Add files using upload-large-folder tool

checkpoint-100/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f51d528395b42388dcf0f534a6207a3f034d9b525416bc64b6f057902621c2f
+size 1740304440

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16e8aade09a90a40d007fa0bf00e1f86baea350c6f8ae65f4231eb9f856cfc06
+size 14180

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d03bee491405f0804b15413c0e0b0f995c7932728fecb4f1497314d356e6f1
+size 988

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc47c48cefa8582e9f5b6467027e7c306fdb33d55aa6a5a0b6c234dffed881d2
+size 1064

checkpoint-100/trainer_state.json

@@ -0,0 +1,56 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.064,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 25.09992027282715,
+      "learning_rate": 4.3999999999999997e-07,
+      "loss": 1.0546456146240235,
+      "step": 50
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 44.00643539428711,
+      "learning_rate": 9.399999999999999e-07,
+      "loss": 1.2045201873779297,
+      "step": 100
+    },
+    {
+      "epoch": 0.064,
+      "eval_loss": 0.15259136259555817,
+      "eval_runtime": 320.8429,
+      "eval_samples_per_second": 6.234,
+      "eval_steps_per_second": 1.558,
+      "step": 100
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5953567215380736.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da6e2a61b6bad49c09f23bbfa4f7ef9e3d7901027f4ad3d2b43105b61dd0d2d
+size 4792

checkpoint-200/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

checkpoint-200/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c2bc389a960d9dfdc929377e92c852281b996f497d8e85f7b6d92256e1d3fcc
+size 1740304440

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93a692cbb9fef17013b112e00e851a326507eef7fd870ba2bf3d5761da4b8273
+size 14180

checkpoint-200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4d7eaa4548eb89bb14ef8ad634f33429d7875bdc4c1591b441fcb5c0f78db3b
+size 988

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124cf7a8b9959cc2e7286d1ca0fbfbdf1fd78046ddd7b8b0be8872a62c701348
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,78 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.128,
+  "eval_steps": 100,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 25.09992027282715,
+      "learning_rate": 4.3999999999999997e-07,
+      "loss": 1.0546456146240235,
+      "step": 50
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 44.00643539428711,
+      "learning_rate": 9.399999999999999e-07,
+      "loss": 1.2045201873779297,
+      "step": 100
+    },
+    {
+      "epoch": 0.064,
+      "eval_loss": 0.15259136259555817,
+      "eval_runtime": 320.8429,
+      "eval_samples_per_second": 6.234,
+      "eval_steps_per_second": 1.558,
+      "step": 100
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 409.5372314453125,
+      "learning_rate": 9.511111111111111e-07,
+      "loss": 0.8091524505615234,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 4.935479640960693,
+      "learning_rate": 8.955555555555555e-07,
+      "loss": 0.9019821166992188,
+      "step": 200
+    },
+    {
+      "epoch": 0.128,
+      "eval_loss": 0.1397811472415924,
+      "eval_runtime": 320.5384,
+      "eval_samples_per_second": 6.24,
+      "eval_steps_per_second": 1.56,
+      "step": 200
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.190401098346536e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da6e2a61b6bad49c09f23bbfa4f7ef9e3d7901027f4ad3d2b43105b61dd0d2d
+size 4792

checkpoint-300/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

checkpoint-300/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e24387fdd245e292c16e2b79803483885069d736df1c42229dc489b2e3e761d
+size 1740304440

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f8d5624bd5068f2c5182c44c3fa271efb8419e50bcd1658bc28380f8fbfc352
+size 14180

checkpoint-300/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0032c98d04d71a11fda8b214fed42c7a7511d08bee284b55a738a2ecde039e2
+size 988

