Training in progress, step 12000

config.json

@@ -31,7 +31,7 @@
   "pad_token_id": 1,
   "scale_embedding": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.28.0",
   "use_cache": true,
   "vocab_size": 128112
 }

last-checkpoint/config.json

@@ -31,7 +31,7 @@
   "pad_token_id": 1,
   "scale_embedding": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
+  "transformers_version": "4.28.0",
   "use_cache": true,
   "vocab_size": 128112
 }

last-checkpoint/generation_config.json

@@ -6,5 +6,5 @@
   "max_length": 200,
   "num_beams": 5,
   "pad_token_id": 1,
-  "transformers_version": "4.28.1"
+  "transformers_version": "4.28.0"
 }

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a344de794efe76499e05226f84f9b9eb183ce1856b9f543366c91090aa50d5
+oid sha256:6d8ba0729e30b9e5881d5caf971c412cd008a797ec6df264f9ce2ab2dc676fe5
 size 3871543575

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9644cb39fc77ce0ecf8404c68767bf11e83b492f019e8898a2c4793d943f36
+oid sha256:7d058b3df03b01ceeb1e8e16160c317d335c85329170d0defffb0885d4b38dba
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48ad0a43aae89b9c2d626e990511e66a4021355e52a4c9454762a9fb104c6dc4
+oid sha256:8a51646c5ca5ad6b2ed000ef8068a62b9fc23eb4d20a88c1d7e7d6d9bc724c2b
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466cc5f8b444b6e6a08a358b89d91b894e9359170249f4e3593cf66128c9e459
+oid sha256:b5d8c186c458ec7fc62528255f98794d112763525bca0fe822708873efed374e
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988143f54fcd42be170761e4e90014713b8da045b4b00b0b1cea0538e6c4a720
+oid sha256:6372f050fec8b9f728b07360e9c0cfeab517903b038f122fa81a78a1a0d2f1aa
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0847987619380757,
-  "global_step": 8000,
+  "epoch": 0.12719814290711356,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,11 +102,59 @@
       "learning_rate": 6.055512651614955e-07,
       "loss": 1.8569,
       "step": 8000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.433319705022791e-07,
+      "loss": 1.8883,
+      "step": 8500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 6.811883886794167e-07,
+      "loss": 1.8776,
+      "step": 9000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 7.190448068565545e-07,
+      "loss": 1.8876,
+      "step": 9500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 7.569012250336922e-07,
+      "loss": 1.8702,
+      "step": 10000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 7.947576432108301e-07,
+      "loss": 1.8573,
+      "step": 10500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.325383485516135e-07,
+      "loss": 1.857,
+      "step": 11000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 8.703947667287513e-07,
+      "loss": 1.8565,
+      "step": 11500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.08251184905889e-07,
+      "loss": 1.831,
+      "step": 12000
     }
   ],
   "max_steps": 943410,
   "num_train_epochs": 10,
-  "total_flos": 4555211547377664.0,
+  "total_flos": 6830201558089728.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e2c6df9f665ed1fd6913a2479257d67dc5550faf5e1eabf5b1b442b388390f
+oid sha256:a6bf4419503f7813df66a605111bbb0f133a163bc1b9d161b51462af15dbefd1
 size 3771

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd9644cb39fc77ce0ecf8404c68767bf11e83b492f019e8898a2c4793d943f36
+oid sha256:7d058b3df03b01ceeb1e8e16160c317d335c85329170d0defffb0885d4b38dba
 size 1944201353

runs/May11_01-55-45_3f2db86f76b4/1683771189.4238312/events.out.tfevents.1683771189.3f2db86f76b4.1020.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562b6a87ac7dbbbafaf11b7c1b61d054b99ff80b51c8d633ba8cb6520b3f9b3f
+size 6187

runs/May11_01-55-45_3f2db86f76b4/events.out.tfevents.1683771189.3f2db86f76b4.1020.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff0c68c70d670e76460ea9b6ca7664824eb2264c60f1be14fa7fdaa77c1fce1c
+size 5720

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51e2c6df9f665ed1fd6913a2479257d67dc5550faf5e1eabf5b1b442b388390f
+oid sha256:a6bf4419503f7813df66a605111bbb0f133a163bc1b9d161b51462af15dbefd1
 size 3771