Training in progress, step 50000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97a8aafd7d380a84c68a1ffbee8decf87b37ec7c719432f14899f88f5dfd34dd
+oid sha256:97795a9879aa45dcdeb68ef66569d87bc46d68acf8067e0ffe4221c441f0f1d9
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd92ea740633d65a035d6e8d9e2b3088d967f47f404c7d4c321c9d904e2b2973
+oid sha256:0cb20288f5642839707b843422b2e8a11178186e15fcb967f97eedfe9cf2d48f
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc7980d1e1da965ebd42df03bdec2ef5751aa8b48365531bf2982e1266edc9f0
+oid sha256:88f3fce24b65e03291953084259f05a0f8247857de1e16e3a8bb8d79a42679db
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f024fb38cc3565fc6edb457594f564ce6662d349b0a725eb005eb23b1557c03f
+oid sha256:7f3636d5d5906420899d9a721abefc725ca1bec46f94db174f2d813e8cafd619
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6392f10e3eab2d9c3514e9b24b388d66ca875971d7dffcecc6401ab79cc23127
+oid sha256:781aa7899ba1ef59504880d20205a5b23aa1436257b30b0eaef3ffd54fc88b2d
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.917812989726624,
-  "global_step": 45000,
+  "epoch": 4.353125544140693,
+  "global_step": 50000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -618,11 +618,79 @@
       "eval_samples_per_second": 288.494,
       "eval_steps_per_second": 4.558,
       "step": 45000
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 6.18088073702545e-05,
+      "loss": 0.4225,
+      "step": 45500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6.110221399222838e-05,
+      "loss": 0.4211,
+      "step": 46000
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 6.039562866071103e-05,
+      "loss": 0.4213,
+      "step": 46500
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 5.9686393768070895e-05,
+      "loss": 0.4207,
+      "step": 47000
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 5.897752048973475e-05,
+      "loss": 0.4193,
+      "step": 47500
+    },
+    {
+      "epoch": 4.18,
+      "learning_rate": 5.826634261264905e-05,
+      "loss": 0.4192,
+      "step": 48000
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 5.7554455195272715e-05,
+      "loss": 0.4193,
+      "step": 48500
+    },
+    {
+      "epoch": 4.27,
+      "learning_rate": 5.684203388517376e-05,
+      "loss": 0.418,
+      "step": 49000
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 5.6129254461650316e-05,
+      "loss": 0.4176,
+      "step": 49500
+    },
+    {
+      "epoch": 4.35,
+      "learning_rate": 5.541629279235954e-05,
+      "loss": 0.4185,
+      "step": 50000
+    },
+    {
+      "epoch": 4.35,
+      "eval_loss": 0.39864614605903625,
+      "eval_runtime": 17.3653,
+      "eval_samples_per_second": 287.93,
+      "eval_steps_per_second": 4.549,
+      "step": 50000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 2.1193817451366423e+21,
+  "total_flos": 2.3548561921193332e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd92ea740633d65a035d6e8d9e2b3088d967f47f404c7d4c321c9d904e2b2973
+oid sha256:0cb20288f5642839707b843422b2e8a11178186e15fcb967f97eedfe9cf2d48f
 size 449471589