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1eb1ac6c98e1509a604f888f2e6f28bea80c725fcfd59330e3be3591813644b
+size 1064

checkpoint-300/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.192,
+  "eval_steps": 100,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 25.09992027282715,
+      "learning_rate": 4.3999999999999997e-07,
+      "loss": 1.0546456146240235,
+      "step": 50
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 44.00643539428711,
+      "learning_rate": 9.399999999999999e-07,
+      "loss": 1.2045201873779297,
+      "step": 100
+    },
+    {
+      "epoch": 0.064,
+      "eval_loss": 0.15259136259555817,
+      "eval_runtime": 320.8429,
+      "eval_samples_per_second": 6.234,
+      "eval_steps_per_second": 1.558,
+      "step": 100
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 409.5372314453125,
+      "learning_rate": 9.511111111111111e-07,
+      "loss": 0.8091524505615234,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 4.935479640960693,
+      "learning_rate": 8.955555555555555e-07,
+      "loss": 0.9019821166992188,
+      "step": 200
+    },
+    {
+      "epoch": 0.128,
+      "eval_loss": 0.1397811472415924,
+      "eval_runtime": 320.5384,
+      "eval_samples_per_second": 6.24,
+      "eval_steps_per_second": 1.56,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.68009877204895,
+      "learning_rate": 8.399999999999999e-07,
+      "loss": 0.8488493347167969,
+      "step": 250
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 250.0933380126953,
+      "learning_rate": 7.844444444444445e-07,
+      "loss": 0.8013427734375,
+      "step": 300
+    },
+    {
+      "epoch": 0.192,
+      "eval_loss": 0.13730598986148834,
+      "eval_runtime": 320.7296,
+      "eval_samples_per_second": 6.236,
+      "eval_steps_per_second": 1.559,
+      "step": 300
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7856631699665456e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da6e2a61b6bad49c09f23bbfa4f7ef9e3d7901027f4ad3d2b43105b61dd0d2d
+size 4792

checkpoint-400/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

checkpoint-400/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e510ff1c0d0b2a753b89342d15a84f3c8e0cb3518e9404ecf61a398d49072d42
+size 1740304440

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60324b2bab14319d4ed37f75c3ee04f669d54ee031664e663eda54c1034ebe85
+size 14180

checkpoint-400/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48f0fed3631545d5c0ac4432b6dc265c750aca3e8a89b3b4268785b1b87056f
+size 988

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8aa5b842d19939b9a7b1b29463530ead81aff748b3c7f3cc968c174806c2a57
+size 1064

checkpoint-400/trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.256,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 25.09992027282715,
+      "learning_rate": 4.3999999999999997e-07,
+      "loss": 1.0546456146240235,
+      "step": 50
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 44.00643539428711,
+      "learning_rate": 9.399999999999999e-07,
+      "loss": 1.2045201873779297,
+      "step": 100
+    },
+    {
+      "epoch": 0.064,
+      "eval_loss": 0.15259136259555817,
+      "eval_runtime": 320.8429,
+      "eval_samples_per_second": 6.234,
+      "eval_steps_per_second": 1.558,
+      "step": 100
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 409.5372314453125,
+      "learning_rate": 9.511111111111111e-07,
+      "loss": 0.8091524505615234,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 4.935479640960693,
+      "learning_rate": 8.955555555555555e-07,
+      "loss": 0.9019821166992188,
+      "step": 200
+    },
+    {
+      "epoch": 0.128,
+      "eval_loss": 0.1397811472415924,
+      "eval_runtime": 320.5384,
+      "eval_samples_per_second": 6.24,
+      "eval_steps_per_second": 1.56,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.68009877204895,
+      "learning_rate": 8.399999999999999e-07,
+      "loss": 0.8488493347167969,
+      "step": 250
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 250.0933380126953,
+      "learning_rate": 7.844444444444445e-07,
+      "loss": 0.8013427734375,
+      "step": 300
+    },
+    {
+      "epoch": 0.192,
+      "eval_loss": 0.13730598986148834,
+      "eval_runtime": 320.7296,
+      "eval_samples_per_second": 6.236,
+      "eval_steps_per_second": 1.559,
+      "step": 300
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 3.164937973022461,
+      "learning_rate": 7.288888888888889e-07,
+      "loss": 0.6347025299072265,
+      "step": 350
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 120.01831817626953,
+      "learning_rate": 6.733333333333333e-07,
+      "loss": 0.960202407836914,
+      "step": 400
+    },
+    {
+      "epoch": 0.256,
+      "eval_loss": 0.12297496199607849,
+      "eval_runtime": 320.4414,
+      "eval_samples_per_second": 6.241,
+      "eval_steps_per_second": 1.56,
+      "step": 400
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3807672490310176e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da6e2a61b6bad49c09f23bbfa4f7ef9e3d7901027f4ad3d2b43105b61dd0d2d
+size 4792

checkpoint-500/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41840a20abd987e0a6f2d9e2278dce7fa2bec86b10a4485b396d4f6d5555f48
+size 1740304440

