fine tuned model, 0.27 loss, 2 epochs, lr 8e-6

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "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,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edae58bc94c5d872a17b71b3a719024ae2251c58582bf7a2e26c6d9b6c833379
+size 3480739801

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ae18da11e0ab25cd4f437df3c3897b4a8be1ba77977b47eb24afc16d1ab3542
+size 1740393387

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6df358c0ccc90a3be5bcbda0bb7cabed30b10e770c69335fea93e70dffed3a81
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97f4929d77fac36ce59038ac24b2b58177672a2378378deb6d0a2d2f9f6f2d2b
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8532d2d84cc94e779cfc69fb06135b67c9dc379466e028952e911a80888f97b
+size 623

special_tokens_map.json

@@ -0,0 +1,9 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "name_or_path": "microsoft/deberta-v3-large",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": 0.27896466851234436,
+  "best_model_checkpoint": "out/checkpoint-900",
+  "epoch": 0.8419083255378859,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.3386548161506653,
+      "eval_runtime": 3.4462,
+      "eval_samples_per_second": 152.924,
+      "eval_steps_per_second": 19.152,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 0.32248201966285706,
+      "eval_runtime": 3.2636,
+      "eval_samples_per_second": 161.477,
+      "eval_steps_per_second": 20.223,
+      "step": 200
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.3344081938266754,
+      "eval_runtime": 3.3846,
+      "eval_samples_per_second": 155.706,
+      "eval_steps_per_second": 19.5,
+      "step": 300
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 0.37741541862487793,
+      "eval_runtime": 3.4216,
+      "eval_samples_per_second": 154.02,
+      "eval_steps_per_second": 19.289,
+      "step": 400
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 6.9799095266062985e-06,
+      "loss": 0.3934,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "eval_loss": 0.41931670904159546,
+      "eval_runtime": 3.2614,
+      "eval_samples_per_second": 161.586,
+      "eval_steps_per_second": 20.237,
+      "step": 500
+    },
+    {
+      "epoch": 0.56,
+      "eval_loss": 0.3693557381629944,
+      "eval_runtime": 3.2679,
+      "eval_samples_per_second": 161.266,
+      "eval_steps_per_second": 20.196,
+      "step": 600
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 0.34475621581077576,
+      "eval_runtime": 3.2639,
+      "eval_samples_per_second": 161.465,
+      "eval_steps_per_second": 20.221,
+      "step": 700
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.34064173698425293,
+      "eval_runtime": 3.2698,
+      "eval_samples_per_second": 161.174,
+      "eval_steps_per_second": 20.185,
+      "step": 800
+    },
+    {
+      "epoch": 0.84,
+      "eval_loss": 0.27896466851234436,
+      "eval_runtime": 3.2598,
+      "eval_samples_per_second": 161.668,
+      "eval_steps_per_second": 20.247,
+      "step": 900
+    }
+  ],
+  "max_steps": 2138,
+  "num_train_epochs": 2,
+  "total_flos": 148483879153632.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:934cd1d9a31a28c5e806831d0e6a9fc0d67bd1870f4d899d5089c72b5e38f970
+size 3247