Training in progress, step 100, checkpoint

checkpoint-100/config.json

@@ -0,0 +1,45 @@
+{
+  "_name_or_path": "Fsoft-AIC/videberta-base",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_head_size": 64,
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "false",
+    "1": "true"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "false": 0,
+    "true": 1
+  },
+  "layer_norm_eps": 1e-07,
+  "max_length": 1024,
+  "max_position_embeddings": 1024,
+  "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": "4.35.0.dev0",
+  "type_vocab_size": 0,
+  "vocab_size": 128000
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5491a0824530dec47cb07220710b0601b529e9ddced52cbf5544d20c174cffa5
+size 1474893317

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87dc666d791b70d0b57db4629ac9efe213e28a520b2bd6548c5b459963c5c6bd
+size 737457141

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aebc89d9a4ce02e53aee842590f82f8f229e89ca133bac16af3555cce82797d6
+size 14575

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:718fea3db5480c69e3c4b26e7aa63c3520ea40839d5d4f7825006197054d1cc3
+size 627

checkpoint-100/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]"
+}

checkpoint-100/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": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "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"
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": 0.5684965252876282,
+  "best_model_checkpoint": "/kaggle/output/checkpoint-100",
+  "epoch": 0.2066115702479339,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.777777777777778e-07,
+      "loss": 0.664,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5625454783439636,
+      "eval_runtime": 28.0598,
+      "eval_samples_per_second": 42.196,
+      "eval_steps_per_second": 21.098,
+      "step": 50
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5684965252876282,
+      "eval_runtime": 27.869,
+      "eval_samples_per_second": 42.485,
+      "eval_steps_per_second": 21.242,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 1000,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 314860163169240.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:359ac16579635edbe192e2a03146d3aa8c5fab4b7a991e049fba5f7b90d4807f
+size 4027