Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7ae91360481ab1aead09d557d58d1b42a726caf7a77a9bf10bee6acbb84e11
+oid sha256:2292682bda06383e4668b0f29444519a7ce7f188949e7579abc9eba8b70995bd
 size 267832560

run-1/checkpoint-1069/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": "4.40.0",
+  "vocab_size": 30522
+}

run-1/checkpoint-1069/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17d4d69227744c8fc16a68bd010522a972bc2d428dbdb302186db88506db9f87
+size 267832560

run-1/checkpoint-1069/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c5bb2b02a77795f51587c809b8be2334e87b4f3d8fd4ef13032b77288dbe9ee
+size 535724410

run-1/checkpoint-1069/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43691fea594f06f1fe96c4d21d3a558ea9118f1a617efafcc9baaf97b6953f76
+size 14054

run-1/checkpoint-1069/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40b0e91e46a33f574601e6097676a162b3d370f67167526748b34eb0e6c5114
+size 1064

run-1/checkpoint-1069/special_tokens_map.json

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

run-1/checkpoint-1069/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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-1069/trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": 0.3611067385212146,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1069",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1069,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 2.976968765258789,
+      "learning_rate": 5.1710250568684506e-05,
+      "loss": 0.5872,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 3.4058539867401123,
+      "learning_rate": 3.592568079802378e-05,
+      "loss": 0.5491,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5090050101280212,
+      "eval_matthews_correlation": 0.3611067385212146,
+      "eval_runtime": 28.3466,
+      "eval_samples_per_second": 36.794,
+      "eval_steps_per_second": 2.328,
+      "step": 1069
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 37680765508320.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.749482033934521e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 25
+  }
+}

run-1/checkpoint-1069/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86af0a103816c5520416e0097dd89d50a07cbde39cfa749f0effccd48467f774
+size 5048

run-1/checkpoint-2138/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": "4.40.0",
+  "vocab_size": 30522
+}

run-1/checkpoint-2138/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cec4ce1d2b9f76db5a8dedca630e6f833ee08905c7efdc3173e0d174c1130648
+size 267832560

run-1/checkpoint-2138/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6de591f08904fd53e4c847c659bc95a41069c1f0c2b910487b6da18ed83ff7a
+size 535724410

run-1/checkpoint-2138/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37bb18caef6eb447741eff7ae91dfd3fcfa8bc8a63135e1f691bb2da338921c
+size 14054

run-1/checkpoint-2138/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6da3a89515b59dff37c5a264b589ef20e97716e0f62e87efd04721694227d277
+size 1064

run-1/checkpoint-2138/special_tokens_map.json

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

run-1/checkpoint-2138/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": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-2138/trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_metric": 0.4546806571399457,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-2138",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 2138,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4677268475210477,
+      "grad_norm": 2.976968765258789,
+      "learning_rate": 5.1710250568684506e-05,
+      "loss": 0.5872,
+      "step": 500
+    },
+    {
+      "epoch": 0.9354536950420954,
+      "grad_norm": 3.4058539867401123,
+      "learning_rate": 3.592568079802378e-05,
+      "loss": 0.5491,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5090050101280212,
+      "eval_matthews_correlation": 0.3611067385212146,
+      "eval_runtime": 28.3466,
+      "eval_samples_per_second": 36.794,
+      "eval_steps_per_second": 2.328,
+      "step": 1069
+    },
+    {
+      "epoch": 1.4031805425631432,
+      "grad_norm": 5.668572902679443,
+      "learning_rate": 2.014111102736307e-05,
+      "loss": 0.3878,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8709073900841908,
+      "grad_norm": 1.8915776014328003,
+      "learning_rate": 4.3565412567023575e-06,
+      "loss": 0.3562,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5790878534317017,
+      "eval_matthews_correlation": 0.4546806571399457,
+      "eval_runtime": 29.1964,
+      "eval_samples_per_second": 35.724,
+      "eval_steps_per_second": 2.261,
+      "step": 2138
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2138,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 75350923275732.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 6.749482033934521e-05,
+    "num_train_epochs": 2,
+    "per_device_train_batch_size": 8,
+    "seed": 25
+  }
+}

run-1/checkpoint-2138/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86af0a103816c5520416e0097dd89d50a07cbde39cfa749f0effccd48467f774
+size 5048

run-2/checkpoint-2138/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.40.0",
   "vocab_size": 30522
 }

run-2/checkpoint-2138/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200ee35d297dc8b8e8eb2bd2d9e52426cc400de72560cdb131044b6b73e0b864
+oid sha256:2292682bda06383e4668b0f29444519a7ce7f188949e7579abc9eba8b70995bd
 size 267832560

