Upload 47 files

Other related trainings and config specs.
Reality: Dumping old files that may be related tbh.

v2xl new/added_tokens.json

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

v2xl new/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "microsoft/deberta-v2-xlarge",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "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": 24,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1536,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

v2xl new/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:530418a25fba745d473ef256d49a8f3cca60ef89ae3debb6381fe55f8390def2
+size 7095909461

v2xl new/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41fdfc7b911784d7dbc7dda1799ccf596dd5f714c996e63be6963589eac6dda7
+size 3548003107

v2xl new/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51eeb1baaf5f33fb8143692004df6c9d9552068e7f238321952b0945ea8ffa6a
+size 14503

v2xl new/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7dbc6ad7398c51b4230f8710686075fb7cff6597c69383b0209345fdcfba63
+size 623

v2xl new/special_tokens_map.json

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

v2xl new/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5598d5e96f339a8d980c15f9afd405a2e5e1be7db41de3ed13b0f03fac1e8c17
+size 2447305

v2xl new/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v2-xlarge", "tokenizer_class": "DebertaV2Tokenizer"}

v2xl new/trainer_state.json

@@ -0,0 +1,142 @@
+{
+  "best_metric": 0.9068051101949407,
+  "best_model_checkpoint": "./resultsv3l32/output/checkpoint-294528",
+  "epoch": 4.0,
+  "global_step": 392704,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.681694100391135e-06,
+      "loss": 0.5874,
+      "step": 25000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.363388200782269e-06,
+      "loss": 0.5086,
+      "step": 50000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.045082301173403e-06,
+      "loss": 0.48,
+      "step": 75000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9011044943248333,
+      "eval_loss": 0.47157734632492065,
+      "eval_runtime": 213.0954,
+      "eval_samples_per_second": 92.198,
+      "eval_steps_per_second": 23.051,
+      "step": 98176
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.7267764015645376e-06,
+      "loss": 0.4559,
+      "step": 100000
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 3.408470501955672e-06,
+      "loss": 0.3309,
+      "step": 125000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 3.0901646023468064e-06,
+      "loss": 0.3398,
+      "step": 150000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.77185870273794e-06,
+      "loss": 0.3382,
+      "step": 175000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9044128874637349,
+      "eval_loss": 0.5638315081596375,
+      "eval_runtime": 212.5015,
+      "eval_samples_per_second": 92.456,
+      "eval_steps_per_second": 23.115,
+      "step": 196352
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 2.4535528031290744e-06,
+      "loss": 0.3082,
+      "step": 200000
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.135246903520209e-06,
+      "loss": 0.1952,
+      "step": 225000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.816941003911343e-06,
+      "loss": 0.2029,
+      "step": 250000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.4986351043024774e-06,
+      "loss": 0.2027,
+      "step": 275000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9068051101949407,
+      "eval_loss": 0.6681745052337646,
+      "eval_runtime": 212.8042,
+      "eval_samples_per_second": 92.324,
+      "eval_steps_per_second": 23.082,
+      "step": 294528
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 1.1803292046936116e-06,
+      "loss": 0.1771,
+      "step": 300000
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 8.620233050847459e-07,
+      "loss": 0.1124,
+      "step": 325000
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 5.437174054758801e-07,
+      "loss": 0.1095,
+      "step": 350000
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 2.2541150586701436e-07,
+      "loss": 0.1038,
+      "step": 375000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9064997200590421,
+      "eval_loss": 0.7638580799102783,
+      "eval_runtime": 211.2725,
+      "eval_samples_per_second": 92.994,
+      "eval_steps_per_second": 23.25,
+      "step": 392704
+    }
+  ],
+  "max_steps": 392704,
+  "num_train_epochs": 4,
+  "total_flos": 3.755067886948521e+17,
+  "trial_name": null,
+  "trial_params": null
+}

v2xl new/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937df70044f985ff8dee511a2bc22fca38bfcadff7c2ef74fd252af4bd7e9dd2
+size 2799

v2xl/added_tokens.json

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

v2xl/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "microsoft/deberta-v2-xlarge",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "conv_act": "gelu",
+  "conv_kernel_size": 3,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "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": 24,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 1536,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

