Training in progress, epoch 1

added_tokens.json

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

checkpoint-250/added_tokens.json

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

checkpoint-250/config.json

@@ -0,0 +1,59 @@
+{
+  "_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,
+  "id2label": {
+    "0": "Society & Culture",
+    "1": "Science & Mathematics",
+    "2": "Health",
+    "3": "Education & Reference",
+    "4": "Computers & Internet",
+    "5": "Sports",
+    "6": "Business & Finance",
+    "7": "Entertainment & Music",
+    "8": "Family & Relationships",
+    "9": "Politics & Government"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Business & Finance": 6,
+    "Computers & Internet": 4,
+    "Education & Reference": 3,
+    "Entertainment & Music": 7,
+    "Family & Relationships": 8,
+    "Health": 2,
+    "Politics & Government": 9,
+    "Science & Mathematics": 1,
+    "Society & Culture": 0,
+    "Sports": 5
+  },
+  "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": "4.31.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

checkpoint-250/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb540ce1b76cae8cb730f46390a29df1fb987b6dd5aa96cc6cf3efb0e7457402
+size 1475556869

checkpoint-250/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b60fe5c771bf1d6371a17ada8a74f4f01b6c72708b6cba4c34199ac3b65440
+size 737788917

checkpoint-250/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9cd9bb740fbec8922391c7cc04b28b60991e2b170db4303ee8ff630d45412ff
+size 14575

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19cd4ab287264ead52ae36fdf79cf0921f7b920697356e06d4b46a038af15fd0
+size 627

checkpoint-250/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-250/spm.model

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

checkpoint-250/tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "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-250/trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.999466666666667e-05,
+      "loss": 2.308,
+      "step": 1
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.8997333333333335e-05,
+      "loss": 1.6916,
+      "step": 188
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.6755,
+      "eval_disk_space_total": 78.1898422241211,
+      "eval_disk_space_used": 24.806385040283203,
+      "eval_f1": 0.6708054417489328,
+      "eval_gpu_ram_allocated": 2.089780330657959,
+      "eval_gpu_ram_cached": 25.85546875,
+      "eval_gpu_ram_total": 39.56402587890625,
+      "eval_gpu_utilization": 50,
+      "eval_loss": 1.1062816381454468,
+      "eval_precision": 0.690043017889279,
+      "eval_recall": 0.6755,
+      "eval_runtime": 2.3912,
+      "eval_samples_per_second": 836.398,
+      "eval_steps_per_second": 26.347,
+      "eval_system_ram_total": 83.48074722290039,
+      "eval_system_ram_used": 4.019077301025391,
+      "step": 188
+    }
+  ],
+  "max_steps": 3750,
+  "num_train_epochs": 15,
+  "total_flos": 478954442421888.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c483311c6e034a3b791b3aba6061603f3b239dec5f5cd88a867a5f6743909401
+size 4091

config.json

@@ -0,0 +1,59 @@
+{
+  "_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,
+  "id2label": {
+    "0": "Society & Culture",
+    "1": "Science & Mathematics",
+    "2": "Health",
+    "3": "Education & Reference",
+    "4": "Computers & Internet",
+    "5": "Sports",
+    "6": "Business & Finance",
+    "7": "Entertainment & Music",
+    "8": "Family & Relationships",
+    "9": "Politics & Government"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Business & Finance": 6,
+    "Computers & Internet": 4,
+    "Education & Reference": 3,
+    "Entertainment & Music": 7,
+    "Family & Relationships": 8,
+    "Health": 2,
+    "Politics & Government": 9,
+    "Science & Mathematics": 1,
+    "Society & Culture": 0,
+    "Sports": 5
+  },
+  "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": "4.31.0",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01b60fe5c771bf1d6371a17ada8a74f4f01b6c72708b6cba4c34199ac3b65440
+size 737788917

runs/Jul22_21-19-20_ab4276e44fca/events.out.tfevents.1690060770.ab4276e44fca.659.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48be183149ce19869bac4a47cdab909fa5882f8436f18519cfbf6506cc8b4a0d
+size 6222

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]"
+}

spm.model

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

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "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"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c483311c6e034a3b791b3aba6061603f3b239dec5f5cd88a867a5f6743909401
+size 4091