Training in progress, epoch 4

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c70c13e5d04c26d3f1731e0285668d3d574cdf941b52bb758883a9e4048d8a5b
+oid sha256:a9992887f6907f8916987f3e3d5b5cd5f9a668b44cebeae398a79e142aced221
 size 267832560

run-1/checkpoint-1072/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

run-1/checkpoint-1072/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1402dcc1a9ea22b48cf3678b18d6951fa650c0a1abcbdb78851001f2e57e5684
+oid sha256:a9992887f6907f8916987f3e3d5b5cd5f9a668b44cebeae398a79e142aced221
 size 267832560

run-1/checkpoint-1072/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f59b3cca6548a79c47d82a0ccc726e3efc9117974e48cd30348e502599ae4f
+oid sha256:6fc9517b39355720ca587337ba7563051682d885fb178f3d079846331368417c
 size 535727290

run-1/checkpoint-1072/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb759deb6668166ad5e7f05d892e3ecfaf9feca83f38a2bee6fa5a21a732911
-size 14244
+oid sha256:32ddadbd4e9ce4478d8580a2b23d53d37db7c6d53eeed56612b957a8c00b76dc
+size 14308

run-1/checkpoint-1072/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a12fcb7d20e914aced25dfedb2e8cc97640fb4986601ab9ad72a7518268a1cfe
+oid sha256:f3765e02ab4bcae5228f1b22b52d5b68ecef8a19a4fc159b8e8f029723c547b6
 size 1064

run-1/checkpoint-1072/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.5290831606897504,
-  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-1072",
+  "best_metric": 0.46849580082104064,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-804",
   "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 1072,
@@ -10,63 +10,67 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.4801884889602661,
-      "eval_matthews_correlation": 0.4522326299878879,
-      "eval_runtime": 0.6893,
-      "eval_samples_per_second": 1513.095,
-      "eval_steps_per_second": 95.747,
+      "eval_loss": 0.5035493969917297,
+      "eval_matthews_correlation": 0.4141806938515634,
+      "eval_runtime": 0.7419,
+      "eval_samples_per_second": 1405.832,
+      "eval_steps_per_second": 88.96,
       "step": 268
     },
     {
       "epoch": 1.87,
-      "learning_rate": 1.0329146614031314e-05,
-      "loss": 0.4583,
+      "grad_norm": 4.896795749664307,
+      "learning_rate": 5.453884401804003e-06,
+      "loss": 0.4997,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5012368559837341,
-      "eval_matthews_correlation": 0.4810794261012942,
-      "eval_runtime": 1.1504,
-      "eval_samples_per_second": 906.647,
-      "eval_steps_per_second": 57.372,
+      "eval_loss": 0.4967799484729767,
+      "eval_matthews_correlation": 0.44251427534495513,
+      "eval_runtime": 0.8433,
+      "eval_samples_per_second": 1236.743,
+      "eval_steps_per_second": 78.26,
       "step": 536
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.5001268982887268,
-      "eval_matthews_correlation": 0.5202123212283704,
-      "eval_runtime": 0.6949,
-      "eval_samples_per_second": 1500.847,
-      "eval_steps_per_second": 94.972,
+      "eval_loss": 0.49384433031082153,
+      "eval_matthews_correlation": 0.46849580082104064,
+      "eval_runtime": 1.1521,
+      "eval_samples_per_second": 905.341,
+      "eval_steps_per_second": 57.289,
       "step": 804
     },
     {
       "epoch": 3.73,
-      "learning_rate": 4.180845058060293e-06,
-      "loss": 0.2539,
+      "grad_norm": 8.912487030029297,
+      "learning_rate": 6.865029316956087e-07,
+      "loss": 0.3522,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.561569333076477,
-      "eval_matthews_correlation": 0.5290831606897504,
-      "eval_runtime": 1.2387,
-      "eval_samples_per_second": 842.006,
-      "eval_steps_per_second": 53.281,
+      "eval_loss": 0.5385918021202087,
+      "eval_matthews_correlation": 0.430812413056651,
+      "eval_runtime": 0.8323,
+      "eval_samples_per_second": 1253.098,
+      "eval_steps_per_second": 79.295,
       "step": 1072
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1340,
-  "num_train_epochs": 5,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 191113458530124.0,
+  "total_flos": 192081608932020.0,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.6477448170002332e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 1.0221265871912396e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 34
+    "seed": 8
   }
 }

run-1/checkpoint-1072/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1aa22f290642ee01c58508f6341455213d65d2b747968e31a42fb22e7b7ee22
-size 4664
+oid sha256:29d6b485a188c4e5c57b6f3bb948e3315674066d3a6ec8f44d6d328263cd659b
+size 4984

run-1/checkpoint-268/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

run-1/checkpoint-268/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccdf837c8ebda4caa44681d02bb2d6ae6b721c17415e8e1a9bdb75243aad05a
+oid sha256:bc9878783b0818c688c28abea8a5d61ace7dcab7d3f290e5b80a5cde21639f4f
 size 267832560

