Upload 7 files

DeBERTa_table_random-table_2e-7/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "naver/trecdl22-crossencoder-debertav3",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1024,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "single_label_classification",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.43.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

DeBERTa_table_random-table_2e-7/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:144edbdfa0c65c1a7a4aa98b0c06e0974dc291248357c722d06976daae78c4a3
+size 1740300340

DeBERTa_table_random-table_2e-7/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0fa4b0e080f5d8f3fa6cb8deb853e396e9f2ea5d8c4cf863bea280f09c423ff
+size 3480832048

DeBERTa_table_random-table_2e-7/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e64671cf5074351759e8cf424571061c026fe485581c166823476662318618
+size 14244

DeBERTa_table_random-table_2e-7/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a7a2d2062e410384b6fbcd4c5a207f00c539b742235a3405178e77349186958
+size 1064

DeBERTa_table_random-table_2e-7/trainer_state.json

@@ -0,0 +1,253 @@
+{
+  "best_metric": 0.06389161199331284,
+  "best_model_checkpoint": "finqa_models/training_naver-trecdl22-crossencoder-debertav3_2024-11-17_17-26-51/checkpoint-14424",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 14424,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10399334442595674,
+      "grad_norm": 0.12019415944814682,
+      "learning_rate": 1.9310870770937327e-07,
+      "loss": 0.1965,
+      "step": 500
+    },
+    {
+      "epoch": 0.2079866888519135,
+      "grad_norm": 6.474766254425049,
+      "learning_rate": 1.8618968386023294e-07,
+      "loss": 0.1351,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3119800332778702,
+      "grad_norm": 23.737518310546875,
+      "learning_rate": 1.7925679423183582e-07,
+      "loss": 0.1353,
+      "step": 1500
+    },
+    {
+      "epoch": 0.415973377703827,
+      "grad_norm": 0.015338932164013386,
+      "learning_rate": 1.723239046034387e-07,
+      "loss": 0.1414,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5199667221297837,
+      "grad_norm": 0.05833850055932999,
+      "learning_rate": 1.653910149750416e-07,
+      "loss": 0.1432,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6239600665557404,
+      "grad_norm": 37.305580139160156,
+      "learning_rate": 1.5845812534664445e-07,
+      "loss": 0.1155,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7279534109816972,
+      "grad_norm": 0.431114137172699,
+      "learning_rate": 1.5153910149750415e-07,
+      "loss": 0.1299,
+      "step": 3500
+    },
+    {
+      "epoch": 0.831946755407654,
+      "grad_norm": 0.022228846326470375,
+      "learning_rate": 1.4460621186910704e-07,
+      "loss": 0.116,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9359400998336106,
+      "grad_norm": 9.204265594482422,
+      "learning_rate": 1.3767332224070992e-07,
+      "loss": 0.0917,
+      "step": 4500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.06588456779718399,
+      "eval_runtime": 6590.3071,
+      "eval_samples_per_second": 84.805,
+      "eval_steps_per_second": 5.3,
+      "step": 4808
+    },
+    {
+      "epoch": 1.0399334442595674,
+      "grad_norm": 44.67750549316406,
+      "learning_rate": 1.307404326123128e-07,
+      "loss": 0.1156,
+      "step": 5000
+    },
+    {
+      "epoch": 1.1439267886855242,
+      "grad_norm": 0.012149451300501823,
+      "learning_rate": 1.2382140876317248e-07,
+      "loss": 0.0982,
+      "step": 5500
+    },
+    {
+      "epoch": 1.2479201331114809,
+      "grad_norm": 1.34881591796875,
+      "learning_rate": 1.1688851913477538e-07,
