Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b33bebca3c31b2a59033909ad09f352f795168df035fa5e21068f27d4fb1f40
+oid sha256:b7593428f1ba9b592490d9198bd08dc3f19d0316437e328d82788ea96618a668
 size 267832560

run-2/checkpoint-1070/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": "4.38.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-1070/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7593428f1ba9b592490d9198bd08dc3f19d0316437e328d82788ea96618a668
+size 267832560

run-2/checkpoint-1070/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ced47b1aedcd99864292547ceda03a3764600d0bc4138cdc344e9e141f473cd
+size 535727290

run-2/checkpoint-1070/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1df6b7b1ff6335db58bce89e3cedae9f448c487e2a4943b7e6ed61881bccbfd
+size 14244

run-2/checkpoint-1070/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a10a782318ff8436a6977d04f72c54fe238a1a879125de3122c5622945faab
+size 1064

run-2/checkpoint-1070/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-1070/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-1070/trainer_state.json

@@ -0,0 +1,85 @@
+{
+  "best_metric": 0.18954364972242177,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-856",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1070,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.622901976108551,
+      "eval_matthews_correlation": 0.0,
+      "eval_runtime": 0.6976,
+      "eval_samples_per_second": 1495.146,
+      "eval_steps_per_second": 94.611,
+      "step": 214
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6693491339683533,
+      "eval_matthews_correlation": 0.11842631274491741,
+      "eval_runtime": 1.934,
+      "eval_samples_per_second": 539.286,
+      "eval_steps_per_second": 34.125,
+      "step": 428
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 1.357163667678833,
+      "learning_rate": 3.7935113291347165e-05,
+      "loss": 0.6007,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.3187288045883179,
+      "eval_matthews_correlation": 0.16411291424457647,
+      "eval_runtime": 0.7002,
+      "eval_samples_per_second": 1489.531,
+      "eval_steps_per_second": 94.256,
+      "step": 642
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.7241299152374268,
+      "eval_matthews_correlation": 0.18954364972242177,
+      "eval_runtime": 0.7297,
+      "eval_samples_per_second": 1429.361,
+      "eval_steps_per_second": 90.449,
+      "step": 856
+    },
+    {
+      "epoch": 4.67,
+      "grad_norm": 0.02015562355518341,
+      "learning_rate": 4.6586981234987745e-06,
+      "loss": 0.1886,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.820284128189087,
+      "eval_matthews_correlation": 0.17970618963824728,
+      "eval_runtime": 0.7049,
+      "eval_samples_per_second": 1479.705,
+      "eval_steps_per_second": 93.634,
+      "step": 1070
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1070,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 16802402872884.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.121152845919556e-05,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 4,
+    "seed": 12
+  }
+}

run-2/checkpoint-1070/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9925351ca91d4d415edf2b12fea3939fa440869d79fbdaa5406de401cf3bbc4a
+size 4984

run-2/checkpoint-428/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7feb3ea5cfcc0719d9aa3e8828e87201c6ba1874b1b9dda6a72a11196b3465a
+oid sha256:f91ce0d32e3d331a97bec4766b3625708317c7a462015a589e5c58aa17a0a83e
 size 267832560

run-2/checkpoint-428/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01af5387baa500deae7a60ef01607a213628612baa70b49dab4c8444e09983b3
-size 535724410
+oid sha256:01beac2a03a926258b352eb83e0b8f6bdba3eee64c73cb47aa03f1d58a2e3343
+size 535727290

run-2/checkpoint-428/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d30d176f4709947ef5e20ca28f86e3ac8c85d9b22de4d4222b40eaa3316066d
-size 14054
+oid sha256:123a5343f68ec13b68a2b560055939797bee709d54072612e9bb907a91476f28
+size 14244

run-2/checkpoint-428/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b4f4d37419af893e7c0515177d5a99af69ac0b950cded792175bcc7ced3722
+oid sha256:d30bc9c1aed483a88d8d8aec183321452b5964d4c251bdf3c79ed88b67776916
 size 1064

run-2/checkpoint-428/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.25145549881333384,
+  "best_metric": 0.11842631274491741,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-428",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,35 +10,35 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6176151633262634,
+      "eval_loss": 0.622901976108551,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.9481,
-      "eval_samples_per_second": 1100.056,
-      "eval_steps_per_second": 69.61,
+      "eval_runtime": 0.6976,
+      "eval_samples_per_second": 1495.146,
+      "eval_steps_per_second": 94.611,
       "step": 214
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.7769425511360168,
-      "eval_matthews_correlation": 0.25145549881333384,
-      "eval_runtime": 0.9343,
-      "eval_samples_per_second": 1116.319,
-      "eval_steps_per_second": 70.64,
+      "eval_loss": 0.6693491339683533,
+      "eval_matthews_correlation": 0.11842631274491741,
+      "eval_runtime": 1.934,
+      "eval_samples_per_second": 539.286,
+      "eval_steps_per_second": 34.125,
       "step": 428
     }
   ],
   "logging_steps": 500,
-  "max_steps": 856,
+  "max_steps": 1070,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.2783203586043606e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 7.121152845919556e-05,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 4,
-    "seed": 20
+    "seed": 12
   }
 }

