Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:951f38e98d13e21dc75cc9bd9b2cdeaa5a6f08f0892623ca0324878e99204599
+oid sha256:26970586a6d29d86ae8558c377e96d91e797d7627d02e12f52a440ec3455da9a
 size 267832560

run-2/checkpoint-108/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa03fca488c5f98da0c4e8ca0a048a75fb6ffb33149d1153b27755b790393eb9
+oid sha256:171306db58df3a626ba3a3d417209cbfc3090dd988a14e8a0c31d1a8e9eec5f0
 size 267832560

run-2/checkpoint-108/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38da991fe5a1e8ad19abb093f73aea2c558e468f324d646c274d396a10261e5
+oid sha256:67a4aa4e26054193eff3ecabdb93d2dfcc79b9f5ce7cd8a1cda793ce8bbafa11
 size 535727290

run-2/checkpoint-108/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1592c6c7d425e047a040d85ed72274684f3070b72374af37eae3af77db9be0b
+oid sha256:ad88fa5f8344a66c499780278f1e8af98f983b90b982d128ac44caa17c35092c
 size 14244

run-2/checkpoint-108/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe513f6af54d88947bce1ccba591911075618ee7ecd3c6da01627dd41bd57a3
+oid sha256:70d0593b626f92029ace37a25c8a6af187ff0257e53c884df93807231256dd5a
 size 1064

run-2/checkpoint-108/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_metric": 0.33730584534490105,
+  "best_metric": 0.27637040604945357,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-108",
-  "epoch": 4.0,
+  "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 108,
   "is_hyper_param_search": true,
@@ -10,53 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.5924028158187866,
+      "eval_loss": 0.5896052122116089,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.7139,
-      "eval_samples_per_second": 1460.954,
-      "eval_steps_per_second": 92.448,
-      "step": 27
-    },
-    {
-      "epoch": 2.0,
-      "eval_loss": 0.5790226459503174,
-      "eval_matthews_correlation": 0.2712686505720511,
-      "eval_runtime": 0.7744,
-      "eval_samples_per_second": 1346.766,
-      "eval_steps_per_second": 85.222,
+      "eval_runtime": 0.7382,
+      "eval_samples_per_second": 1412.91,
+      "eval_steps_per_second": 89.408,
       "step": 54
     },
     {
-      "epoch": 3.0,
-      "eval_loss": 0.6065369248390198,
-      "eval_matthews_correlation": 0.3342982430724728,
-      "eval_runtime": 1.2898,
-      "eval_samples_per_second": 808.645,
-      "eval_steps_per_second": 51.17,
-      "step": 81
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": 0.6588127613067627,
-      "eval_matthews_correlation": 0.33730584534490105,
-      "eval_runtime": 0.761,
-      "eval_samples_per_second": 1370.504,
-      "eval_steps_per_second": 86.724,
+      "epoch": 2.0,
+      "eval_loss": 0.620072603225708,
+      "eval_matthews_correlation": 0.27637040604945357,
+      "eval_runtime": 0.7895,
+      "eval_samples_per_second": 1321.116,
+      "eval_steps_per_second": 83.599,
       "step": 108
     }
   ],
   "logging_steps": 500,
-  "max_steps": 135,
+  "max_steps": 162,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 0,
-  "train_batch_size": 32,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.196781434256157e-05,
-    "num_train_epochs": 5,
-    "per_device_train_batch_size": 32,
-    "seed": 15
+    "learning_rate": 4.44263313595678e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 36
   }
 }

run-2/checkpoint-108/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69153e9bbab207ff12f995d64fcbc179aebf9c056495013eeb831a9bd3f09fb4
+oid sha256:64b88362824c828734d46d9219cae04a83c937724d8224d58b37d769b6b5a4e8
 size 4984

run-2/checkpoint-162/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-2/checkpoint-162/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155e5f212958ced8d22198891f6ba03246b3eee162e8dd76d5b1e98cf3d13007
+size 267832560

run-2/checkpoint-162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e3a862ed5315c8b661078c480b4a2134cfb25632ea1f2e6205a66b5a25142
+size 535727290

run-2/checkpoint-162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9e1298fe2b21bcb4b95b9996800b3e757caae71def6f36bdd0e262dede54ddc
+size 14244

run-2/checkpoint-162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37dcae55aee4f008683740270966e51f480d3a013fc719f21b7b4b53fe093346
+size 1064

run-2/checkpoint-162/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-162/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-162/trainer_state.json

@@ -0,0 +1,53 @@
+{
+  "best_metric": 0.27637040604945357,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-108",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 162,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5896052122116089,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7382,
+      "eval_samples_per_second": 1412.91,
+      "eval_steps_per_second": 89.408,
+      "step": 54
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.620072603225708,
+      "eval_matthews_correlation": 0.27637040604945357,
+      "eval_runtime": 0.7895,
+      "eval_samples_per_second": 1321.116,
+      "eval_steps_per_second": 83.599,
+      "step": 108
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.7161808013916016,
+      "eval_matthews_correlation": 0.26305149678201956,
+      "eval_runtime": 0.7943,
+      "eval_samples_per_second": 1313.053,
+      "eval_steps_per_second": 83.089,
+      "step": 162
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 4.44263313595678e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 36
+  }
+}

run-2/checkpoint-162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b88362824c828734d46d9219cae04a83c937724d8224d58b37d769b6b5a4e8
+size 4984

run-3/checkpoint-214/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "vocab_size": 30522
+}

run-3/checkpoint-214/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26970586a6d29d86ae8558c377e96d91e797d7627d02e12f52a440ec3455da9a
+size 267832560

run-3/checkpoint-214/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b036b3e8966fc75e7cccb26ae26b4310381ba2bb7be0d311b6840eadd68d0d29
+size 535727290

run-3/checkpoint-214/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0652a30494a7551b8120ac6e0902e8c5305fecb27d67d6132c2fc2ce1b8b74e4
+size 14308

run-3/checkpoint-214/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:178773c64473840f38798d849aedfc7304591bd0d6beef9503a4d06a5810eabb
+size 1064

run-3/checkpoint-214/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-214/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-214/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-3/checkpoint-214",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.6183657050132751,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.7672,
+      "eval_samples_per_second": 1359.472,
+      "eval_steps_per_second": 86.026,
+      "step": 214
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 856,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.4139589618940448e-06,
+    "num_train_epochs": 4,
+    "per_device_train_batch_size": 4,
+    "seed": 29
+  }
+}

run-3/checkpoint-214/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c633136cab74654c7b4a0769dd1ba1b598d9e84725645951026a4c6f90d735
+size 4984

runs/Feb28_18-10-00_5620ed9b2fff/events.out.tfevents.1709144711.5620ed9b2fff.209.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64d6b68edd55f6297d9cce4163973c034ca328c90f32e2a25adc2a001cf2f83a
+size 6447

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64b88362824c828734d46d9219cae04a83c937724d8224d58b37d769b6b5a4e8
+oid sha256:99c633136cab74654c7b4a0769dd1ba1b598d9e84725645951026a4c6f90d735
 size 4984