Training in progress, step 20000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6efcea1f718e992622738eebec6655b308d8abaef61a2f7a2af6fa93b0ce7b9
+oid sha256:227bb459455ca9395e8701d0b76fa538ae5551af488261f8a6c040d98a6dded3
 size 893438545

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d606552814a4ba7950abd9e209968958ecfd2f24d817fd26ef28c35737c8054d
+oid sha256:9ee7451dd5ec81a01259d5968e23ec645d0c3962b135c90aa707004f25bc4403
 size 449471589

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c1cdccf174ece9de604197435ede54ec32a3b78eb6226070a07ab576a5585d
-size 15523
+oid sha256:cc90007b132e8f26a3d447fb1e8dee59d5ce3dfd07c853ec26d9c159e851307d
+size 15459

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd4ea5b486ac1940989e451ce41280116176be849f45b93fb6c79bbd63b9b878
+oid sha256:56d7925c4d371c4e7cd499e68da31588c0a08bf1a905f213b26db017a95291f6
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d524b4cb1391ef7e50966a3eef7ac714ecb6ed976eedf165d99a07d29c73b99
+oid sha256:a6464ca3b88e496d5d945a7955ac6cabd3c94f9611fe337e2e8a9af945aa679a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.870852564660803,
-  "global_step": 10000,
+  "epoch": 0.8705493166187864,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -142,11 +142,147 @@
       "eval_samples_per_second": 46.975,
       "eval_steps_per_second": 0.742,
       "step": 10000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.833541625738316e-05,
+      "loss": 0.3929,
+      "step": 10500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.809924007281187e-05,
+      "loss": 0.3906,
+      "step": 11000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.78525261765341e-05,
+      "loss": 0.3899,
+      "step": 11500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.759533544151208e-05,
+      "loss": 0.3892,
+      "step": 12000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.732773132571125e-05,
+      "loss": 0.3889,
+      "step": 12500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 9.705034604088048e-05,
+      "loss": 0.3865,
+      "step": 13000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.676213628592508e-05,
+      "loss": 0.3865,
+      "step": 13500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.64637187296151e-05,
+      "loss": 0.3867,
+      "step": 14000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.615516700201724e-05,
+      "loss": 0.3858,
+      "step": 14500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.583720443927501e-05,
+      "loss": 0.3853,
+      "step": 15000
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.36506548523902893,
+      "eval_runtime": 96.1419,
+      "eval_samples_per_second": 52.006,
+      "eval_steps_per_second": 0.822,
+      "step": 15000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.550863512110018e-05,
+      "loss": 0.3844,
+      "step": 15500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.517016728422667e-05,
+      "loss": 0.3834,
+      "step": 16000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.482188444052858e-05,
+      "loss": 0.3826,
+      "step": 16500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.446387252358614e-05,
+      "loss": 0.3824,
+      "step": 17000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 9.40962198674828e-05,
+      "loss": 0.3825,
+      "step": 17500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 9.371901718501017e-05,
+      "loss": 0.3804,
+      "step": 18000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 9.333314023958391e-05,
+      "loss": 0.3803,
+      "step": 18500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 9.293713767144707e-05,
+      "loss": 0.381,
+      "step": 19000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 9.253187106312908e-05,
+      "loss": 0.3793,
+      "step": 19500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.211744040810141e-05,
+      "loss": 0.3793,
+      "step": 20000
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 0.35968872904777527,
+      "eval_runtime": 95.0235,
+      "eval_samples_per_second": 52.619,
+      "eval_steps_per_second": 0.831,
+      "step": 20000
     }
   ],
   "max_steps": 100000,
   "num_train_epochs": 9,
-  "total_flos": 4.709861347295232e+20,
+  "total_flos": 9.419722694590464e+20,
   "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:cd49a349d77c455473f49543bf6e96561e293025b2e65d9b3c90c0be2504db32
+oid sha256:fb90956c2fc47703463b50fd267631dda0878fd140ff91c80ab2b7c4fc6e5708
 size 5615

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d606552814a4ba7950abd9e209968958ecfd2f24d817fd26ef28c35737c8054d
+oid sha256:9ee7451dd5ec81a01259d5968e23ec645d0c3962b135c90aa707004f25bc4403
 size 449471589

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd49a349d77c455473f49543bf6e96561e293025b2e65d9b3c90c0be2504db32
+oid sha256:fb90956c2fc47703463b50fd267631dda0878fd140ff91c80ab2b7c4fc6e5708
 size 5615