run-2/checkpoint-428/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d59a3030f49e6d9ba6b53703d0aecc5a3cdf0ff9b87524d64c50670dec0e33
-size 4920
+oid sha256:9925351ca91d4d415edf2b12fea3939fa440869d79fbdaa5406de401cf3bbc4a
+size 4984

run-2/checkpoint-642/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d37aded1f4476bbe051cc3bfcec41462be35bfe49b40bc6597fbe45a146bc1
+oid sha256:955e9d37c7ccf9fb2880c11ea1f35e7ffd6a30ab6bb769dfa19b27a03652e9cc
 size 267832560

run-2/checkpoint-642/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef5020ece8eb289d5cf85d6fc8e8bee89797830e5366db88b5dd8f4aae439706
-size 535724410
+oid sha256:49e846a73ef024263b9276d16b7bbf1b5a16de68a3a7164b8fdf60475011e3da
+size 535727290

run-2/checkpoint-642/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466fe0e260a39f52aac06c5607d4735d2c8103b2ac9ad54f5e71129ba4c43fb2
-size 14054
+oid sha256:459a440c9d15ba5e5b2229c7ffbe3145e047b6e5e97660610634d47c20f261e5
+size 14244

run-2/checkpoint-642/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:524be37aab3f413fec1d7104c5de4e629f9090793566ac787fa2c9f2c4d95a2b
+oid sha256:380f2c8df8ab872e64b071c5a78cf09b05e00c6ec4fb7780bd08fd5e87023ef7
 size 1064

run-2/checkpoint-642/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.25145549881333384,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-428",
+  "best_metric": 0.16411291424457647,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-642",
   "epoch": 3.0,
   "eval_steps": 500,
   "global_step": 642,
@@ -10,51 +10,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6176151633262634,
+      "eval_loss": 0.622901976108551,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.9481,
-      "eval_samples_per_second": 1100.056,
-      "eval_steps_per_second": 69.61,
+      "eval_runtime": 0.6976,
+      "eval_samples_per_second": 1495.146,
+      "eval_steps_per_second": 94.611,
       "step": 214
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.7769425511360168,
-      "eval_matthews_correlation": 0.25145549881333384,
-      "eval_runtime": 0.9343,
-      "eval_samples_per_second": 1116.319,
-      "eval_steps_per_second": 70.64,
+      "eval_loss": 0.6693491339683533,
+      "eval_matthews_correlation": 0.11842631274491741,
+      "eval_runtime": 1.934,
+      "eval_samples_per_second": 539.286,
+      "eval_steps_per_second": 34.125,
       "step": 428
     },
     {
       "epoch": 2.34,
-      "grad_norm": 0.6545006036758423,
-      "learning_rate": 1.7793014575504117e-05,
-      "loss": 0.536,
+      "grad_norm": 1.357163667678833,
+      "learning_rate": 3.7935113291347165e-05,
+      "loss": 0.6007,
       "step": 500
     },
     {
       "epoch": 3.0,
-      "eval_loss": 1.5843945741653442,
-      "eval_matthews_correlation": 0.1975523186260999,
-      "eval_runtime": 0.9037,
-      "eval_samples_per_second": 1154.164,
-      "eval_steps_per_second": 73.034,
+      "eval_loss": 1.3187288045883179,
+      "eval_matthews_correlation": 0.16411291424457647,
+      "eval_runtime": 0.7002,
+      "eval_samples_per_second": 1489.531,
+      "eval_steps_per_second": 94.256,
       "step": 642
     }
   ],
   "logging_steps": 500,
-  "max_steps": 856,
+  "max_steps": 1070,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 8269898302032.0,
+  "total_flos": 8429531866428.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.2783203586043606e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 7.121152845919556e-05,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 4,
-    "seed": 20
+    "seed": 12
   }
 }

run-2/checkpoint-642/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d59a3030f49e6d9ba6b53703d0aecc5a3cdf0ff9b87524d64c50670dec0e33
-size 4920
+oid sha256:9925351ca91d4d415edf2b12fea3939fa440869d79fbdaa5406de401cf3bbc4a
+size 4984

