Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:135197ad3195b359042613773b71696c5cf012cf3d066a9a2511d3838c3c35a9
+oid sha256:709e0174af7e7bfc36b2ca42177cb07663d435c4830e3ef2fd95156cc7684138
 size 409103316

run-3/checkpoint-1068/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2560b43fe84762a911d714a67fc5c2919fee7fafebcd308e914817d2dc8566ef
+oid sha256:638ef2c8256344c11b1952e1c4803f20ccd2b0e0c4c754cc573884f7f3399cea
 size 409103316

run-3/checkpoint-1068/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:854f66ea0079d652fdf4f15eeae49e6b2a1b1c1adb91ab7348289dfc954ec4ae
+oid sha256:bee566473dc2dae2be0d80c7c09cd94e61ef20ac726fbf26c3b5573a0884d8b7
 size 818327802

run-3/checkpoint-1068/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:250d95c13c6d803d5fd5b5d295b3c98a11c83777eb8bc2925a16ee9368fd5b57
+oid sha256:88efce74fbb2721dc5ac34e297a693ee9d8b613381cc20bc06917c3f551f452b
 size 14244

run-3/checkpoint-1068/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b015e282a908a0b0a7df9e3b39dbc5733ce7bd87981602ed5348ef6e624452a
+oid sha256:bf5c025422936aa654887c4e9b654e6c7b7b7d0a40a731b6b887b2c5d246abef
 size 1064

run-3/checkpoint-1068/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6060042381286621,
+  "best_metric": 0.5784130692481995,
   "best_model_checkpoint": "BERT-WMM/run-3/checkpoint-534",
   "epoch": 4.0,
   "eval_steps": 500,
@@ -10,52 +10,52 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7262910798122065,
-      "eval_loss": 0.6716192960739136,
-      "eval_runtime": 2.087,
-      "eval_samples_per_second": 1020.621,
-      "eval_steps_per_second": 64.208,
+      "eval_accuracy": 0.7549295774647887,
+      "eval_loss": 0.603171169757843,
+      "eval_runtime": 2.3997,
+      "eval_samples_per_second": 887.602,
+      "eval_steps_per_second": 55.84,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 8.963554382324219,
-      "learning_rate": 2.063992947537006e-05,
-      "loss": 0.5881,
+      "grad_norm": 9.50742244720459,
+      "learning_rate": 8.206819746059557e-06,
+      "loss": 0.6057,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7652582159624414,
-      "eval_loss": 0.6060042381286621,
-      "eval_runtime": 2.1035,
-      "eval_samples_per_second": 1012.591,
-      "eval_steps_per_second": 63.703,
+      "eval_accuracy": 0.7676056338028169,
+      "eval_loss": 0.5784130692481995,
+      "eval_runtime": 2.4488,
+      "eval_samples_per_second": 869.828,
+      "eval_steps_per_second": 54.722,
       "step": 534
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7680751173708921,
-      "eval_loss": 0.7311103343963623,
-      "eval_runtime": 1.9991,
-      "eval_samples_per_second": 1065.459,
-      "eval_steps_per_second": 67.029,
+      "eval_accuracy": 0.7657276995305164,
+      "eval_loss": 0.6564009189605713,
+      "eval_runtime": 2.4626,
+      "eval_samples_per_second": 864.929,
+      "eval_steps_per_second": 54.413,
       "step": 801
     },
     {
       "epoch": 3.75,
-      "grad_norm": 5.572795391082764,
-      "learning_rate": 2.470977472403458e-06,
-      "loss": 0.2017,
+      "grad_norm": 23.906795501708984,
+      "learning_rate": 9.825065893169892e-07,
+      "loss": 0.2903,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.7690140845070422,
-      "eval_loss": 0.9167852997779846,
-      "eval_runtime": 2.1137,
-      "eval_samples_per_second": 1007.72,
-      "eval_steps_per_second": 63.396,
+      "eval_accuracy": 0.7544600938967136,
+      "eval_loss": 0.7257726788520813,
+      "eval_runtime": 2.4681,
+      "eval_samples_per_second": 863.014,
+      "eval_steps_per_second": 54.293,
       "step": 1068
     }
   ],
@@ -68,9 +68,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.8808881478336665e-05,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 32,
-    "weight_decay": 1.7684940065509674e-05
+    "num_train_epochs": 4
   }
 }

run-3/checkpoint-1068/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6332b6cec121d165520e5db70de2b1562eb8b726bb5c9d5f52be871bd32d17a
+oid sha256:a8c637656beacaec83a46c1d786535828a5c615851f4d21b0069fcadd723fa83
 size 4856

