Initial model upload

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google-bert/bert-base-multilingual-cased",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "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": "4.45.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6338438c96dbe054a39d52d16eceec29a0f612cb283f8cd9fd5da8823323517
+size 709080904

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca579e6b1b5f2b21e1220f0dc4555d25462fec1cfa13655fe74e75efd71b99e2
+size 1418232250

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9b02f0bac09a4b7716909d0b2f1735c5acd7faf7526766fa0dac91732c93ff0
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3aa0ebfb3f401274cfb3798b5939bc14f7cb17e6f4b46e96ee5e82d487f2776
+size 1064

trainer_state.json

@@ -0,0 +1,222 @@
+{
+  "best_metric": 0.0495530404150486,
+  "best_model_checkpoint": "./bert_question_answer/checkpoint-506",
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 759,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9960474308300395,
+      "grad_norm": 535022.625,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 4.5676,
+      "step": 63
+    },
+    {
+      "epoch": 0.9960474308300395,
+      "eval_loss": 1.4936771392822266,
+      "eval_runtime": 124.1238,
+      "eval_samples_per_second": 50.417,
+      "eval_steps_per_second": 0.749,
+      "step": 63
+    },
+    {
+      "epoch": 1.992094861660079,
+      "grad_norm": 169985.234375,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.5263,
+      "step": 126
+    },
+    {
+      "epoch": 1.992094861660079,
+      "eval_loss": 0.20066042244434357,
+      "eval_runtime": 123.7513,
+      "eval_samples_per_second": 50.569,
+      "eval_steps_per_second": 0.752,
+      "step": 126
+    },
+    {
+      "epoch": 2.9881422924901186,
+      "grad_norm": 111777.1484375,
+      "learning_rate": 2e-05,
+      "loss": 0.1157,
+      "step": 189
+    },
+    {
+      "epoch": 2.9881422924901186,
+      "eval_loss": 0.08579555153846741,
+      "eval_runtime": 124.3773,
+      "eval_samples_per_second": 50.315,
+      "eval_steps_per_second": 0.748,
+      "step": 189
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 48445.76953125,
+      "learning_rate": 1.8306878306878308e-05,
+      "loss": 0.0586,
+      "step": 253
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.0610487125813961,
+      "eval_runtime": 124.3926,
+      "eval_samples_per_second": 50.308,
+      "eval_steps_per_second": 0.748,
+      "step": 253
+    },
+    {
+      "epoch": 4.996047430830039,
+      "grad_norm": 95084.5546875,
+      "learning_rate": 1.6640211640211642e-05,
+      "loss": 0.0365,
+      "step": 316
+    },
+    {
+      "epoch": 4.996047430830039,
+      "eval_loss": 0.05348861962556839,
+      "eval_runtime": 124.0651,
+      "eval_samples_per_second": 50.441,
+      "eval_steps_per_second": 0.75,
+      "step": 316
+    },
+    {
+      "epoch": 5.992094861660079,
+      "grad_norm": 38486.77734375,
+      "learning_rate": 1.4973544973544975e-05,
+      "loss": 0.0261,
+      "step": 379
+    },
+    {
+      "epoch": 5.992094861660079,
+      "eval_loss": 0.053615033626556396,
+      "eval_runtime": 124.6756,
+      "eval_samples_per_second": 50.194,
+      "eval_steps_per_second": 0.746,
+      "step": 379
+    },
+    {
+      "epoch": 6.988142292490118,
+      "grad_norm": 53503.58203125,
+      "learning_rate": 1.3306878306878308e-05,
+      "loss": 0.0191,
+      "step": 442
+    },
+    {
+      "epoch": 6.988142292490118,
+      "eval_loss": 0.05153428390622139,
+      "eval_runtime": 124.176,
+      "eval_samples_per_second": 50.396,
+      "eval_steps_per_second": 0.749,
+      "step": 442
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 49217.56640625,
+      "learning_rate": 1.1613756613756614e-05,
+      "loss": 0.0149,
+      "step": 506
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.0495530404150486,
+      "eval_runtime": 124.4318,
+      "eval_samples_per_second": 50.293,
+      "eval_steps_per_second": 0.747,
+      "step": 506
+    },
+    {
+      "epoch": 8.996047430830039,
+      "grad_norm": 78619.8828125,
+      "learning_rate": 9.947089947089947e-06,
+      "loss": 0.0108,
+      "step": 569
+    },
+    {
+      "epoch": 8.996047430830039,
+      "eval_loss": 0.05309264734387398,
+      "eval_runtime": 124.173,
+      "eval_samples_per_second": 50.397,
+      "eval_steps_per_second": 0.749,
+      "step": 569
+    },
+    {
+      "epoch": 9.992094861660078,
+      "grad_norm": 68375.4375,
+      "learning_rate": 8.28042328042328e-06,
+      "loss": 0.0093,
+      "step": 632
+    },
+    {
+      "epoch": 9.992094861660078,
+      "eval_loss": 0.055722925812006,
+      "eval_runtime": 124.3567,
+      "eval_samples_per_second": 50.323,
+      "eval_steps_per_second": 0.748,
+      "step": 632
+    },
+    {
+      "epoch": 10.988142292490119,
+      "grad_norm": 52463.015625,
+      "learning_rate": 6.613756613756615e-06,
+      "loss": 0.0081,
+      "step": 695
+    },
+    {
+      "epoch": 10.988142292490119,
+      "eval_loss": 0.052927400916814804,
+      "eval_runtime": 124.2278,
+      "eval_samples_per_second": 50.375,
+      "eval_steps_per_second": 0.749,
+      "step": 695
+    },
+    {
+      "epoch": 12.0,
+      "grad_norm": 42119.37109375,
+      "learning_rate": 4.920634920634921e-06,
+      "loss": 0.0063,
+      "step": 759
+    },
+    {
+      "epoch": 12.0,
+      "eval_loss": 0.05621393024921417,
+      "eval_runtime": 124.2369,
+      "eval_samples_per_second": 50.371,
+      "eval_steps_per_second": 0.749,
+      "step": 759
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 945,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 4,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 4
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6178240952660787e+17,
+  "train_batch_size": 68,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4cd19d30c4a62dd3127d2dbe5e881cd6d4aec3b684607bf1b639ce178aa30dd
+size 5240