Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec2ea68333a614d42e9906b4c0123ea9bd2806dfabd0b395b99fc032edd38eb
+oid sha256:283334a2d347839e8a7ff8deb0f9ae786bba66cf28a808e64685c440d20ea7d0
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fd83b05dbe1178aa7de56dcabd9c0941ac3537da28ec906b02e3678860c627
+oid sha256:ec396f976c616c82b9b38c2d72895f7c781c5d75e31b9e5a3f2f9d7ed3587864
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
+oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
+oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012223789374706159,
+  "epoch": 0.018335684062059238,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 358.019,
       "eval_steps_per_second": 179.009,
       "step": 26
+    },
+    {
+      "epoch": 0.014104372355430184,
+      "grad_norm": 0.0335276760160923,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 10.3736,
+      "step": 30
+    },
+    {
+      "epoch": 0.018335684062059238,
+      "eval_loss": 10.371171951293945,
+      "eval_runtime": 2.5173,
+      "eval_samples_per_second": 355.933,
+      "eval_steps_per_second": 177.966,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 378229063680.0,
+  "total_flos": 578658140160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null