Training in progress, step 900, checkpoint

checkpoint-900/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-900/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7689cb9e578e6ff23c472b6b89d44ec2dc061eb80574d224770d15d48882a8b
+size 1474893573

checkpoint-900/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baa9ee16cd3de8ccdda427441b280c6d692e941eb8eaea43015b03066b176397
+size 737457141

checkpoint-900/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1c1f569431d58283f3fbc997efce4b3e16cd01ee209c1f878c91243e40de338
+size 14575

checkpoint-900/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc356ec59d335c7b0c5cd452933492e17947e07adfe349a9499875c8d3aab306
+size 627

checkpoint-900/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-900/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-900/trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "best_metric": 0.5623977184295654,
+  "best_model_checkpoint": "/kaggle/output/checkpoint-900",
+  "epoch": 1.859504132231405,
+  "eval_steps": 50,
+  "global_step": 900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.6979,
+      "step": 1
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.6723740696907043,
+      "eval_runtime": 28.903,
+      "eval_samples_per_second": 40.965,
+      "eval_steps_per_second": 20.482,
+      "step": 50
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.6272028088569641,
+      "eval_runtime": 28.756,
+      "eval_samples_per_second": 41.174,
+      "eval_steps_per_second": 20.587,
+      "step": 100
+    },
+    {
+      "epoch": 0.31,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5726658701896667,
+      "eval_runtime": 28.7791,
+      "eval_samples_per_second": 41.141,
+      "eval_steps_per_second": 20.57,
+      "step": 150
+    },
+    {
+      "epoch": 0.41,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5658872723579407,
+      "eval_runtime": 28.8005,
+      "eval_samples_per_second": 41.11,
+      "eval_steps_per_second": 20.555,
+      "step": 200
+    },
+    {
+      "epoch": 0.52,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5675005316734314,
+      "eval_runtime": 28.7479,
+      "eval_samples_per_second": 41.186,
+      "eval_steps_per_second": 20.593,
+      "step": 250
+    },
+    {
+      "epoch": 0.62,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5632852911949158,
+      "eval_runtime": 28.807,
+      "eval_samples_per_second": 41.101,
+      "eval_steps_per_second": 20.551,
+      "step": 300
+    },
+    {
+      "epoch": 0.72,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5931060910224915,
+      "eval_runtime": 29.0233,
+      "eval_samples_per_second": 40.795,
+      "eval_steps_per_second": 20.397,
+      "step": 350
+    },
+    {
+      "epoch": 0.83,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5643754005432129,
+      "eval_runtime": 28.8155,
+      "eval_samples_per_second": 41.089,
+      "eval_steps_per_second": 20.545,
+      "step": 400
+    },
+    {
+      "epoch": 0.93,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5633080005645752,
+      "eval_runtime": 29.0501,
+      "eval_samples_per_second": 40.757,
+      "eval_steps_per_second": 20.379,
+      "step": 450
+    },
+    {
+      "epoch": 1.03,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5926231145858765,
+      "eval_runtime": 28.7918,
+      "eval_samples_per_second": 41.123,
+      "eval_steps_per_second": 20.561,
+      "step": 500
+    },
+    {
+      "epoch": 1.14,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5648908019065857,
+      "eval_runtime": 28.8558,
+      "eval_samples_per_second": 41.032,
+      "eval_steps_per_second": 20.516,
+      "step": 550
+    },
+    {
+      "epoch": 1.24,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5628103017807007,
+      "eval_runtime": 28.9143,
+      "eval_samples_per_second": 40.949,
+      "eval_steps_per_second": 20.474,
+      "step": 600
+    },
+    {
+      "epoch": 1.34,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5630568265914917,
+      "eval_runtime": 28.8676,
+      "eval_samples_per_second": 41.015,
+      "eval_steps_per_second": 20.507,
+      "step": 650
+    },
+    {
+      "epoch": 1.45,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5687929391860962,
+      "eval_runtime": 28.9082,
+      "eval_samples_per_second": 40.957,
+      "eval_steps_per_second": 20.479,
+      "step": 700
+    },
+    {
+      "epoch": 1.55,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5623889565467834,
+      "eval_runtime": 28.8406,
+      "eval_samples_per_second": 41.053,
+      "eval_steps_per_second": 20.527,
+      "step": 750
+    },
+    {
+      "epoch": 1.65,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5629884600639343,
+      "eval_runtime": 28.8402,
+      "eval_samples_per_second": 41.054,
+      "eval_steps_per_second": 20.527,
+      "step": 800
+    },
+    {
+      "epoch": 1.76,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5627905130386353,
+      "eval_runtime": 29.4658,
+      "eval_samples_per_second": 40.182,
+      "eval_steps_per_second": 20.091,
+      "step": 850
+    },
+    {
+      "epoch": 1.86,
+      "eval_accuracy": 0.75,
+      "eval_loss": 0.5623977184295654,
+      "eval_runtime": 29.0192,
+      "eval_samples_per_second": 40.801,
+      "eval_steps_per_second": 20.4,
+      "step": 900
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 1000,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 2907702695903472.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-900/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbe5e88ca49040823bdb83dc035b8a4470c58ae105b0482f624b7d48f5e08cbe
+size 4027