Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9d1735e03593e326e1e528895da92b01589e1a2f64e413b4662eddc1d66131
+oid sha256:82a662254a9bd9189f215541b7a62820144d6786928f15ae2de7f755f01c5828
 size 116795404

run-3/checkpoint-1650/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "cointegrated/rubert-tiny2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "emb_size": 312,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 600,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 2048,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 3,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 83828
+}

run-3/checkpoint-1650/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a662254a9bd9189f215541b7a62820144d6786928f15ae2de7f755f01c5828
+size 116795404

run-3/checkpoint-1650/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6be5d5046bd18d02831886a2ca4ce380850936fc5d24f1cf627c971ca435bd10
+size 233621882

run-3/checkpoint-1650/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989e0de2cbf91e1f074906d2b83814b66827c8558181a9e5c07f660052e422ec
+size 13990

run-3/checkpoint-1650/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a14bf2ce9f6e05ed349d9057c685478492cdf05f37594ddaa3f216426168c4
+size 1064

run-3/checkpoint-1650/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-3/checkpoint-1650/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 2048,
+  "never_split": null,
+  "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": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1650/trainer_state.json

@@ -0,0 +1,71 @@
+{
+  "best_metric": 0.3877551020408163,
+  "best_model_checkpoint": "rubert-tiny2-finetuned-classification\\run-3\\checkpoint-550",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1650,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.3662899505209146e-06,
+      "loss": 2.35,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.3877551020408163,
+      "eval_loss": 2.2825658321380615,
+      "eval_runtime": 1.1797,
+      "eval_samples_per_second": 207.683,
+      "eval_steps_per_second": 13.563,
+      "step": 550
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.722508415987777e-07,
+      "loss": 2.2529,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.3795918367346939,
+      "eval_loss": 2.1926839351654053,
+      "eval_runtime": 1.103,
+      "eval_samples_per_second": 222.122,
+      "eval_steps_per_second": 14.506,
+      "step": 1100
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 1.7821173267664104e-07,
+      "loss": 2.1925,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.37551020408163266,
+      "eval_loss": 2.160534143447876,
+      "eval_runtime": 1.431,
+      "eval_samples_per_second": 171.209,
+      "eval_steps_per_second": 11.181,
+      "step": 1650
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1650,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2885602679400.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9603290594430513e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 4,
+    "seed": 40
+  }
+}

run-3/checkpoint-1650/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e267ca63c53f31d703414854821a4189b7f58d9ce572859ccd38579e71acb732
+size 4728

runs/Jan15_00-51-52_DESKTOP-RFEED41/events.out.tfevents.1705260668.DESKTOP-RFEED41.20976.9

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d9fa85fa96d592886a14e286787c3cc78dbeb83859ca4758437fc3a187945c
-size 5912
+oid sha256:a370ef6c93ad0457d5f90e34e76925fc88e4c13ba22dc9b90b5dc2292076f0df
+size 6746