Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d672a1575b1f21621fac1db7adb929e5744de2aabb7381afbc512d8312f215
+oid sha256:e3262445aea116ed7fe4a43b9989a214dd1cee6e9955da79ac9177b64919d6a8
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9795985dbbc5d90ddee94d8b261ea5b0d3730d43fe21749ad91acae644263c
+oid sha256:5e8f53be7f0e4bb665397ab9bab0822757d4218d90c5d7498328617ae98d39d2
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9abf883c2e9c09674e212674962f98f5fa416abc3e528367d43967e85b78711
+oid sha256:f6772af577974c8afd4f01c292dee37aefb71155f4658c2cd442b9995c16c293
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010798463295607933,
+  "epoch": 0.0161976949434119,
   "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": 17.638,
       "eval_steps_per_second": 8.819,
       "step": 26
+    },
+    {
+      "epoch": 0.012459765341086075,
+      "grad_norm": 0.3194844126701355,
+      "learning_rate": 0.0001,
+      "loss": 0.6237,
+      "step": 30
+    },
+    {
+      "epoch": 0.0161976949434119,
+      "eval_loss": 0.5683814883232117,
+      "eval_runtime": 57.4235,
+      "eval_samples_per_second": 17.658,
+      "eval_steps_per_second": 8.829,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8568679201505280.0,
+  "total_flos": 1.285301880225792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null