run-3/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f8b5c2a4ec7c4ba90d6aff2ea3e383335216cad48a11aad9a4c34ba98ec717
+oid sha256:fed076af4c274336a1bbda01e7b9e95519d0bf0a1fe5c7f712970d2aa901f093
 size 409103316

run-3/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a15515177657ad8b28551b140b8ba13ae9ced7b249f415715555788f0ae3458f
+oid sha256:b2699e5ce5a66cbca0b105d6408b39db28914becd331e717afd744ad8431c462
 size 818327802

run-3/checkpoint-534/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc165f31ff0ffc674ac86349e2664c1e7bec0f07f3940fd4286bacf83dbab044
+oid sha256:50b42ca1a83d9e0487eef7bc4978f59ad97364890e28f585669fc8e766195ed9
 size 14244

run-3/checkpoint-534/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3db5ba154f6a7f69aebf98a2b4a4ac03660b2d28daa6f2a82bd1de57dd1df6d
+oid sha256:9844fc449bc7d92d10fa8131195695656fc5bae595590761350f9f767121bb98
 size 1064

run-3/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6060042381286621,
+  "best_metric": 0.5784130692481995,
   "best_model_checkpoint": "BERT-WMM/run-3/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7262910798122065,
-      "eval_loss": 0.6716192960739136,
-      "eval_runtime": 2.087,
-      "eval_samples_per_second": 1020.621,
-      "eval_steps_per_second": 64.208,
+      "eval_accuracy": 0.7549295774647887,
+      "eval_loss": 0.603171169757843,
+      "eval_runtime": 2.3997,
+      "eval_samples_per_second": 887.602,
+      "eval_steps_per_second": 55.84,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 8.963554382324219,
-      "learning_rate": 2.063992947537006e-05,
-      "loss": 0.5881,
+      "grad_norm": 9.50742244720459,
+      "learning_rate": 8.206819746059557e-06,
+      "loss": 0.6057,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7652582159624414,
-      "eval_loss": 0.6060042381286621,
-      "eval_runtime": 2.1035,
-      "eval_samples_per_second": 1012.591,
-      "eval_steps_per_second": 63.703,
+      "eval_accuracy": 0.7676056338028169,
+      "eval_loss": 0.5784130692481995,
+      "eval_runtime": 2.4488,
+      "eval_samples_per_second": 869.828,
+      "eval_steps_per_second": 54.722,
       "step": 534
     }
   ],
@@ -43,9 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.8808881478336665e-05,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 32,
-    "weight_decay": 1.7684940065509674e-05
+    "num_train_epochs": 4
   }
 }

run-3/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6332b6cec121d165520e5db70de2b1562eb8b726bb5c9d5f52be871bd32d17a
+oid sha256:a8c637656beacaec83a46c1d786535828a5c615851f4d21b0069fcadd723fa83
 size 4856

run-3/checkpoint-801/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05281ccfdb04657dc1f21097d3ad9814c9a9b02f644351f16dffed288040b382
+oid sha256:abcee7b655d87d819ba748aa8f11b89f8184a75c41ea3f5cc09ed28b8dd04dde
 size 409103316

run-3/checkpoint-801/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27ea57bff0992ea25dfd5bf56db87bf04d8cd5bd28a538a99a2d7764f24c4a2d
+oid sha256:1b4d09b23a9d36890a6ed4f07e4aa3231a59c99ec420ee4282010c427b8c1c25
 size 818327802

run-3/checkpoint-801/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb690786753304d1db2cd6b182863e5aa8196fd7b3d7323f4e394214c3dc44f0
+oid sha256:1f2e88e818a2ba76e34870352cb30ede96939fd3b25fc6442146490e0caecf29
 size 14244

run-3/checkpoint-801/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3575a4ca08ff450ace7dcb5ea12993a659670863eefbcb00aa5df4d3ebd0c5
+oid sha256:60b556c69d4b9a7a2ce657180051c90827c184737105bee587768464e8ffe74c
 size 1064

