Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41bee6aa79e953bf3187cbe2796dff33de1a8aedf6a6269a727ed170d54d5655
+size 711443456

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f925079ee585aa491e1a3ce2c5cbd6a4b32f752a71938b8c8c8c1894933cfa5a
+size 1423007994

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6450b213664c6e53e8b072bfbd830445a60b8c83ca647602edf469d54ba6517
+size 15984

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c57e7c6ecc3d66d06c23a09f67cffe47d38f9b7155a8251e3754aaf74be764
+size 15984

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:241a95ba9bca127c11fa9732a46cfebaa63af1b7be243fd5e10c6d720e566a69
+size 15984

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:740808d9180036fb71203c76152ae82e00f83c039b571ed2bfba99f0feba58c4
+size 15984

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45cc54c14b7e517761eb2e7961be88d2163bb7514a15cea8e30fef21ad2dacab
+size 15984

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59202df8b936ff9e5869bd057a7d7dd9c9f78c99741f587c1813b7c4a8221226
+size 15984

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b64b17553ea355122562c16efe67917ec5df03c1a7844c5523ac836ca096a55
+size 15984

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92158573da24fb668ab4bf1ecb0ee053dd90490e6c5c8eba3004b600c963c19c
+size 15984

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f784a342e7c6f1e9a1df73a7e755829ad13fb28984e510cf8277b88dcc412c4d
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,116 @@
+{
+  "best_metric": 0.7404627946070191,
+  "best_model_checkpoint": "checkpoint/cross_encoder_20250522_full_data/checkpoint-2317",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2317,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.9638161659240723,
+      "learning_rate": 4.315925766076824e-09,
+      "loss": 0.6827,
+      "step": 1
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.8890857696533203,
+      "learning_rate": 8.631851532153649e-07,
+      "loss": 0.6745,
+      "step": 200
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 2.8610997200012207,
+      "learning_rate": 1.7263703064307298e-06,
+      "loss": 0.5921,
+      "step": 400
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 4.058478832244873,
+      "learning_rate": 2.5895554596460943e-06,
+      "loss": 0.5238,
+      "step": 600
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 2.51100492477417,
+      "learning_rate": 3.4527406128614595e-06,
+      "loss": 0.4943,
+      "step": 800
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 3.381241798400879,
+      "learning_rate": 4.3159257660768235e-06,
+      "loss": 0.4882,
+      "step": 1000
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 3.5782713890075684,
+      "learning_rate": 5.179110919292189e-06,
+      "loss": 0.4782,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 5.436559200286865,
+      "learning_rate": 6.042296072507553e-06,
+      "loss": 0.4719,
+      "step": 1400
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 2.6600098609924316,
+      "learning_rate": 6.905481225722919e-06,
+      "loss": 0.4593,
+      "step": 1600
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 4.711264610290527,
+      "learning_rate": 7.768666378938283e-06,
+      "loss": 0.4629,
+      "step": 1800
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 7.427570819854736,
+      "learning_rate": 8.631851532153647e-06,
+      "loss": 0.4549,
+      "step": 2000
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 2.386420965194702,
+      "learning_rate": 9.495036685369013e-06,
+      "loss": 0.4572,
+      "step": 2200
+    },
+    {
+      "epoch": 1.0,
+      "eval_f2": 0.7404627946070191,
+      "eval_loss": 0.4705376923084259,
+      "eval_precision": 0.47348360206208184,
+      "eval_recall": 0.8619708466453674,
+      "eval_runtime": 147.2641,
+      "eval_samples_per_second": 816.166,
+      "eval_steps_per_second": 6.376,
+      "step": 2317
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 23170,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 7.80324253508567e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc931ca29050915c36f13d6eefa6efb4cca44f2f3756faa2eeed66e1b2bfd1b
+size 5112