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:b450e3288e80b175beb99aa8ce8eea811fce52f96af9ba0e7c238759c3ac5b92
+oid sha256:95eedd15f81c00848ff5e624d580bdaa62eb2c9ffed022039bed2b6f5b7ddedf
 size 201353800

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef45302779bd43020a3495a88b9e75e4299ece932d2ff318c3dfeaa3c6bf7bd
+oid sha256:ec073eb4a557da66b00b4cdf0452053edea242e2570d55b16ddfa08c5b869c2f
 size 102462970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54e4775648a48ac53be64e73dbddaaa09be7325092a28a30012be1516415332e
+oid sha256:42b69e81c7062c121b0530b668ff1a856987a6b215a72814ca005d799b3ead3c
 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": 0.06552006552006552,
+  "epoch": 0.07371007371007371,
   "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": 23.636,
       "eval_steps_per_second": 2.963,
       "step": 40
+    },
+    {
+      "epoch": 0.0687960687960688,
+      "grad_norm": 4.837084770202637,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 9.8265,
+      "step": 42
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "grad_norm": 4.688211441040039,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.6876,
+      "step": 45
+    },
+    {
+      "epoch": 0.07371007371007371,
+      "eval_loss": 2.300471782684326,
+      "eval_runtime": 43.5151,
+      "eval_samples_per_second": 23.647,
+      "eval_steps_per_second": 2.964,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9900661973975040.0,
+  "total_flos": 1.113824472072192e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null