Training in progress, step 55000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97795a9879aa45dcdeb68ef66569d87bc46d68acf8067e0ffe4221c441f0f1d9
+oid sha256:b262f3940750b190d96db404d8b7be748afd37e7722c173c295ae970e72d408f
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb20288f5642839707b843422b2e8a11178186e15fcb967f97eedfe9cf2d48f
+oid sha256:c41267e907c3c64a9eab9a9be9e42135251f0170acce84b7512dcf74b73603d6
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f3fce24b65e03291953084259f05a0f8247857de1e16e3a8bb8d79a42679db
+oid sha256:bff383314706f04a5be47f7718a16317dcbc2e34ef67666665654cf6c6ee365b
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f3636d5d5906420899d9a721abefc725ca1bec46f94db174f2d813e8cafd619
+oid sha256:45a60ece43c7f2b86d8fa5a261371b3d68475d4bd4f09601e0100b9c7dc8846c
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:781aa7899ba1ef59504880d20205a5b23aa1436257b30b0eaef3ffd54fc88b2d
+oid sha256:8ec42c25eb7478ac84d4d9417b6c2bb3174731b719c2aa0a659b71f10e98687e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.353125544140693,
-  "global_step": 50000,
+  "epoch": 4.788438098554762,
+  "global_step": 55000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -686,11 +686,79 @@
       "eval_samples_per_second": 287.93,
       "eval_steps_per_second": 4.549,
       "step": 50000
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 5.470332478992507e-05,
+      "loss": 0.4189,
+      "step": 50500
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 5.399052636853316e-05,
+      "loss": 0.418,
+      "step": 51000
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 5.327807340052843e-05,
+      "loss": 0.4174,
+      "step": 51500
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 5.25661416730201e-05,
+      "loss": 0.4178,
+      "step": 52000
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 5.18563285019876e-05,
+      "loss": 0.4172,
+      "step": 52500
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 5.114738388115157e-05,
+      "loss": 0.4166,
+      "step": 53000
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 5.043806455560185e-05,
+      "loss": 0.4175,
+      "step": 53500
+    },
+    {
+      "epoch": 4.7,
+      "learning_rate": 4.972996720023507e-05,
+      "loss": 0.4169,
+      "step": 54000
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 4.90232665274781e-05,
+      "loss": 0.4159,
+      "step": 54500
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 4.8318136905147416e-05,
+      "loss": 0.4163,
+      "step": 55000
+    },
+    {
+      "epoch": 4.79,
+      "eval_loss": 0.3956509530544281,
+      "eval_runtime": 17.4712,
+      "eval_samples_per_second": 286.186,
+      "eval_steps_per_second": 4.522,
+      "step": 55000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 2.3548561921193332e+21,
+  "total_flos": 2.590349259484095e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb20288f5642839707b843422b2e8a11178186e15fcb967f97eedfe9cf2d48f
+oid sha256:c41267e907c3c64a9eab9a9be9e42135251f0170acce84b7512dcf74b73603d6
 size 449471589