run-1/checkpoint-268/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2819fceb92563ce2132bfcd7742f3a0af37662847dd7e7950649954455007212
+oid sha256:e636934686b41a0f79de6208f706315ddc2a3cfa0585cee3ba2d34a439b209db
 size 535727290

run-1/checkpoint-268/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33a9c26fe1adbe5f1000a1f3d74c1bc587be4f7b6690bc5588a81f70304c9d14
-size 14244
+oid sha256:1a7df60d1f16fe9e85b40c9a61615d24bef5f0ce05b0f715ad8da2204ad48db8
+size 14308

run-1/checkpoint-268/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f9dd8f51fd82f223470aaeacd6e7b0481b1ae891ad5c9a9bed8c63aa42e6b3a
+oid sha256:464e697567a35a41b5d63da1ecc000461d81bd321d5860f5da26db618d04341e
 size 1064

run-1/checkpoint-268/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4522326299878879,
+  "best_metric": 0.4141806938515634,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-268",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,24 +10,26 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.4801884889602661,
-      "eval_matthews_correlation": 0.4522326299878879,
-      "eval_runtime": 0.6893,
-      "eval_samples_per_second": 1513.095,
-      "eval_steps_per_second": 95.747,
+      "eval_loss": 0.5035493969917297,
+      "eval_matthews_correlation": 0.4141806938515634,
+      "eval_runtime": 0.7419,
+      "eval_samples_per_second": 1405.832,
+      "eval_steps_per_second": 88.96,
       "step": 268
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1340,
-  "num_train_epochs": 5,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
   "save_steps": 500,
   "total_flos": 0,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.6477448170002332e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 1.0221265871912396e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 34
+    "seed": 8
   }
 }

run-1/checkpoint-268/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1aa22f290642ee01c58508f6341455213d65d2b747968e31a42fb22e7b7ee22
-size 4664
+oid sha256:29d6b485a188c4e5c57b6f3bb948e3315674066d3a6ec8f44d6d328263cd659b
+size 4984

run-1/checkpoint-536/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

run-1/checkpoint-536/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d98edead287397dbc85e9965e55e0e9a63f182e2ec349fac928973b841db896
+oid sha256:362d9c0cd2587fbb0107cad0126e6f5d8cff717dff52b10facf7769e2fb5712d
 size 267832560

run-1/checkpoint-536/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af1eb72f05bdc789e62e12a02f45666b68ffc9a9e3b265cf587c59eb4f859615
+oid sha256:e5212b8745eb1c4c6ef881e3d21b4023283b2bc6765d8cb3aab22e3fe10e74e9
 size 535727290

run-1/checkpoint-536/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6ebe287cfea3dfa72a8b1b6f7c5dca99ab99027833636d010a42c39c8d98519
-size 14244
+oid sha256:d3c3a6d458d1ea31703d0759423a03a8df70fee2479aeb6598078341111b8adb
+size 14308

run-1/checkpoint-536/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:131ccd977f9f8b655127b0bfc9d5858f739a5117dd5605449b2124dee8f1f1b2
+oid sha256:b05a47d04eae8f5a42931783c79ad8a5775116597c4d7a406555dd541bfaf966
 size 1064

run-1/checkpoint-536/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4810794261012942,
+  "best_metric": 0.44251427534495513,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-536",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,39 +10,42 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.4801884889602661,
-      "eval_matthews_correlation": 0.4522326299878879,
-      "eval_runtime": 0.6893,
-      "eval_samples_per_second": 1513.095,
-      "eval_steps_per_second": 95.747,
+      "eval_loss": 0.5035493969917297,
+      "eval_matthews_correlation": 0.4141806938515634,
+      "eval_runtime": 0.7419,
+      "eval_samples_per_second": 1405.832,
+      "eval_steps_per_second": 88.96,
       "step": 268
     },
     {
       "epoch": 1.87,
-      "learning_rate": 1.0329146614031314e-05,
-      "loss": 0.4583,
+      "grad_norm": 4.896795749664307,
+      "learning_rate": 5.453884401804003e-06,
+      "loss": 0.4997,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5012368559837341,
-      "eval_matthews_correlation": 0.4810794261012942,
-      "eval_runtime": 1.1504,
-      "eval_samples_per_second": 906.647,
-      "eval_steps_per_second": 57.372,
+      "eval_loss": 0.4967799484729767,
+      "eval_matthews_correlation": 0.44251427534495513,
+      "eval_runtime": 0.8433,
+      "eval_samples_per_second": 1236.743,
+      "eval_steps_per_second": 78.26,
       "step": 536
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1340,
-  "num_train_epochs": 5,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 95441467104708.0,
+  "total_flos": 96116481642000.0,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.6477448170002332e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 1.0221265871912396e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 34
+    "seed": 8
   }
 }

