Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed090d487cdc9b5aa3341481357254b238cfd291f94ab79b0f143526da57202
+oid sha256:655cdb218ab6e19e581b0f2d91de16a334330ed258f148ab5b53bd9bf545af95
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72c21c0ece7af4b4a9cf8ca83046e312bc388078c867b0c13c7a7fce691a9e90
+oid sha256:3239e81df1f60d38c1231feca4f12fdafcc850f588d26237dc2d6d6ba66328d4
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8f742328bfffa68d3697fe4655cdfe31ad19b761f081134e1ec9c8c44b0fce
+oid sha256:1403f5f6dad417051678c35178d95263c603148a177f023926cdbed3ff3e125f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baae720e33260fead254c87141d85e241b839ae924033bfd9652fb777f3f1bf0
+oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012949733451319795,
+  "epoch": 0.0017266311268426392,
   "eval_steps": 13,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,35 @@
       "learning_rate": 0.0001,
       "loss": 6.3389,
       "step": 30
+    },
+    {
+      "epoch": 0.0014244706796451773,
+      "grad_norm": 3.460523843765259,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 6.5699,
+      "step": 33
+    },
+    {
+      "epoch": 0.0015539680141583752,
+      "grad_norm": 2.5011720657348633,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 6.2508,
+      "step": 36
+    },
+    {
+      "epoch": 0.0016834653486715733,
+      "grad_norm": 3.5199382305145264,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 6.1756,
+      "step": 39
+    },
+    {
+      "epoch": 0.0016834653486715733,
+      "eval_loss": 1.5250167846679688,
+      "eval_runtime": 956.8088,
+      "eval_samples_per_second": 10.195,
+      "eval_steps_per_second": 5.098,
+      "step": 39
     }
   ],
   "logging_steps": 3,
@@ -120,7 +149,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9801969665310720.0,
+  "total_flos": 1.306929288708096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null