Training in progress, step 12000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5fee8207f36c1b9e1aef79d344f7acbd6caf908727460d1f50dc9581e679367
+oid sha256:8373da8a35ea2973595aaa754eb1ce4ce158cf82e530eb5f3d3263c26016eafe
 size 3871543575

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c41eab122f41bae21df10cfc712894e9e7bd882238893269188f80c7cb7ed36
+oid sha256:4f0c1477718f243e5c2feb4582e32e5aec1009dee1bba00375d74beb1c51e8b6
 size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5c6b922987d8fae6a92f121f201440c06fdcfa4c266591d2fae2c8688a68dd
+oid sha256:b3c214362304afce4731fa2f0b02f3ed0d948ac7e1592784b2fc59f7d950813d
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f93db576e82558e0b61e6e8b192bf5aac925b16461b57945ec850e5bbb2bc68
+oid sha256:6b3ea0646994a87a4341acac6bafbc5e858aebc07f9ae2570dcf52ec4e42c905
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90692e4f477275b35625e5ab8f213a0dc1ef39bc5eead93ee278d535c0ddbd06
+oid sha256:aba867de59f21a3b55b7c3b356f82675050d5da836e24f4ec1d060a995ce5ac1
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5642544787699252,
-  "global_step": 8000,
+  "epoch": 0.8463817181548878,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,11 +102,59 @@
       "learning_rate": 1.8046919211584273e-05,
       "loss": 1.6065,
       "step": 8000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.569505472339987e-05,
+      "loss": 1.6454,
+      "step": 8500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.3404218833084988e-05,
+      "loss": 1.6504,
+      "step": 9000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.1206887331469077e-05,
+      "loss": 1.6647,
+      "step": 9500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.134210454381382e-06,
+      "loss": 1.7032,
+      "step": 10000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.215571284652925e-06,
+      "loss": 1.6892,
+      "step": 10500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.478169205974455e-06,
+      "loss": 1.7176,
+      "step": 11000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.946634313732729e-06,
+      "loss": 1.7457,
+      "step": 11500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.645046185968865e-06,
+      "loss": 1.7474,
+      "step": 12000
     }
   ],
   "max_steps": 14178,
   "num_train_epochs": 1,
-  "total_flos": 8919658633003008.0,
+  "total_flos": 1.2217331547734016e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c41eab122f41bae21df10cfc712894e9e7bd882238893269188f80c7cb7ed36
+oid sha256:4f0c1477718f243e5c2feb4582e32e5aec1009dee1bba00375d74beb1c51e8b6
 size 1944201353

runs/May10_03-30-00_b2d6d2516701/events.out.tfevents.1683689456.b2d6d2516701.33377.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a70d3ed55f0b2c023c4ba5e7aa43ccd012e1164a2e7cee2be4a996bcbc83e55
-size 5404
+oid sha256:2baa34955eb027dbe249395493ed4910cb78637a0b8e2f32db680729a5f5a058
+size 6660