Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:807bb71a6a475c0a23ae1b333d56cf9d34b4a9d2df20e6ca7a12e8aed90b0c07
+oid sha256:f2679097f22ee50d1133b868eb8c599811af879313c456b3c34d6c034c09e030
 size 567598552

run-4/checkpoint-4/added_tokens.json

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

run-4/checkpoint-4/config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "microsoft/deberta-v3-small",
+  "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": 6,
+  "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-4/checkpoint-4/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807bb71a6a475c0a23ae1b333d56cf9d34b4a9d2df20e6ca7a12e8aed90b0c07
+size 567598552

run-4/checkpoint-4/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8c332e30b76772f85413e9fb853d5b13489db29c71d3541f6550f74d2494693
+size 1135260474

run-4/checkpoint-4/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67e61165e9cc40f7d67c9d47de2ab4fc93bcf69a31b430b45b63f52022efca3b
+size 14308

run-4/checkpoint-4/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33639bd6149876ffa3a4890d945f75eafbaa5144c709acc08400c65697616071
+size 1064

run-4/checkpoint-4/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-4/checkpoint-4/spm.model

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

run-4/checkpoint-4/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-4/checkpoint-4/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.4729241877256318,
+  "best_model_checkpoint": "microsoft/deberta-v3-smallsed_rte-finetuned-rte/run-4/checkpoint-4",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6945120096206665,
+      "eval_runtime": 1.7879,
+      "eval_samples_per_second": 154.928,
+      "eval_steps_per_second": 10.068,
+      "step": 4
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.4183577103266747e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 64,
+    "seed": 13
+  }
+}

run-4/checkpoint-4/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:289bd2556a328273c7c6f9aa8d402dc93e5ef25dfdc6e45606530658cdd01d8b
+size 4984

runs/Mar05_19-28-01_f943f6aa6ee4/events.out.tfevents.1709668906.f943f6aa6ee4.164.8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45da237d7ace8bf750773aab48082bc22d21ee3ef1352888453070443524e5f6
+size 5481

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289bd2556a328273c7c6f9aa8d402dc93e5ef25dfdc6e45606530658cdd01d8b
+oid sha256:33de822bf81ee1e56f7d53cd619eab37a97127ce127550ee6a45a57563abe008
 size 4984