v2xl/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea3c98817c299ee60aacdebd14f4a08035dbe524378bcf64407b3e07da43d90
+size 7095909461

v2xl/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a1f786762c51cfec4d1514e2a566964637358788a892dbd9592dc4123ac1cc
+size 3548003107

v2xl/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83f2eb52ce3fdf6765605cdca2051f8bbf6ea652fc1f29b5232a2dd3f0a25408
+size 14503

v2xl/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1930bfa221eacebdb1f3b51ae8fa0d37b8a67db926a6a1c3b36f1929a2861dc1
+size 559

v2xl/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b0b995dc2f9ae2800cc5b64a6adfaccac0ce1dea781c260e20894f495b81f6f
+size 623

v2xl/special_tokens_map.json

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

v2xl/spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5598d5e96f339a8d980c15f9afd405a2e5e1be7db41de3ed13b0f03fac1e8c17
+size 2447305

v2xl/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v2-xlarge", "tokenizer_class": "DebertaV2Tokenizer"}

v2xl/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": 0.9058380414312618,
+  "best_model_checkpoint": "./resultsv2xl/output/checkpoint-294528",
+  "epoch": 3.0,
+  "global_step": 294528,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.2562126159447515e-06,
+      "loss": 0.527,
+      "step": 98176
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8983559831017458,
+      "eval_loss": 0.4922527074813843,
+      "eval_runtime": 231.3267,
+      "eval_samples_per_second": 84.932,
+      "eval_steps_per_second": 21.234,
+      "step": 98176
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.1293307712312536e-06,
+      "loss": 0.3335,
+      "step": 196352
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9027332417162925,
+      "eval_loss": 0.5514769554138184,
+      "eval_runtime": 231.2763,
+      "eval_samples_per_second": 84.95,
+      "eval_steps_per_second": 21.239,
+      "step": 196352
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.4705984338428644e-09,
+      "loss": 0.1729,
+      "step": 294528
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9058380414312618,
+      "eval_loss": 0.65480637550354,
+      "eval_runtime": 230.3593,
+      "eval_samples_per_second": 85.289,
+      "eval_steps_per_second": 21.323,
+      "step": 294528
+    }
+  ],
+  "max_steps": 294528,
+  "num_train_epochs": 3,
+  "total_flos": 2.8162430874533802e+17,
+  "trial_name": null,
+  "trial_params": null
+}

v2xl/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49fc87ca654f3e63fe7381a5b9e1d9f73d219885e1a7a116dbcf2a749c415f4b
+size 2799

v3-1 epoch/added_tokens.json

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

v3-1 epoch/config.json

@@ -0,0 +1,45 @@
+{
+  "_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,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "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": "4.13.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

v3-1 epoch/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc477f55816300ce73341afa1829884ca66d85b8ad8bf2184a39105a9e0ff0c
+size 3480748761

v3-1 epoch/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced5efa4b8b24ddeeba8b0d5884ac47af7b00aaf5fe0ea97be2a53ea418301b9
+size 1740426539

v3-1 epoch/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c72fe6cbb3a9729e8eaec990f08c6133b4ee2ddd44df6ca26274ba6bb751261
+size 14503

v3-1 epoch/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b03ed43bb905000173ec810b3d544870bb440ffcecdfbe8c5f2bdc77248135
+size 559

v3-1 epoch/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49da2828958bbc3229278c6d041c95960908ca65be2589040e4c80abbee39bde
+size 623

v3-1 epoch/special_tokens_map.json

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

v3-1 epoch/spm.model

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

v3-1 epoch/tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "split_by_punct": false, "sp_model_kwargs": {}, "vocab_type": "spm", "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "microsoft/deberta-v3-large", "tokenizer_class": "DebertaV2Tokenizer"}

v3-1 epoch/trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": 0.9100117066218761,
+  "best_model_checkpoint": "./resultsv3p2/output/checkpoint-98176",
+  "epoch": 1.0,
+  "global_step": 98176,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.1928048978707266e-06,
+      "loss": 0.4695,
+      "step": 98176
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9100117066218761,
+      "eval_loss": 0.3915119469165802,
+      "eval_runtime": 352.6229,
+      "eval_samples_per_second": 55.717,
+      "eval_steps_per_second": 13.93,
+      "step": 98176
+    }
+  ],
+  "max_steps": 196352,
+  "num_train_epochs": 2,
+  "total_flos": 4.154826179696498e+16,
+  "trial_name": null,
+  "trial_params": null
+}

