Training in progress, step 15000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73489cdb01a4bb6cfe5252edc42886df8eebea1bb75734e470347a6522c023a1
+oid sha256:6839e8fd9262ae9437bdd437abd1bad3c3b82511739449fec8292a69e4d5b10b
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5920908de9e54da20823768f6ef8cc7bc5d55494a5080bb14683341420ff389e
+oid sha256:b31e0a533670bdb77786399adaddbe18894c2044c85487dcc9d0c41d55182f57
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b44d07e2d139a22d271aa72093cf081d67bc950fe387651d7d6d2f2dba45fb6
+oid sha256:f5d4271a4bb1cdb3db9b1359f873030d4eefa7f15660df68f0302617274cecfd
 size 15587

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:351b48ff70cf2e76c396612d9003a4396dc5f5b7c719dcf507ee09719e12672a
+oid sha256:e5a758f6bb9e87b722e928f89b126a9e2bb6d7d2276a24ffb9fee6ce69354628
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d524b4cb1391ef7e50966a3eef7ac714ecb6ed976eedf165d99a07d29c73b99
+oid sha256:5a1bbe8751f81eef53f97fffae533ac792444b305682e60f93b951d5e4e28b33
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8706251088281386,
-  "global_step": 10000,
+  "epoch": 1.305937663242208,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -142,11 +142,79 @@
       "eval_samples_per_second": 292.073,
       "eval_steps_per_second": 4.615,
       "step": 10000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.833541625738316e-05,
+      "loss": 0.4531,
+      "step": 10500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.809972296167543e-05,
+      "loss": 0.4531,
+      "step": 11000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 9.785303008093405e-05,
+      "loss": 0.4522,
+      "step": 11500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 9.759586023711756e-05,
+      "loss": 0.4504,
+      "step": 12000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 9.732827688303682e-05,
+      "loss": 0.4503,
+      "step": 12500
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 9.705034604088048e-05,
+      "loss": 0.4485,
+      "step": 13000
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 9.676213628592508e-05,
+      "loss": 0.448,
+      "step": 13500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 9.64637187296151e-05,
+      "loss": 0.4487,
+      "step": 14000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 9.615579416918834e-05,
+      "loss": 0.4475,
+      "step": 14500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 9.583720443927501e-05,
+      "loss": 0.4468,
+      "step": 15000
+    },
+    {
+      "epoch": 1.31,
+      "eval_loss": 0.4257063567638397,
+      "eval_runtime": 17.0089,
+      "eval_samples_per_second": 293.963,
+      "eval_steps_per_second": 4.645,
+      "step": 15000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 4.709861347295232e+20,
+  "total_flos": 7.064605817122141e+20,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5920908de9e54da20823768f6ef8cc7bc5d55494a5080bb14683341420ff389e
+oid sha256:b31e0a533670bdb77786399adaddbe18894c2044c85487dcc9d0c41d55182f57
 size 449471589