Training in progress, step 41000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9879d5d88e7644494f4c879b1c5e524603249d32b69969a0534f73a0d99cdd8
+oid sha256:a43c2a0afd3692b4457c78e060bd95a6ca8422aa3f2bfb48776d966c67148820
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b43d2d95bf538247d49799d209038264216cbb911042f24a24e56175bd002ec5
+oid sha256:cb247ef281f39dbf138924be64b77fed104e544ac60daad36b17f01b15edabf4
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78de93de67391223b4c448919361f3b2f57691bd51a633014c5f582b70c0d977
+oid sha256:83988fc1574bdb56177858ad2504e5d5e90771242080ec94288ec2934ea05174
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aeb9cc77150e881276f00e59441fb5620f10d8b951379e0f05e5c2a60199333
+oid sha256:a519ef81b846f8a03a3bd8bed22cf3df79611baad6f40e402df6bfc345f1aa61
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.7,
+  "epoch": 2.7333333333333334,
   "eval_steps": 500,
-  "global_step": 40500,
+  "global_step": 41000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2858,6 +2858,41 @@
       "learning_rate": 2.006666666666667e-06,
       "loss": 0.0529,
       "step": 40500
+    },
+    {
+      "epoch": 2.7066666666666666,
+      "grad_norm": 0.24057607352733612,
+      "learning_rate": 1.9622222222222224e-06,
+      "loss": 0.0537,
+      "step": 40600
+    },
+    {
+      "epoch": 2.7133333333333334,
+      "grad_norm": 0.22103776037693024,
+      "learning_rate": 1.9182222222222225e-06,
+      "loss": 0.0499,
+      "step": 40700
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.23199285566806793,
+      "learning_rate": 1.873777777777778e-06,
+      "loss": 0.0574,
+      "step": 40800
+    },
+    {
+      "epoch": 2.7266666666666666,
+      "grad_norm": 0.3680346608161926,
+      "learning_rate": 1.8293333333333336e-06,
+      "loss": 0.0455,
+      "step": 40900
+    },
+    {
+      "epoch": 2.7333333333333334,
+      "grad_norm": 0.11471223831176758,
+      "learning_rate": 1.784888888888889e-06,
+      "loss": 0.046,
+      "step": 41000
     }
   ],
   "logging_steps": 100,
@@ -2877,7 +2912,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.865117827072e+16,
+  "total_flos": 9.986909405184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null