Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae5c280bcf18b30e319e9cd122232051272fd040514d0737d5316c6eab38d509
+oid sha256:67394bf326e0c0d4a3526741c7a812383711e307ea0b8dd5d67441ba6bcfc075
 size 737719272

run-2/checkpoint-28/added_tokens.json

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

run-2/checkpoint-28/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

run-2/checkpoint-28/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c21b324ea4182d8123cfa36b24cb61c1afabdbf19eb97ce5bd4d01fd6f0ce4
+size 737719272

run-2/checkpoint-28/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49de6c2425b9bee3db271c09ad1a2c2d37ac4ab12707cb1363906018de2826ca
+size 1475558394

run-2/checkpoint-28/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c392f5d2a6a07a95b446e842cfd4c8c5c41a7030a28c1870e536a04ca0d252df
+size 14244

run-2/checkpoint-28/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d45572000e9fd878d04619fde215df00261b65c41fa889d3b38da0dee880f32d
+size 1064

run-2/checkpoint-28/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-2/checkpoint-28/spm.model

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

run-2/checkpoint-28/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

run-2/checkpoint-28/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": 0.5373623427702773,
+  "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-2/checkpoint-28",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 28,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5380865335464478,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.528,
+      "eval_samples_per_second": 412.584,
+      "eval_steps_per_second": 26.108,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.450260192155838,
+      "eval_matthews_correlation": 0.5373623427702773,
+      "eval_runtime": 2.6414,
+      "eval_samples_per_second": 394.87,
+      "eval_steps_per_second": 24.987,
+      "step": 28
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 28,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.62287589751255e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 32,
+    "seed": 19
+  }
+}

run-2/checkpoint-28/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90d2310c03506d61913d05e2ce8d8d5e390c79fa41362e0dc007ab445a40532d
+size 4984

run-3/checkpoint-107/added_tokens.json

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

run-3/checkpoint-107/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

run-3/checkpoint-107/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67394bf326e0c0d4a3526741c7a812383711e307ea0b8dd5d67441ba6bcfc075
+size 737719272

run-3/checkpoint-107/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e595c43832c1d65ec81820d9f7741fdccd4e04d89d04ce3552ed1d984ff215d
+size 1475558394

run-3/checkpoint-107/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32ec2547f4139a81075749df2412ebd63f29f506a01b2d6fcc4b2fa1d2a610f9
+size 14308

run-3/checkpoint-107/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e5deee4632d4a977ccb779620d17198045f7d6bb95b7353d19fe3701313b801
+size 1064

run-3/checkpoint-107/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-3/checkpoint-107/spm.model

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

run-3/checkpoint-107/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

run-3/checkpoint-107/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-3/checkpoint-107",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 107,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6721658110618591,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.5775,
+      "eval_samples_per_second": 404.657,
+      "eval_steps_per_second": 25.606,
+      "step": 107
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 107,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.9667504968658146e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 24
+  }
+}

run-3/checkpoint-107/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1356e6d925e3c6944af7bc8c06e2f74b8c28da04053da0dc529ebdb8c576da0b
+size 4984

runs/Feb29_12-55-06_e1aa4b7a2e4c/events.out.tfevents.1709211772.e1aa4b7a2e4c.252.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b38ecc16be378abc26bdcf9ccc59562933d974d029b4afca896a2efd0b6a1f84
+size 5483

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90d2310c03506d61913d05e2ce8d8d5e390c79fa41362e0dc007ab445a40532d
+oid sha256:1356e6d925e3c6944af7bc8c06e2f74b8c28da04053da0dc529ebdb8c576da0b
 size 4984