Training in progress, step 1000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,36 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "eos_token_id": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 140274
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:821773593319cef84468d10a244226341b7b8667c44dd2971a1cf23640daed44
+size 775678032

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52632d962d021592a4d35dcf054f881443ff2887ff0e4bbbc4353a2b8b9a91f6
+size 1551478091

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55722c1d04d6be8d4523cc19c3a4a31a7e2280365d564803d84b6488532136d
+size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b19a7500950d30fded81aead129a45d919e1761663c3b918dd44c1accdbcb20
+size 1465

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 7.187783241271973,
+  "best_model_checkpoint": "/kaggle/working/MASRIBERTv3_ckpts/checkpoint-1000",
+  "epoch": 0.1503250779811342,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03758126949528355,
+      "grad_norm": 104.15485382080078,
+      "learning_rate": 4.680451127819549e-06,
+      "loss": 82.7376953125,
+      "step": 250
+    },
+    {
+      "epoch": 0.0751625389905671,
+      "grad_norm": 95.12043762207031,
+      "learning_rate": 9.3796992481203e-06,
+      "loss": 71.7012734375,
+      "step": 500
+    },
+    {
+      "epoch": 0.11274380848585065,
+      "grad_norm": 104.137451171875,
+      "learning_rate": 1.4078947368421053e-05,
+      "loss": 64.50540625,
+      "step": 750
+    },
+    {
+      "epoch": 0.1503250779811342,
+      "grad_norm": 100.89773559570312,
+      "learning_rate": 1.8778195488721807e-05,
+      "loss": 61.0135390625,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1503250779811342,
+      "eval_loss": 7.187783241271973,
+      "eval_runtime": 245.496,
+      "eval_samples_per_second": 70.07,
+      "eval_steps_per_second": 1.096,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 250,
+  "max_steps": 26612,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6866686140416e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b4f316695fa91258ca64377b288abdca2772303c74261f1a0379699703970df
+size 5201