run-1/checkpoint-536/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1aa22f290642ee01c58508f6341455213d65d2b747968e31a42fb22e7b7ee22
-size 4664
+oid sha256:29d6b485a188c4e5c57b6f3bb948e3315674066d3a6ec8f44d6d328263cd659b
+size 4984

run-1/checkpoint-804/config.json

@@ -20,6 +20,6 @@
   "sinusoidal_pos_embds": false,
   "tie_weights_": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.35.2",
+  "transformers_version": "4.38.2",
   "vocab_size": 30522
 }

run-1/checkpoint-804/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:945826e2756aee187ff6d9bdd54154b39351f77603e0170a083bc3c49be4ee68
+oid sha256:4784b2cdaf1f4f2a65b67673cf9a474f50aacc6b6b52a55770494552957df28b
 size 267832560

run-1/checkpoint-804/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ea911767fd5bd81c9ae263da864a0ce433894f85b467a23058011a3b4b7e2cb
+oid sha256:494174d39b2739ea5767bec872526ea91a8f51fb559ed3ecd20e2d63381bd46c
 size 535727290

run-1/checkpoint-804/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0420cf3993252b233c288946920f1af18011a1b61e0f617168a7cf0d3fe2092b
-size 14244
+oid sha256:65c4502cc2c96e2c95cfbd885846a4486d9bbe6f82fd2b8441148c27de597eb2
+size 14308

run-1/checkpoint-804/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:475f434ce1db47dc716bfd6101d5f9cecc5edefc32602d23d923f0f0f46628c3
+oid sha256:76cbf4faf8458eeab8085fe97b4e0f9442c5aa8273abf11a8f8bb22a481d6a86
 size 1064

run-1/checkpoint-804/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5202123212283704,
+  "best_metric": 0.46849580082104064,
   "best_model_checkpoint": "distilbert-base-uncased-finetuned-cola/run-1/checkpoint-804",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,48 +10,51 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.4801884889602661,
-      "eval_matthews_correlation": 0.4522326299878879,
-      "eval_runtime": 0.6893,
-      "eval_samples_per_second": 1513.095,
-      "eval_steps_per_second": 95.747,
+      "eval_loss": 0.5035493969917297,
+      "eval_matthews_correlation": 0.4141806938515634,
+      "eval_runtime": 0.7419,
+      "eval_samples_per_second": 1405.832,
+      "eval_steps_per_second": 88.96,
       "step": 268
     },
     {
       "epoch": 1.87,
-      "learning_rate": 1.0329146614031314e-05,
-      "loss": 0.4583,
+      "grad_norm": 4.896795749664307,
+      "learning_rate": 5.453884401804003e-06,
+      "loss": 0.4997,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.5012368559837341,
-      "eval_matthews_correlation": 0.4810794261012942,
-      "eval_runtime": 1.1504,
-      "eval_samples_per_second": 906.647,
-      "eval_steps_per_second": 57.372,
+      "eval_loss": 0.4967799484729767,
+      "eval_matthews_correlation": 0.44251427534495513,
+      "eval_runtime": 0.8433,
+      "eval_samples_per_second": 1236.743,
+      "eval_steps_per_second": 78.26,
       "step": 536
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.5001268982887268,
-      "eval_matthews_correlation": 0.5202123212283704,
-      "eval_runtime": 0.6949,
-      "eval_samples_per_second": 1500.847,
-      "eval_steps_per_second": 94.972,
+      "eval_loss": 0.49384433031082153,
+      "eval_matthews_correlation": 0.46849580082104064,
+      "eval_runtime": 1.1521,
+      "eval_samples_per_second": 905.341,
+      "eval_steps_per_second": 57.289,
       "step": 804
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1340,
-  "num_train_epochs": 5,
+  "max_steps": 1072,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
   "save_steps": 500,
-  "total_flos": 95441467104708.0,
+  "total_flos": 96116481642000.0,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.6477448170002332e-05,
-    "num_train_epochs": 5,
+    "learning_rate": 1.0221265871912396e-05,
+    "num_train_epochs": 4,
     "per_device_train_batch_size": 32,
-    "seed": 34
+    "seed": 8
   }
 }

run-1/checkpoint-804/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1aa22f290642ee01c58508f6341455213d65d2b747968e31a42fb22e7b7ee22
-size 4664
+oid sha256:29d6b485a188c4e5c57b6f3bb948e3315674066d3a6ec8f44d6d328263cd659b
+size 4984

runs/Mar16_01-46-29_6e5f088ca464/events.out.tfevents.1710554081.6e5f088ca464.226.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4eb0db1e584b1ca711fac69e781c89919befb1d668dd94d9c7557dc3b971aa
+size 6705

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d71decb8fd1c3b29f479f69dd55dfb41734b34761f0097d998f78bf9dd25bdb
+oid sha256:29d6b485a188c4e5c57b6f3bb948e3315674066d3a6ec8f44d6d328263cd659b
 size 4984