v3-1 epoch/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9409407acd571c783e5eb22459059a64f9129882be790fb39c9ffdda3344fd0b
+size 2799

v3perfect/README.md

@@ -0,0 +1,77 @@
+---
+language:
+- en
+license: mit
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model-index:
+- name: mnlilearn
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE MNLI
+      type: glue
+      args: mnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.9175142392188771
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mnlilearn
+
+This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the GLUE MNLI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4103
+- Accuracy: 0.9175
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 6e-06
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Accuracy |
+|:-------------:|:-----:|:-----:|:---------------:|:--------:|
+| 0.3631        | 1.0   | 49088 | 0.3129          | 0.9130   |
+| 0.2267        | 2.0   | 98176 | 0.4157          | 0.9153   |
+
+
+### Framework versions
+
+- Transformers 4.13.0.dev0
+- Pytorch 1.10.0
+- Datasets 1.15.2.dev0
+- Tokenizers 0.10.3
+NDugar/v3-Large-mnli

v3perfect/added_tokens.json

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

v3perfect/all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9175142392188771,
+    "eval_loss": 0.41033002734184265,
+    "eval_runtime": 78.2213,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 125.695,
+    "eval_steps_per_second": 15.712,
+    "train_loss": 0.2868618026395198,
+    "train_runtime": 21298.9707,
+    "train_samples": 392702,
+    "train_samples_per_second": 36.875,
+    "train_steps_per_second": 4.609
+}

v3perfect/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-large",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "mnli",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "entailment",
+    "1": "neutral",
+    "2": "contradiction"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "contradiction": 2,
+    "entailment": 0,
+    "neutral": 1
+  },
+  "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": "4.13.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

v3perfect/eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.9175142392188771,
+    "eval_loss": 0.41033002734184265,
+    "eval_runtime": 78.2213,
+    "eval_samples": 9832,
+    "eval_samples_per_second": 125.695,
+    "eval_steps_per_second": 15.712
+}

v3perfect/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2723410e9906cee3b3636c827dcdd99e3badcb98768693a5dd20f6b4b7d8c91
+size 1740426539

v3perfect/special_tokens_map.json

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

v3perfect/spm.model

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

v3perfect/tokenizer_config.json

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

v3perfect/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.2868618026395198,
+    "train_runtime": 21298.9707,
+    "train_samples": 392702,
+    "train_samples_per_second": 36.875,
+    "train_steps_per_second": 4.609
+}

v3perfect/trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 98176,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.61,
+      "learning_rate": 4.168681083504881e-06,
+      "loss": 0.3631,
+      "step": 30000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9129903209373408,
+      "eval_loss": 0.31294044852256775,
+      "eval_runtime": 78.2833,
+      "eval_samples_per_second": 125.378,
+      "eval_steps_per_second": 15.674,
+      "step": 49088
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 2.334304873326132e-06,
+      "loss": 0.2901,
+      "step": 60000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 4.999286631473819e-07,
+      "loss": 0.2267,
+      "step": 90000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.915333672949567,
+      "eval_loss": 0.41572055220603943,
+      "eval_runtime": 78.1399,
+      "eval_samples_per_second": 125.608,
+      "eval_steps_per_second": 15.703,
+      "step": 98176
+    },
+    {
+      "epoch": 2.0,
+      "step": 98176,
+      "total_flos": 3.65975017449044e+17,
+      "train_loss": 0.2868618026395198,
+      "train_runtime": 21298.9707,
+      "train_samples_per_second": 36.875,
+      "train_steps_per_second": 4.609
+    }
+  ],
+  "max_steps": 98176,
+  "num_train_epochs": 2,
+  "total_flos": 3.65975017449044e+17,
+  "trial_name": null,
+  "trial_params": null
+}

v3perfect/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe31ac00049c414b30f35dccac26a8c9e1eb745034ce6fbe76c79bad8d698e01
+size 2799