run-2/checkpoint-2138/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:461213f9e8a54d8999067eeb75e099c03eb938d69eb56ffe5e68269a9134cf36
+oid sha256:38d9932cadcc72e99b583551907c150e219d3002dac2a084260e2fc459be870c
 size 535724410

run-2/checkpoint-2138/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98400294eef529d1f2787b05722f24c8811106c0700e9e830fc37d3292a00f04
-size 14054
+oid sha256:22a50707598de04408565ca20d1c05f242653f0f6139d0cfac55909f5c83c345
+size 13990

run-2/checkpoint-2138/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:060e1a085d6858de1c12aaf460994c62236816afccdd8f1dc65ddbde3e0d26b4
+oid sha256:7fc268b5b567f4a019701f42c405b694232d88ed3e059f86b8fab8ae11c200b7
 size 1064

run-2/checkpoint-2138/tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

run-2/checkpoint-2138/tokenizer_config.json

@@ -45,7 +45,7 @@
   "cls_token": "[CLS]",
   "do_lower_case": true,
   "mask_token": "[MASK]",
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "strip_accents": null,

run-2/checkpoint-2138/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.16393153624590007,
+  "best_metric": 0.42239354524181305,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-2138",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -9,55 +9,55 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.23,
-      "grad_norm": 3.03009033203125,
-      "learning_rate": 6.435826529339398e-05,
-      "loss": 0.6104,
+      "epoch": 0.23386342376052385,
+      "grad_norm": 6.864675998687744,
+      "learning_rate": 7.257742157959134e-06,
+      "loss": 0.6169,
       "step": 500
     },
     {
-      "epoch": 0.47,
-      "grad_norm": 3.0893821716308594,
-      "learning_rate": 6.120035237418916e-05,
-      "loss": 0.599,
+      "epoch": 0.4677268475210477,
+      "grad_norm": 18.30718421936035,
+      "learning_rate": 6.296706384924291e-06,
+      "loss": 0.5397,
       "step": 1000
     },
     {
-      "epoch": 0.7,
-      "grad_norm": 4.689079284667969,
-      "learning_rate": 5.804243945498436e-05,
-      "loss": 0.6233,
+      "epoch": 0.7015902712815716,
+      "grad_norm": 14.399059295654297,
+      "learning_rate": 5.335670611889448e-06,
+      "loss": 0.5124,
       "step": 1500
     },
     {
-      "epoch": 0.94,
-      "grad_norm": 2.1753005981445312,
-      "learning_rate": 5.488452653577955e-05,
-      "loss": 0.6504,
+      "epoch": 0.9354536950420954,
+      "grad_norm": 33.269954681396484,
+      "learning_rate": 4.3746348388546045e-06,
+      "loss": 0.5342,
       "step": 2000
     },
     {
       "epoch": 1.0,
-      "eval_loss": 0.6044347286224365,
-      "eval_matthews_correlation": 0.16393153624590007,
-      "eval_runtime": 30.5852,
-      "eval_samples_per_second": 34.102,
-      "eval_steps_per_second": 2.158,
+      "eval_loss": 0.543093740940094,
+      "eval_matthews_correlation": 0.42239354524181305,
+      "eval_runtime": 28.1501,
+      "eval_samples_per_second": 37.051,
+      "eval_steps_per_second": 2.345,
       "step": 2138
     }
   ],
   "logging_steps": 500,
-  "max_steps": 10690,
+  "max_steps": 4276,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
-  "total_flos": 32685295716816.0,
+  "total_flos": 32740145499072.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 6.751617821259878e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 8.218777930993977e-06,
+    "num_train_epochs": 2,
     "per_device_train_batch_size": 4,
-    "seed": 13
+    "seed": 38
   }
 }

run-2/checkpoint-2138/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c5c7be0f50a61c6e9e22c6c96912df518c2bf9ae78538097c92c4dbd3fca91
-size 4984
+oid sha256:52a3b2e1ec5a1c8f67e0f69b146b5cfc61a90f4dd76ed7c7f6e062bc7284397e
+size 5048

runs/Apr23_13-58-51_309eb7d6022b/events.out.tfevents.1713888517.309eb7d6022b.9612.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d78acdc914cfc78e7d15bbfcf5050104d0377f4dbc5f34b09d9315e64803d3f1
+size 6517

runs/Apr23_13-58-51_309eb7d6022b/events.out.tfevents.1713891455.309eb7d6022b.9612.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65bf00178bc1f8c40047d100076acb7b102065294378fdaf2cda23e9c08234dc
+size 5828

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de6e654bc5562972689e528d7506196f0ff109bd86fc3e0cc344b82d96435ef0
+oid sha256:52a3b2e1ec5a1c8f67e0f69b146b5cfc61a90f4dd76ed7c7f6e062bc7284397e
 size 5048