Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a47810db67e1ee72bb7f191d0ca913c3cf851bed5704a671ea5bf0968f6ca76
+oid sha256:b57e6a53b0a6f445bbfe58bfb8eb4a0facf1a178ded76205a05772d31d1921d6
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7efc8fbf24f91135107314ed7b819d1b0d3184a9418c615c0d709ff24cc1bf57
+oid sha256:388a1d2158bf61f400eb1cd61b31752153e6ab5e31eeee0feb7dfb1297f3c0ea
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17cbebe4a9e2c8ad0c518b56649d7131ed53158aace72f907edc100be5f2ba1a
+oid sha256:b9abf883c2e9c09674e212674962f98f5fa416abc3e528367d43967e85b78711
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
+oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005399231647803967,
+  "epoch": 0.010798463295607933,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 17.679,
       "eval_steps_per_second": 8.84,
       "step": 13
+    },
+    {
+      "epoch": 0.008306510227390717,
+      "grad_norm": 0.30139827728271484,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.652,
+      "step": 20
+    },
+    {
+      "epoch": 0.010798463295607933,
+      "eval_loss": 0.587783694267273,
+      "eval_runtime": 57.3749,
+      "eval_samples_per_second": 17.673,
+      "eval_steps_per_second": 8.837,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4284339600752640.0,
+  "total_flos": 8568679201505280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null