run-2/checkpoint-856/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27626274def27c9e5f0ede06699eccc9fca618421c5670171c59a5b7bb0bc50
+oid sha256:8d7fc0ebbfd3955802d3bc98ef627cbaaa60a67957d6617d060aa879e86f74b5
 size 267832560

run-2/checkpoint-856/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91f7394c728500aa68bbe29a75db3198b7d0c751ffc1593b88ea2fba588d8c42
-size 535724410
+oid sha256:06c7ccf331c7f4f77d0cf84856691943b9acee52ec3eab295724b9ad971db10f
+size 535727290

run-2/checkpoint-856/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a8a81a3e9c375ac5e32a3bec083b8fd3ff43e0f665a1ebc2f09c530719bc7eb
-size 14054
+oid sha256:0959e4fc49f256382e0dc2b5eaaf6de1ebc7372d1c9b5b34f8bda98d7f54a5b9
+size 14244

run-2/checkpoint-856/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6101755e70840fa69ae18a6720e6b0998296d977a410bf72ba3a6ac1d5932863
+oid sha256:de31a0e7adf5d8ef4931b73625e96f3d7d082ff90485a5440fb14cbcadca1600
 size 1064

run-2/checkpoint-856/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.25145549881333384,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-428",
+  "best_metric": 0.18954364972242177,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-2/checkpoint-856",
   "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 856,
@@ -10,60 +10,60 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.6176151633262634,
+      "eval_loss": 0.622901976108551,
       "eval_matthews_correlation": 0.0,
-      "eval_runtime": 0.9481,
-      "eval_samples_per_second": 1100.056,
-      "eval_steps_per_second": 69.61,
+      "eval_runtime": 0.6976,
+      "eval_samples_per_second": 1495.146,
+      "eval_steps_per_second": 94.611,
       "step": 214
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.7769425511360168,
-      "eval_matthews_correlation": 0.25145549881333384,
-      "eval_runtime": 0.9343,
-      "eval_samples_per_second": 1116.319,
-      "eval_steps_per_second": 70.64,
+      "eval_loss": 0.6693491339683533,
+      "eval_matthews_correlation": 0.11842631274491741,
+      "eval_runtime": 1.934,
+      "eval_samples_per_second": 539.286,
+      "eval_steps_per_second": 34.125,
       "step": 428
     },
     {
       "epoch": 2.34,
-      "grad_norm": 0.6545006036758423,
-      "learning_rate": 1.7793014575504117e-05,
-      "loss": 0.536,
+      "grad_norm": 1.357163667678833,
+      "learning_rate": 3.7935113291347165e-05,
+      "loss": 0.6007,
       "step": 500
     },
     {
       "epoch": 3.0,
-      "eval_loss": 1.5843945741653442,
-      "eval_matthews_correlation": 0.1975523186260999,
-      "eval_runtime": 0.9037,
-      "eval_samples_per_second": 1154.164,
-      "eval_steps_per_second": 73.034,
+      "eval_loss": 1.3187288045883179,
+      "eval_matthews_correlation": 0.16411291424457647,
+      "eval_runtime": 0.7002,
+      "eval_samples_per_second": 1489.531,
+      "eval_steps_per_second": 94.256,
       "step": 642
     },
     {
       "epoch": 4.0,
-      "eval_loss": 1.8945112228393555,
-      "eval_matthews_correlation": 0.2128478036255419,
-      "eval_runtime": 0.9124,
-      "eval_samples_per_second": 1143.125,
-      "eval_steps_per_second": 72.336,
+      "eval_loss": 1.7241299152374268,
+      "eval_matthews_correlation": 0.18954364972242177,
+      "eval_runtime": 0.7297,
+      "eval_samples_per_second": 1429.361,
+      "eval_steps_per_second": 90.449,
       "step": 856
     }
   ],
   "logging_steps": 500,
-  "max_steps": 856,
+  "max_steps": 1070,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 8269898302032.0,
+  "total_flos": 8429531866428.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 4.2783203586043606e-05,
-    "num_train_epochs": 4,
+    "learning_rate": 7.121152845919556e-05,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 4,
-    "seed": 20
+    "seed": 12
   }
 }

run-2/checkpoint-856/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d59a3030f49e6d9ba6b53703d0aecc5a3cdf0ff9b87524d64c50670dec0e33
-size 4920
+oid sha256:9925351ca91d4d415edf2b12fea3939fa440869d79fbdaa5406de401cf3bbc4a
+size 4984

runs/Mar08_16-02-10_50bca828e3b2/events.out.tfevents.1709913834.50bca828e3b2.2324.5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435cd4f9ebbd7f6b8485cd1f7bb28face7d44957f87413ffca74d74c5e02d93c
-size 5210
+oid sha256:b105d1d67ef7f472f2a4ca6630093c1b4b4138218112338bc286a40fd80409d3
+size 6991