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e810d6ba6cd35e38138346e80dc488127ed759e6e40299ba97798ee34c783af
+size 2271441914

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40e6457e5a15e10eebea51ab9d0765297dafb5eadc657de5b57d3781d638deaf
+size 14180

checkpoint-500/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:626829538aca7940353b7f46f08c3f43239373a2e67000f06460ca4c197f4065
+size 988

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:215e94693570a82dbed7af5f4f9cffa462ea8649a10019126b61ab63c5495e59
+size 1064

checkpoint-500/trainer_state.json

@@ -0,0 +1,144 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.32,
+  "eval_steps": 100,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 25.09992027282715,
+      "learning_rate": 4.3999999999999997e-07,
+      "loss": 1.0546456146240235,
+      "step": 50
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 44.00643539428711,
+      "learning_rate": 9.399999999999999e-07,
+      "loss": 1.2045201873779297,
+      "step": 100
+    },
+    {
+      "epoch": 0.064,
+      "eval_loss": 0.15259136259555817,
+      "eval_runtime": 320.8429,
+      "eval_samples_per_second": 6.234,
+      "eval_steps_per_second": 1.558,
+      "step": 100
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 409.5372314453125,
+      "learning_rate": 9.511111111111111e-07,
+      "loss": 0.8091524505615234,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 4.935479640960693,
+      "learning_rate": 8.955555555555555e-07,
+      "loss": 0.9019821166992188,
+      "step": 200
+    },
+    {
+      "epoch": 0.128,
+      "eval_loss": 0.1397811472415924,
+      "eval_runtime": 320.5384,
+      "eval_samples_per_second": 6.24,
+      "eval_steps_per_second": 1.56,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.68009877204895,
+      "learning_rate": 8.399999999999999e-07,
+      "loss": 0.8488493347167969,
+      "step": 250
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 250.0933380126953,
+      "learning_rate": 7.844444444444445e-07,
+      "loss": 0.8013427734375,
+      "step": 300
+    },
+    {
+      "epoch": 0.192,
+      "eval_loss": 0.13730598986148834,
+      "eval_runtime": 320.7296,
+      "eval_samples_per_second": 6.236,
+      "eval_steps_per_second": 1.559,
+      "step": 300
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 3.164937973022461,
+      "learning_rate": 7.288888888888889e-07,
+      "loss": 0.6347025299072265,
+      "step": 350
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 120.01831817626953,
+      "learning_rate": 6.733333333333333e-07,
+      "loss": 0.960202407836914,
+      "step": 400
+    },
+    {
+      "epoch": 0.256,
+      "eval_loss": 0.12297496199607849,
+      "eval_runtime": 320.4414,
+      "eval_samples_per_second": 6.241,
+      "eval_steps_per_second": 1.56,
+      "step": 400
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 25.20623779296875,
+      "learning_rate": 6.177777777777777e-07,
+      "loss": 0.7631096649169922,
+      "step": 450
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 124.12076568603516,
+      "learning_rate": 5.622222222222222e-07,
+      "loss": 0.9197311401367188,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.13506844639778137,
+      "eval_runtime": 320.4909,
+      "eval_samples_per_second": 6.24,
+      "eval_steps_per_second": 1.56,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.975877152705832e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da6e2a61b6bad49c09f23bbfa4f7ef9e3d7901027f4ad3d2b43105b61dd0d2d
+size 4792

checkpoint-600/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

checkpoint-600/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18988f5ea942fa89e4a092078c8b3f3fbeb3856f07493d528ec810d7f838251e
+size 1740304440

checkpoint-600/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56a2fdf431c074b4cb70dda7a139d6d8a19ae50eba8f1bd05ac3e3177e25c88e
+size 14180

checkpoint-600/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcb65f7c732b29824f760066581ac9307df8061d26977f3ff63f0632ff073692
+size 988