+      "loss": 0.1059,
+      "step": 6000
+    },
+    {
+      "epoch": 1.3519134775374377,
+      "grad_norm": 0.14894534647464752,
+      "learning_rate": 1.0996949528563504e-07,
+      "loss": 0.1085,
+      "step": 6500
+    },
+    {
+      "epoch": 1.4559068219633944,
+      "grad_norm": 0.004204815719276667,
+      "learning_rate": 1.0303660565723793e-07,
+      "loss": 0.0949,
+      "step": 7000
+    },
+    {
+      "epoch": 1.559900166389351,
+      "grad_norm": 0.024665243923664093,
+      "learning_rate": 9.610371602884082e-08,
+      "loss": 0.1246,
+      "step": 7500
+    },
+    {
+      "epoch": 1.6638935108153077,
+      "grad_norm": 71.5008316040039,
+      "learning_rate": 8.91708264004437e-08,
+      "loss": 0.101,
+      "step": 8000
+    },
+    {
+      "epoch": 1.7678868552412645,
+      "grad_norm": 88.50396728515625,
+      "learning_rate": 8.22379367720466e-08,
+      "loss": 0.1177,
+      "step": 8500
+    },
+    {
+      "epoch": 1.8718801996672214,
+      "grad_norm": 0.28365257382392883,
+      "learning_rate": 7.530504714364947e-08,
+      "loss": 0.0987,
+      "step": 9000
+    },
+    {
+      "epoch": 1.975873544093178,
+      "grad_norm": 25.998218536376953,
+      "learning_rate": 6.838602329450914e-08,
+      "loss": 0.1001,
+      "step": 9500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.06637805700302124,
+      "eval_runtime": 6587.2735,
+      "eval_samples_per_second": 84.844,
+      "eval_steps_per_second": 5.303,
+      "step": 9616
+    },
+    {
+      "epoch": 2.0798668885191347,
+      "grad_norm": 59.35243225097656,
+      "learning_rate": 6.145313366611204e-08,
+      "loss": 0.0962,
+      "step": 10000
+    },
+    {
+      "epoch": 2.1838602329450914,
+      "grad_norm": 0.29308849573135376,
+      "learning_rate": 5.4520244037714916e-08,
+      "loss": 0.082,
+      "step": 10500
+    },
+    {
+      "epoch": 2.2878535773710484,
+      "grad_norm": 1.2921684980392456,
+      "learning_rate": 4.75873544093178e-08,
+      "loss": 0.102,
+      "step": 11000
+    },
+    {
+      "epoch": 2.391846921797005,
+      "grad_norm": 0.1976485699415207,
+      "learning_rate": 4.0654464780920686e-08,
+      "loss": 0.0869,
+      "step": 11500
+    },
+    {
+      "epoch": 2.4958402662229617,
+      "grad_norm": 0.0572974793612957,
+      "learning_rate": 3.373544093178036e-08,
+      "loss": 0.0971,
+      "step": 12000
+    },
+    {
+      "epoch": 2.5998336106489184,
+      "grad_norm": 0.030522992834448814,
+      "learning_rate": 2.6802551303383248e-08,
+      "loss": 0.1078,
+      "step": 12500
+    },
+    {
+      "epoch": 2.7038269550748755,
+      "grad_norm": 9.981757164001465,
+      "learning_rate": 1.9869661674986133e-08,
+      "loss": 0.091,
+      "step": 13000
+    },
+    {
+      "epoch": 2.8078202995008317,
+      "grad_norm": 0.05898750573396683,
+      "learning_rate": 1.2936772046589018e-08,
+      "loss": 0.0928,
+      "step": 13500
+    },
+    {
+      "epoch": 2.9118136439267888,
+      "grad_norm": 0.04275263100862503,
+      "learning_rate": 6.003882418191902e-09,
+      "loss": 0.0764,
+      "step": 14000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.06389161199331284,
+      "eval_runtime": 6582.4724,
+      "eval_samples_per_second": 84.906,
+      "eval_steps_per_second": 5.307,
+      "step": 14424
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14424,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0751821588988006e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

DeBERTa_table_random-table_2e-7/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67e6cc5135d8500f47565ed7f34764ec5cde7335763c3b50ced2e1056c312778
+size 5304