079669e
+size 9216

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45745993737346ae32a0c24fb2cb17308cae0695ea15176ba54a95673359eca8
+oid sha256:24da636762d3fc71696a12c52428a4f49f5396ac6e83e2bed69b7146ff3c78a1
 size 54221200

run-13/checkpoint-4216/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-13/checkpoint-4216/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24da636762d3fc71696a12c52428a4f49f5396ac6e83e2bed69b7146ff3c78a1
+size 54221200

run-13/checkpoint-4216/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1930c127e73f32751db6e70417234c139280b9ae7e59c23f4674c212ee57de93
+size 108564282

run-13/checkpoint-4216/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08136d8aabbe00c84b577a8be1629f5314ec5ca811cb1ca08ca40c08727468e9
+size 14308

run-13/checkpoint-4216/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1cc983409c19193b14e3550b870b3f3a7234005c32ac14c03339f984b016817
+size 1064

run-13/checkpoint-4216/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-13/checkpoint-4216/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-13/checkpoint-4216/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": 0.926605504587156,
+  "best_model_checkpoint": "electra-distilled-sst\\run-13\\checkpoint-3162",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 4216,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 22.835023880004883,
+      "learning_rate": 4.3163581221778226e-05,
+      "loss": 0.8573,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9162844036697247,
+      "eval_loss": 0.5491362810134888,
+      "eval_runtime": 1.4473,
+      "eval_samples_per_second": 602.517,
+      "eval_steps_per_second": 4.837,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 38.72591018676758,
+      "learning_rate": 3.7769413020716535e-05,
+      "loss": 0.4496,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9105504587155964,
+      "eval_loss": 0.5399537682533264,
+      "eval_runtime": 1.4499,
+      "eval_samples_per_second": 601.429,
+      "eval_steps_per_second": 4.828,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 6.218717575073242,
+      "learning_rate": 3.237524481965485e-05,
+      "loss": 0.3331,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9208715596330275,
+      "eval_loss": 0.5268839001655579,
+      "eval_runtime": 1.4424,
+      "eval_samples_per_second": 604.54,
+      "eval_steps_per_second": 4.853,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 4.019476890563965,
+      "learning_rate": 2.6981076618593168e-05,
+      "loss": 0.2593,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9174311926605505,
+      "eval_loss": 0.5509608387947083,
+      "eval_runtime": 1.453,
+      "eval_samples_per_second": 600.123,
+      "eval_steps_per_second": 4.818,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 19.7722110748291,
+      "learning_rate": 2.1586908417531485e-05,
+      "loss": 0.2191,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9162844036697247,
+      "eval_loss": 0.5370484590530396,
+      "eval_runtime": 1.4546,
+      "eval_samples_per_second": 599.496,
+      "eval_steps_per_second": 4.812,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 12.621796607971191,
+      "learning_rate": 1.6202975829754548e-05,
+      "loss": 0.1874,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.926605504587156,
+      "eval_loss": 0.572212815284729,
+      "eval_runtime": 1.4456,
+      "eval_samples_per_second": 603.228,
+      "eval_steps_per_second": 4.842,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 12.125116348266602,
+      "learning_rate": 1.0808807628692863e-05,
+      "loss": 0.1614,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.9197247706422018,
+      "eval_loss": 0.5944486260414124,
+      "eval_runtime": 1.4613,
+      "eval_samples_per_second": 596.712,
+      "eval_steps_per_second": 4.79,
+      "step": 3689
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 7.69290828704834,
+      "learning_rate": 5.414639427631178e-06,
+      "loss": 0.1463,
+      "step": 4216
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.9208715596330275,
+      "eval_loss": 0.652703046798706,
+      "eval_runtime": 1.4499,
+      "eval_samples_per_second": 601.423,
+      "eval_steps_per_second": 4.828,
+      "step": 4216
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 1497908425331724.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.8585651118406669,
+    "learning_rate": 4.854751380955516e-05,
+    "num_train_epochs": 9,
+    "temperature": 23
+  }
+}

run-13/checkpoint-4216/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c102614f2d06a7080afce70c5e28f1aff4a701034ab879e8e673132a317abae
+size 5048