run-3/checkpoint-801/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6060042381286621,
+  "best_metric": 0.5784130692481995,
   "best_model_checkpoint": "BERT-WMM/run-3/checkpoint-534",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7262910798122065,
-      "eval_loss": 0.6716192960739136,
-      "eval_runtime": 2.087,
-      "eval_samples_per_second": 1020.621,
-      "eval_steps_per_second": 64.208,
+      "eval_accuracy": 0.7549295774647887,
+      "eval_loss": 0.603171169757843,
+      "eval_runtime": 2.3997,
+      "eval_samples_per_second": 887.602,
+      "eval_steps_per_second": 55.84,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 8.963554382324219,
-      "learning_rate": 2.063992947537006e-05,
-      "loss": 0.5881,
+      "grad_norm": 9.50742244720459,
+      "learning_rate": 8.206819746059557e-06,
+      "loss": 0.6057,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7652582159624414,
-      "eval_loss": 0.6060042381286621,
-      "eval_runtime": 2.1035,
-      "eval_samples_per_second": 1012.591,
-      "eval_steps_per_second": 63.703,
+      "eval_accuracy": 0.7676056338028169,
+      "eval_loss": 0.5784130692481995,
+      "eval_runtime": 2.4488,
+      "eval_samples_per_second": 869.828,
+      "eval_steps_per_second": 54.722,
       "step": 534
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7680751173708921,
-      "eval_loss": 0.7311103343963623,
-      "eval_runtime": 1.9991,
-      "eval_samples_per_second": 1065.459,
-      "eval_steps_per_second": 67.029,
+      "eval_accuracy": 0.7657276995305164,
+      "eval_loss": 0.6564009189605713,
+      "eval_runtime": 2.4626,
+      "eval_samples_per_second": 864.929,
+      "eval_steps_per_second": 54.413,
       "step": 801
     }
   ],
@@ -52,9 +52,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 3.8808881478336665e-05,
-    "num_train_epochs": 4,
-    "per_device_train_batch_size": 32,
-    "weight_decay": 1.7684940065509674e-05
+    "num_train_epochs": 4
   }
 }

run-3/checkpoint-801/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6332b6cec121d165520e5db70de2b1562eb8b726bb5c9d5f52be871bd32d17a
+oid sha256:a8c637656beacaec83a46c1d786535828a5c615851f4d21b0069fcadd723fa83
 size 4856

run-4/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
+oid sha256:709e0174af7e7bfc36b2ca42177cb07663d435c4830e3ef2fd95156cc7684138
 size 409103316

run-4/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8b54fc5e8c9423b8eb78032472c72dce9ff03db39846d1622f31a3d6911c46
+oid sha256:52ef4431d2c45c5021200b1e749d9a863141163026b276944e492c1db9ee3f59
 size 818327802

run-4/checkpoint-267/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d605219d0cdfe1356d19dfc261c4f045664dbc44ddf04517d0b2ebd1dab264c7
+oid sha256:44c8fc955f6ab66538b705aa40f6ebb08474ec445464a7a19ca29971b9fc42d4
 size 1064

run-4/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6019130349159241,
+  "best_metric": 0.6081846952438354,
   "best_model_checkpoint": "BERT-WMM/run-4/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,23 +10,23 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7563380281690141,
-      "eval_loss": 0.6019130349159241,
-      "eval_runtime": 2.4566,
-      "eval_samples_per_second": 867.035,
-      "eval_steps_per_second": 54.546,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6081846952438354,
+      "eval_runtime": 2.4392,
+      "eval_samples_per_second": 873.231,
+      "eval_steps_per_second": 54.936,
       "step": 267
     }
   ],
   "logging_steps": 500,
-  "max_steps": 801,
+  "max_steps": 1335,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "per_device_train_batch_size": 32
+    "num_train_epochs": 5
   }
 }

run-4/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
 size 4856

run-4/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c26a4990298c617435add4fef099a107381df4b5d4dd2ceb1932c28c743541
+oid sha256:976557a36bef1a4a492485f3f6cb8948205b7b3a9ea05ce8ce0eb8982fcc1d9e
 size 409103316

run-4/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c82d05f4ce26f22c9acaa7998473a49f5f6cbfcd52e5fa856d9f347b60ad8c
+oid sha256:890b6f5cc14af75c85002de6e2745609f1bf02f4a33a71cd0af847d31243fe8a
 size 818327802

run-4/checkpoint-534/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda5eab8086c3361f01b6da1d0d501e5d7ffcc15041db5c9a3384c00b843300f
+oid sha256:5e2aa06609570d504e0cfaf6c3bd801e1681706921a7512c6ccb9eded784901f
 size 1064

