Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ef18e08a9c17b2fb9b8ccde982a8239483cde795247827af7cb580503bb16a
+oid sha256:3ea5682a32e67553733161e24919b8256171520aaf9a72fb6461c8d023334b0f
 size 40036040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:944c8456b3e58c34cea3f7a300e3a051a0c84fd9656d9059a82ebdf9469ba1c5
+oid sha256:f8417a2e0bd9dee93861abecea4888b406a923187a5ec3ba715ab84d9297bc24
 size 20814996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d4ce98297dbe9ce16d8aeca4ab3d4f1f6ecfc395ce39836ce23e0f5364d053
+oid sha256:12da8cf14faf21b4ce97a203fbc022d55852967af79c15ad0d9fb35a64362e46
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73cbf425fe8e079f586aa4701c8340389c70a4705a912add7a2c0a4fa520c8a7
+oid sha256:ae75e092a889d5e969a2ae073023153d014a68766ac86876f11258c486a735da
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.023732270325391675,
+  "epoch": 0.026698804116065636,
   "eval_steps": 2,
-  "global_step": 16,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -191,6 +191,28 @@
       "eval_samples_per_second": 3.755,
       "eval_steps_per_second": 3.755,
       "step": 16
+    },
+    {
+      "epoch": 0.025215537220728654,
+      "grad_norm": 25.165361404418945,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.9765,
+      "step": 17
+    },
+    {
+      "epoch": 0.026698804116065636,
+      "grad_norm": 14.660453796386719,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.5801,
+      "step": 18
+    },
+    {
+      "epoch": 0.026698804116065636,
+      "eval_loss": 0.34035831689834595,
+      "eval_runtime": 151.1958,
+      "eval_samples_per_second": 3.757,
+      "eval_steps_per_second": 3.757,
+      "step": 18
     }
   ],
   "logging_steps": 1,
@@ -210,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2602068892188672.0,
+  "total_flos": 2927327503712256.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null