Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:109d187ff5b9a4d9b1cf17c3a48677dfbdc62289f6a3e9831c48c055c2ed837a
+oid sha256:b851075172d50769116d12249a9cff22e8c21976931d8165a57d7498ec6667c1
 size 430911284

run-moubnul5/checkpoint-1500/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-S",
+    "2": "B-S"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-S": 2,
+    "I-S": 1,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-moubnul5/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72499718ac926766f5468d262201bcc97e778acb5445043206214e875b740e84
+size 430911284

run-moubnul5/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97068838fc3520b68bda214528044c4eda5bcd6b81e067058b1515d82254de74
+size 861942330

run-moubnul5/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2623190ade7475a14422c6523b005c8acd111f240775a08c6f4ab59256d8d57
+size 14244

run-moubnul5/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c760e131eecd128de99d6ae96641dcf76e359c1e356bd934c4313d53dd4fdfc
+size 1064

run-moubnul5/checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-moubnul5/checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-moubnul5/checkpoint-1500/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.901960784313726,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.515832482124617,
+      "eval_f1_sklearn": 0.9513251883367813,
+      "eval_loss": 0.12229713052511215,
+      "eval_precision": 0.5629877369007804,
+      "eval_precision_sklearn": 0.9513251883367813,
+      "eval_recall": 0.4759660697455231,
+      "eval_recall_sklearn": 0.9513251883367813,
+      "eval_runtime": 4.2613,
+      "eval_samples_per_second": 95.745,
+      "eval_steps_per_second": 23.936,
+      "step": 306
+    },
+    {
+      "epoch": 1.6339869281045751,
+      "grad_norm": 1.7371214628219604,
+      "learning_rate": 6.73202614379085e-05,
+      "loss": 0.1032,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.507920792079208,
+      "eval_f1_sklearn": 0.9493735118466763,
+      "eval_loss": 0.16793084144592285,
+      "eval_precision": 0.5349322210636079,
+      "eval_precision_sklearn": 0.9493735118466763,
+      "eval_recall": 0.48350612629594725,
+      "eval_recall_sklearn": 0.9493735118466763,
+      "eval_runtime": 6.1428,
+      "eval_samples_per_second": 66.42,
+      "eval_steps_per_second": 16.605,
+      "step": 612
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.6094600251151109,
+      "eval_f1_sklearn": 0.9524181271712401,
+      "eval_loss": 0.16153906285762787,
+      "eval_precision": 0.5481927710843374,
+      "eval_precision_sklearn": 0.9524181271712401,
+      "eval_recall": 0.6861451460885957,
+      "eval_recall_sklearn": 0.9524181271712401,
+      "eval_runtime": 5.1328,
+      "eval_samples_per_second": 79.488,
+      "eval_steps_per_second": 19.872,
+      "step": 918
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 0.30743545293807983,
+      "learning_rate": 3.464052287581699e-05,
+      "loss": 0.0309,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.5933147632311978,
+      "eval_f1_sklearn": 0.9537452671845115,
+      "eval_loss": 0.18510332703590393,
+      "eval_precision": 0.5846294602012809,
+      "eval_precision_sklearn": 0.9537452671845115,
+      "eval_recall": 0.6022620169651273,
+      "eval_recall_sklearn": 0.9537452671845115,
+      "eval_runtime": 4.6906,
+      "eval_samples_per_second": 86.982,
+      "eval_steps_per_second": 21.746,
+      "step": 1224
+    },
+    {
+      "epoch": 4.901960784313726,
+      "grad_norm": 0.012615224346518517,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 0.0077,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1530,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 470773232452584.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 0.0001,
+    "metric": "eval/loss",
+    "per_device_train_batch_size": 4
+  }
+}

run-moubnul5/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89dc8df7f3fb0987257613d8306e14cf03e86313d666bec5ca1670eced74774
+size 5112

run-rstr4mx4/checkpoint-500/config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "bert-base-cased",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-S",
+    "2": "B-S"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-S": 2,
+    "I-S": 1,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 28996
+}

run-rstr4mx4/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b851075172d50769116d12249a9cff22e8c21976931d8165a57d7498ec6667c1
+size 430911284

run-rstr4mx4/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d236b1fab577737a3f8670ca4cf7455ac362d8b2a3df06f1b7b6b0fa39be881c
+size 861942330

run-rstr4mx4/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a801e52b02802e184980e68632305a0661a666536a8c36170f2de2d9852f4e
+size 14244

run-rstr4mx4/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c81b034b86eebaffe44e92389aedc2049503c0d1a95608e020f982e69e75c97f
+size 1064

run-rstr4mx4/checkpoint-500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-rstr4mx4/checkpoint-500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-rstr4mx4/checkpoint-500/trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.2679738562091503,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.2111706197398623,
+      "eval_f1_sklearn": 0.9420352082438815,
+      "eval_loss": 0.16127675771713257,
+      "eval_precision": 0.5609756097560976,
+      "eval_precision_sklearn": 0.9420352082438815,
+      "eval_recall": 0.13006597549481622,
+      "eval_recall_sklearn": 0.9420352082438815,
+      "eval_runtime": 4.3006,
+      "eval_samples_per_second": 94.87,
+      "eval_steps_per_second": 23.718,
+      "step": 153
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.40728631480616534,
+      "eval_f1_sklearn": 0.9447285218002264,
+      "eval_loss": 0.14659850299358368,
+      "eval_precision": 0.40370370370370373,
+      "eval_precision_sklearn": 0.9447285218002264,
+      "eval_recall": 0.410933081998115,
+      "eval_recall_sklearn": 0.9447285218002264,
+      "eval_runtime": 4.3654,
+      "eval_samples_per_second": 93.462,
+      "eval_steps_per_second": 23.365,
+      "step": 306
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.4323818437061301,
+      "eval_f1_sklearn": 0.9470705335883524,
+      "eval_loss": 0.1423368901014328,
+      "eval_precision": 0.42936802973977695,
+      "eval_precision_sklearn": 0.9470705335883524,
+      "eval_recall": 0.4354382657869934,
+      "eval_recall_sklearn": 0.9470705335883524,
+      "eval_runtime": 4.343,
+      "eval_samples_per_second": 93.944,
+      "eval_steps_per_second": 23.486,
+      "step": 459
+    },
+    {
+      "epoch": 3.2679738562091503,
+      "grad_norm": 1.8578802347183228,
+      "learning_rate": 1.7320261437908499e-06,
+      "loss": 0.1506,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 765,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 433135952304768.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "_wandb": {},
+    "assignments": {},
+    "learning_rate": 5e-06,
+    "metric": "eval/loss",
+    "per_device_train_batch_size": 8
+  }
+}

run-rstr4mx4/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f0faac25d416a58bb76b05100d0033c9bd328d14d03906ad62dab5d8d399b71
+size 5112

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89dc8df7f3fb0987257613d8306e14cf03e86313d666bec5ca1670eced74774
+oid sha256:4f0faac25d416a58bb76b05100d0033c9bd328d14d03906ad62dab5d8d399b71
 size 5112