run-4/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5817901492118835,
+  "best_metric": 0.5776590704917908,
   "best_model_checkpoint": "BERT-WMM/run-4/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,39 +10,39 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7563380281690141,
-      "eval_loss": 0.6019130349159241,
-      "eval_runtime": 2.4566,
-      "eval_samples_per_second": 867.035,
-      "eval_steps_per_second": 54.546,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6081846952438354,
+      "eval_runtime": 2.4392,
+      "eval_samples_per_second": 873.231,
+      "eval_steps_per_second": 54.936,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.674468994140625,
-      "learning_rate": 5.7987153604787005e-06,
-      "loss": 0.6061,
+      "grad_norm": 9.532360076904297,
+      "learning_rate": 9.65168237740807e-06,
+      "loss": 0.6057,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7619718309859155,
-      "eval_loss": 0.5817901492118835,
-      "eval_runtime": 2.4611,
-      "eval_samples_per_second": 865.469,
-      "eval_steps_per_second": 54.447,
+      "eval_accuracy": 0.7657276995305164,
+      "eval_loss": 0.5776590704917908,
+      "eval_runtime": 2.4594,
+      "eval_samples_per_second": 866.069,
+      "eval_steps_per_second": 54.485,
       "step": 534
     }
   ],
   "logging_steps": 500,
-  "max_steps": 801,
+  "max_steps": 1335,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 349221394826640.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "per_device_train_batch_size": 32
+    "num_train_epochs": 5
   }
 }

run-4/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
 size 4856

run-4/checkpoint-801/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d7f234a18b08d68556eb791d0055c0b179dd8190747f6d104dae29ea9eda1d
+oid sha256:22b99fd8821bb6a7a58373b3e00909c671d6605dea0dd95a2c9cb3761b3b7f4e
 size 409103316

run-4/checkpoint-801/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cb41a29b069558e60295633a1200ae5a46374d86a3d3f48077ca97f9aa46387
+oid sha256:62a624295ad87feed2451e9981cc71ab700084e2468c6ef4e3d6a128b0f68b6c
 size 818327802

run-4/checkpoint-801/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cbdc9fc2ef477673574bd96dbcbae5c7987ba9b5b853636ae08a8f9164bbb32
+oid sha256:6d4fd24f628450570301e96568f256a50cad9a43cd0a510b6a50e86be9f9a3a5
 size 1064

run-4/checkpoint-801/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5817901492118835,
+  "best_metric": 0.5776590704917908,
   "best_model_checkpoint": "BERT-WMM/run-4/checkpoint-534",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -10,48 +10,48 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7563380281690141,
-      "eval_loss": 0.6019130349159241,
-      "eval_runtime": 2.4566,
-      "eval_samples_per_second": 867.035,
-      "eval_steps_per_second": 54.546,
+      "eval_accuracy": 0.7577464788732394,
+      "eval_loss": 0.6081846952438354,
+      "eval_runtime": 2.4392,
+      "eval_samples_per_second": 873.231,
+      "eval_steps_per_second": 54.936,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.674468994140625,
-      "learning_rate": 5.7987153604787005e-06,
-      "loss": 0.6061,
+      "grad_norm": 9.532360076904297,
+      "learning_rate": 9.65168237740807e-06,
+      "loss": 0.6057,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7619718309859155,
-      "eval_loss": 0.5817901492118835,
-      "eval_runtime": 2.4611,
-      "eval_samples_per_second": 865.469,
-      "eval_steps_per_second": 54.447,
+      "eval_accuracy": 0.7657276995305164,
+      "eval_loss": 0.5776590704917908,
+      "eval_runtime": 2.4594,
+      "eval_samples_per_second": 866.069,
+      "eval_steps_per_second": 54.485,
       "step": 534
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.7582159624413145,
-      "eval_loss": 0.6465383768081665,
-      "eval_runtime": 2.4941,
-      "eval_samples_per_second": 854.016,
-      "eval_steps_per_second": 53.727,
+      "eval_accuracy": 0.7690140845070422,
+      "eval_loss": 0.6647635102272034,
+      "eval_runtime": 2.4523,
+      "eval_samples_per_second": 868.556,
+      "eval_steps_per_second": 54.642,
       "step": 801
     }
   ],
   "logging_steps": 500,
-  "max_steps": 801,
+  "max_steps": 1335,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 349221394826640.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "per_device_train_batch_size": 32
+    "num_train_epochs": 5
   }
 }

run-4/checkpoint-801/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
 size 4856

runs/Apr19_08-35-52_21d31c708e60/events.out.tfevents.1713517318.21d31c708e60.946.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3dc83e8492bb33036fe1c271a9d1d2b3531582185b77e860f0ebc378b9e5bb4
+size 7285

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8c637656beacaec83a46c1d786535828a5c615851f4d21b0069fcadd723fa83
+oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
 size 4856