Training in progress, step 45000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b937992da12590ba2ee2ecfa5a6224eb75cd0a6dbf99f744bec6042034768fdb
+oid sha256:97a8aafd7d380a84c68a1ffbee8decf87b37ec7c719432f14899f88f5dfd34dd
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe032267303d174768a4c71a5b4ab969ea1dd84441a01822ea3e2ec637af7091
+oid sha256:dd92ea740633d65a035d6e8d9e2b3088d967f47f404c7d4c321c9d904e2b2973
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9bf566fdf421530052a690839f4abb9b1083bf68461ba305086568aa88aeb4
+oid sha256:cc7980d1e1da965ebd42df03bdec2ef5751aa8b48365531bf2982e1266edc9f0
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bb55876e03a71e55e428a60dd59e185d61d2bbf026ccff833af7b992fa10a9a
+oid sha256:f024fb38cc3565fc6edb457594f564ce6662d349b0a725eb005eb23b1557c03f
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7c3bc66ef595b060943f43f042dfbc9f45a9f2c4def064a14535b0336d42b5a
+oid sha256:6392f10e3eab2d9c3514e9b24b388d66ca875971d7dffcecc6401ab79cc23127
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.4825004353125544,
-  "global_step": 40000,
+  "epoch": 3.917812989726624,
+  "global_step": 45000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -550,11 +550,79 @@
       "eval_samples_per_second": 276.137,
       "eval_steps_per_second": 4.363,
       "step": 40000
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 6.875774190311069e-05,
+      "loss": 0.4253,
+      "step": 40500
+    },
+    {
+      "epoch": 3.57,
+      "learning_rate": 6.807474478259389e-05,
+      "loss": 0.424,
+      "step": 41000
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 6.738861804531726e-05,
+      "loss": 0.4239,
+      "step": 41500
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 6.669953098278655e-05,
+      "loss": 0.4241,
+      "step": 42000
+    },
+    {
+      "epoch": 3.7,
+      "learning_rate": 6.600904004302253e-05,
+      "loss": 0.4238,
+      "step": 42500
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 6.531454815259442e-05,
+      "loss": 0.4225,
+      "step": 43000
+    },
+    {
+      "epoch": 3.79,
+      "learning_rate": 6.461760768262325e-05,
+      "loss": 0.4229,
+      "step": 43500
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 6.391839059274147e-05,
+      "loss": 0.4238,
+      "step": 44000
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 6.321706940430336e-05,
+      "loss": 0.421,
+      "step": 44500
+    },
+    {
+      "epoch": 3.92,
+      "learning_rate": 6.25138171578181e-05,
+      "loss": 0.4225,
+      "step": 45000
+    },
+    {
+      "epoch": 3.92,
+      "eval_loss": 0.4011038839817047,
+      "eval_runtime": 17.3314,
+      "eval_samples_per_second": 288.494,
+      "eval_steps_per_second": 4.558,
+      "step": 45000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 1.8838886777718807e+21,
+  "total_flos": 2.1193817451366423e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe032267303d174768a4c71a5b4ab969ea1dd84441a01822ea3e2ec637af7091
+oid sha256:dd92ea740633d65a035d6e8d9e2b3088d967f47f404c7d4c321c9d904e2b2973
 size 449471589