checkpoint-600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1da014bf8a42665ddf5c484720cbba2070f1a3afe5db34d484a965add48bd2d9
+size 1064

checkpoint-600/trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.384,
+  "eval_steps": 100,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 25.09992027282715,
+      "learning_rate": 4.3999999999999997e-07,
+      "loss": 1.0546456146240235,
+      "step": 50
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 44.00643539428711,
+      "learning_rate": 9.399999999999999e-07,
+      "loss": 1.2045201873779297,
+      "step": 100
+    },
+    {
+      "epoch": 0.064,
+      "eval_loss": 0.15259136259555817,
+      "eval_runtime": 320.8429,
+      "eval_samples_per_second": 6.234,
+      "eval_steps_per_second": 1.558,
+      "step": 100
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 409.5372314453125,
+      "learning_rate": 9.511111111111111e-07,
+      "loss": 0.8091524505615234,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 4.935479640960693,
+      "learning_rate": 8.955555555555555e-07,
+      "loss": 0.9019821166992188,
+      "step": 200
+    },
+    {
+      "epoch": 0.128,
+      "eval_loss": 0.1397811472415924,
+      "eval_runtime": 320.5384,
+      "eval_samples_per_second": 6.24,
+      "eval_steps_per_second": 1.56,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.68009877204895,
+      "learning_rate": 8.399999999999999e-07,
+      "loss": 0.8488493347167969,
+      "step": 250
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 250.0933380126953,
+      "learning_rate": 7.844444444444445e-07,
+      "loss": 0.8013427734375,
+      "step": 300
+    },
+    {
+      "epoch": 0.192,
+      "eval_loss": 0.13730598986148834,
+      "eval_runtime": 320.7296,
+      "eval_samples_per_second": 6.236,
+      "eval_steps_per_second": 1.559,
+      "step": 300
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 3.164937973022461,
+      "learning_rate": 7.288888888888889e-07,
+      "loss": 0.6347025299072265,
+      "step": 350
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 120.01831817626953,
+      "learning_rate": 6.733333333333333e-07,
+      "loss": 0.960202407836914,
+      "step": 400
+    },
+    {
+      "epoch": 0.256,
+      "eval_loss": 0.12297496199607849,
+      "eval_runtime": 320.4414,
+      "eval_samples_per_second": 6.241,
+      "eval_steps_per_second": 1.56,
+      "step": 400
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 25.20623779296875,
+      "learning_rate": 6.177777777777777e-07,
+      "loss": 0.7631096649169922,
+      "step": 450
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 124.12076568603516,
+      "learning_rate": 5.622222222222222e-07,
+      "loss": 0.9197311401367188,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.13506844639778137,
+      "eval_runtime": 320.4909,
+      "eval_samples_per_second": 6.24,
+      "eval_steps_per_second": 1.56,
+      "step": 500
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 24.420225143432617,
+      "learning_rate": 5.066666666666667e-07,
+      "loss": 0.7606878662109375,
+      "step": 550
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 354.97039794921875,
+      "learning_rate": 4.511111111111111e-07,
+      "loss": 0.7917160034179688,
+      "step": 600
+    },
+    {
+      "epoch": 0.384,
+      "eval_loss": 0.14342211186885834,
+      "eval_runtime": 313.4668,
+      "eval_samples_per_second": 6.38,
+      "eval_steps_per_second": 1.595,
+      "step": 600
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.570791931934176e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da6e2a61b6bad49c09f23bbfa4f7ef9e3d7901027f4ad3d2b43105b61dd0d2d
+size 4792

checkpoint-700/config.json

@@ -0,0 +1,39 @@
+{
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "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,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.12.1",
+  "type_vocab_size": 0,
+  "use_cache": false,
+  "vocab_size": 128100
+}

checkpoint-700/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f272bca2fa45d8eab2903f6dd5c65ba31069d1a44a84bc417cdf35e496b8b80c
+size 1740304440

checkpoint-700/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aab418b245eac4a8b791f07c97230ee4c7b673a4eb8a04cdc2c305af309cbef
+size 14180

checkpoint-700/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c0398359e885f2196fa72ee4be475e75de50479bda2cff1b0c6825b4ce37ea
+size 988

