Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0298ff43d8ce12b4779108f6dc628b694797fa846716755315d51f3747e3ed3f
+oid sha256:9a98d81a13e585b6e2e956e137deede010c06fdfe77852805cfa6ca0175d94b2
 size 737719272

run-3/checkpoint-63/added_tokens.json

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

run-3/checkpoint-63/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": "4.38.2",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

run-3/checkpoint-63/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a98d81a13e585b6e2e956e137deede010c06fdfe77852805cfa6ca0175d94b2
+size 737719272

run-3/checkpoint-63/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62e2fdc0ccfa3b503fb01c68bc6e7c8e962dd7507b0e9312bb3ac40b7583d99d
+size 1475558394

run-3/checkpoint-63/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db534c65568502baad5ed88a6e0acee964c1829664a6d91e8350031fd74ce08a
+size 14244

run-3/checkpoint-63/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34186c9d7d016681c9a4dc5ea46f6e8534e127089989f5aa69a471561e456975
+size 1064

run-3/checkpoint-63/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-63/spm.model

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

run-3/checkpoint-63/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-63/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.5270758122743683,
+  "best_model_checkpoint": "deberta-v3-base-finetuned-rte/run-3/checkpoint-63",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5270758122743683,
+      "eval_loss": 0.6918896436691284,
+      "eval_runtime": 5.8038,
+      "eval_samples_per_second": 47.728,
+      "eval_steps_per_second": 6.031,
+      "step": 63
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 63,
+  "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": 4.17370455664283e-06,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 4,
+    "seed": 18
+  }
+}

run-3/checkpoint-63/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3246c655d87d079430cdbfe78eeedaebf6386c1a98b196264325763847a9be7
+size 4920

runs/Mar10_13-32-58_4e3c1469116f/events.out.tfevents.1710078996.4e3c1469116f.2145.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2026bdac690a0a63a0916ca2731868a9842501b9df31f2d420549e1f68aa218
+size 5426

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f481bd5d69eb48f2f53b64e542d5ef66bdd38a05958ed1e10734deddb12e1d22
+oid sha256:e3246c655d87d079430cdbfe78eeedaebf6386c1a98b196264325763847a9be7
 size 4920