Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed1ca670602465a09e34815d2a91e895491af587d899f2f9221d046f8418e488
+oid sha256:addf2c20d805defeeba126f957fe7e15318350431e2b5e04930f90de650ce4a4
 size 737719272

run-0/checkpoint-54/config.json

@@ -1,25 +1,25 @@
 {
-  "_name_or_path": "microsoft/deberta-v3-large",
+  "_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": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "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": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "pooler_dropout": 0,
   "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 1024,
+  "pooler_hidden_size": 768,
   "pos_att_type": [
     "p2c",
     "c2p"

run-0/checkpoint-54/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db25cee7efaa01864d9a77a4f74d0c9d2326018ba142cbe1a036d5a07c453429
-size 1740304440
+oid sha256:87044b595d7a0181326ff6aa982233682df37fd6d8fb80df3ec774762970f2de
+size 737719272

run-0/checkpoint-54/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f5b3b6ade9c56e825e668910d5ab939bc488a51bdabc63d4539a124f9083b4a
-size 3480840240
+oid sha256:d82c05a99b2ddbece306287918332f8f59b994cacc193b350ed76d00309fc79c
+size 1475558394

run-0/checkpoint-54/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a45d58deab7b40d9aeb8b53350029d22a9ff60fdf1c1b2e911c09dd065d85c
-size 14244
+oid sha256:535fc72798472b297dd7ab9d9b14270d2141a65660dfe7805ca4e687a65153c6
+size 14308

run-0/checkpoint-54/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24ba1810c98b8defe45bf5ba34ee6195e35b1ba63433d1bef77b9c14523c344f
+oid sha256:d17c6060f37e6e1e853f64a44f581e6b17dd9816ba7801bd9ee1fab58db240a9
 size 1064

run-0/checkpoint-54/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.4307702429617212,
-  "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-0/checkpoint-54",
-  "epoch": 1.0,
+  "best_metric": 0.048639888821286496,
+  "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-0/checkpoint-27",
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 54,
   "is_hyper_param_search": true,
@@ -10,26 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6075441837310791,
-      "eval_matthews_correlation": 0.4307702429617212,
-      "eval_runtime": 3.4416,
-      "eval_samples_per_second": 303.053,
-      "eval_steps_per_second": 19.177,
+      "eval_loss": 0.691221296787262,
+      "eval_matthews_correlation": 0.048639888821286496,
+      "eval_runtime": 2.4651,
+      "eval_samples_per_second": 423.102,
+      "eval_steps_per_second": 26.773,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6872335076332092,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.5239,
+      "eval_samples_per_second": 413.257,
+      "eval_steps_per_second": 26.151,
       "step": 54
     }
   ],
   "logging_steps": 500,
-  "max_steps": 216,
+  "max_steps": 54,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 8,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 2.0352764481854907e-05,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 8,
-    "seed": 4
+    "learning_rate": 1.295113530605781e-06,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 16,
+    "seed": 29
   }
 }

run-0/checkpoint-54/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:809a0430adc83b27e312907f1dee6ad0edefa61c1f8ccdf999f9172f36110b1e
+oid sha256:1ca2192d898bc34b22b60030a4c304d30c36cac0af471e752e5be729bc08981c
 size 4984

run-1/checkpoint-14/added_tokens.json

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

run-1/checkpoint-14/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": "4.38.1",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

run-1/checkpoint-14/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:addf2c20d805defeeba126f957fe7e15318350431e2b5e04930f90de650ce4a4
+size 737719272

run-1/checkpoint-14/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76618ed074c6aae765314ede1b3a4699bc037d97c8dc98b4faac758ccea6e0ff
+size 1475558394

run-1/checkpoint-14/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ef99b44f5e2f5cc2946d95c84805d4de22151489fbe29c087c0348eac9e40a
+size 14244

run-1/checkpoint-14/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5340f0affb3c04318226642a3c0cdaab66af8030805bd703e69e0ed5471db96e
+size 1064

run-1/checkpoint-14/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-1/checkpoint-14/spm.model

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

run-1/checkpoint-14/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-1/checkpoint-14/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "deberta-v3-large-finetuned-cola-midterm/run-1/checkpoint-14",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 14,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5280356407165527,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 2.4754,
+      "eval_samples_per_second": 421.353,
+      "eval_steps_per_second": 26.663,
+      "step": 14
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 9.722494086779406e-05,
+    "num_train_epochs": 1,
+    "per_device_train_batch_size": 32,
+    "seed": 36
+  }
+}

run-1/checkpoint-14/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4f92e6596e45521adbb2f39bbfe7decd0667f5983debc527e7e2a15239c14c
+size 4984

runs/Feb29_12-55-06_e1aa4b7a2e4c/events.out.tfevents.1709211510.e1aa4b7a2e4c.252.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aaa7d5d8a900d545764d02c7e5de3107b95c87928449407f1d7b019a6319e483
+size 5483

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca2192d898bc34b22b60030a4c304d30c36cac0af471e752e5be729bc08981c
+oid sha256:ea4f92e6596e45521adbb2f39bbfe7decd0667f5983debc527e7e2a15239c14c
 size 4984