Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:065a62bf7bcb97eb269b25670c6f7f3deeb0b472aaa0daff8c729855902bb574
+oid sha256:14bb7aeed0a11e6ed9897a0616963001898e2ee58a912d51d1225c45e1c31f66
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49551666a79fd04078c4d9fefdf40a154196583d8c985287ace7023db349caa6
+oid sha256:5d24642f2a578c5cb112a5ce97f3c4bcf943e45db52d271add2d3ba373cc27e3
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819a1a4b78b08f06c5413d5e7c348d939353dc9fff83115785505860e0d3a348
+oid sha256:7ec40ab5ce32b0b6a10bff4a1d056084884854a2252ae4ce10c40291cbba5eef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e92785679980f3fcd23b14ce1acaffcae115e3e9164492d0e4b31775d32447
+oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0021232289412437223,
+  "epoch": 0.004246457882487445,
   "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": 26.003,
       "eval_steps_per_second": 13.001,
       "step": 13
+    },
+    {
+      "epoch": 0.0032665060634518802,
+      "grad_norm": 3.42970871925354,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 9.7219,
+      "step": 20
+    },
+    {
+      "epoch": 0.004246457882487445,
+      "eval_loss": 2.3963499069213867,
+      "eval_runtime": 99.1073,
+      "eval_samples_per_second": 26.012,
+      "eval_steps_per_second": 13.006,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2443123863060480.0,
+  "total_flos": 4682654070865920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null