checkpoint-700/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06591d16f9a758f81bbcc69f12ba25035d86ebc49b91e73ab92a526cbf9d1d89
+size 1064

checkpoint-700/trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.448,
+  "eval_steps": 100,
+  "global_step": 700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.032,
+      "grad_norm": 25.09992027282715,
+      "learning_rate": 4.3999999999999997e-07,
+      "loss": 1.0546456146240235,
+      "step": 50
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 44.00643539428711,
+      "learning_rate": 9.399999999999999e-07,
+      "loss": 1.2045201873779297,
+      "step": 100
+    },
+    {
+      "epoch": 0.064,
+      "eval_loss": 0.15259136259555817,
+      "eval_runtime": 320.8429,
+      "eval_samples_per_second": 6.234,
+      "eval_steps_per_second": 1.558,
+      "step": 100
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 409.5372314453125,
+      "learning_rate": 9.511111111111111e-07,
+      "loss": 0.8091524505615234,
+      "step": 150
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 4.935479640960693,
+      "learning_rate": 8.955555555555555e-07,
+      "loss": 0.9019821166992188,
+      "step": 200
+    },
+    {
+      "epoch": 0.128,
+      "eval_loss": 0.1397811472415924,
+      "eval_runtime": 320.5384,
+      "eval_samples_per_second": 6.24,
+      "eval_steps_per_second": 1.56,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.68009877204895,
+      "learning_rate": 8.399999999999999e-07,
+      "loss": 0.8488493347167969,
+      "step": 250
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 250.0933380126953,
+      "learning_rate": 7.844444444444445e-07,
+      "loss": 0.8013427734375,
+      "step": 300
+    },
+    {
+      "epoch": 0.192,
+      "eval_loss": 0.13730598986148834,
+      "eval_runtime": 320.7296,
+      "eval_samples_per_second": 6.236,
+      "eval_steps_per_second": 1.559,
+      "step": 300
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 3.164937973022461,
+      "learning_rate": 7.288888888888889e-07,
+      "loss": 0.6347025299072265,
+      "step": 350
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 120.01831817626953,
+      "learning_rate": 6.733333333333333e-07,
+      "loss": 0.960202407836914,
+      "step": 400
+    },
+    {
+      "epoch": 0.256,
+      "eval_loss": 0.12297496199607849,
+      "eval_runtime": 320.4414,
+      "eval_samples_per_second": 6.241,
+      "eval_steps_per_second": 1.56,
+      "step": 400
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 25.20623779296875,
+      "learning_rate": 6.177777777777777e-07,
+      "loss": 0.7631096649169922,
+      "step": 450
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 124.12076568603516,
+      "learning_rate": 5.622222222222222e-07,
+      "loss": 0.9197311401367188,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.13506844639778137,
+      "eval_runtime": 320.4909,
+      "eval_samples_per_second": 6.24,
+      "eval_steps_per_second": 1.56,
+      "step": 500
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 24.420225143432617,
+      "learning_rate": 5.066666666666667e-07,
+      "loss": 0.7606878662109375,
+      "step": 550
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 354.97039794921875,
+      "learning_rate": 4.511111111111111e-07,
+      "loss": 0.7917160034179688,
+      "step": 600
+    },
+    {
+      "epoch": 0.384,
+      "eval_loss": 0.14342211186885834,
+      "eval_runtime": 313.4668,
+      "eval_samples_per_second": 6.38,
+      "eval_steps_per_second": 1.595,
+      "step": 600
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 10.307374000549316,
+      "learning_rate": 3.955555555555555e-07,
+      "loss": 0.7462944030761719,
+      "step": 650
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 318.738525390625,
+      "learning_rate": 3.4000000000000003e-07,
+      "loss": 0.7443762969970703,
+      "step": 700
+    },
+    {
+      "epoch": 0.448,
+      "eval_loss": 0.11785667389631271,
+      "eval_runtime": 320.2436,
+      "eval_samples_per_second": 6.245,
+      "eval_steps_per_second": 1.561,
+      "step": 700
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.16536597145749e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-700/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3da6e2a61b6bad49c09f23bbfa4f7ef9e3d7901027f4ad3d2b43105b61dd0d2d
+size 4792