Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10e88d5e63aa1f430ed14aaece2b3920ffc4ab1147c8a4162915e6f8ab83a9f9
+oid sha256:6137c48656511a4041b41fe82b23b2fd9080ce734a6db5e0143dd900d0d71296
 size 42487072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fdc48aee508967763ffe85f968559f99974c52333512c39eba622e43f17c52d
+oid sha256:20de964ab454e0c1409bd1b6e2dae9d382a7c63a5c41f718b0b07a805fb1d952
 size 21735354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b3ae3137845389cd30c83a794ea24e60625e4e5de5330fc48fc3909d3a4d43
+oid sha256:0923d445f321df35110251ce013719390c03945935abe7a84cbff340b8eba72c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.39215686274509803,
+  "epoch": 0.4411764705882353,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 119.356,
       "eval_steps_per_second": 15.266,
       "step": 40
+    },
+    {
+      "epoch": 0.4117647058823529,
+      "grad_norm": 9.598522186279297,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 8.0472,
+      "step": 42
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "grad_norm": 9.460302352905273,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.9261,
+      "step": 45
+    },
+    {
+      "epoch": 0.4411764705882353,
+      "eval_loss": 1.886256217956543,
+      "eval_runtime": 1.4284,
+      "eval_samples_per_second": 120.413,
+      "eval_steps_per_second": 15.402,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1406050800500736.0,
+  "total_flos": 1589448731000832.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null