Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08d9e1ddad1eed3350161f029d34c7b069b4debe6e273ce6a97439e92d7eab4b
+oid sha256:1ef0d92a9d9cc6333f0de2ee09c73fda4362739b96219ea37dad5f061ab3fa0a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f8da2da0c711d68f0019bd54db49e63b64fe16c2992f8203e73ff93b13fd728
+oid sha256:81d564364eb846e4c5cf03b42b4356c598872e84266894a76c497e20c8f558ef
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb9755ddd10b8007ca74b6400241c0510340050721843c619fbd7d09ee355b03
+oid sha256:100a98efda01deac0d9d0ec043e13e0ceab192c7fc1329dd719aa17191cede2e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00046835665359171006,
+  "epoch": 0.0009367133071834201,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 1.411,
       "step": 9
+    },
+    {
+      "epoch": 0.0005620279843100521,
+      "grad_norm": 0.655875027179718,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.9647,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007025349803875652,
+      "grad_norm": 0.9592669010162354,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.1025,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007493706457467361,
+      "eval_loss": 1.0458663702011108,
+      "eval_runtime": 1196.2164,
+      "eval_samples_per_second": 7.515,
+      "eval_steps_per_second": 3.758,
+      "step": 16
+    },
+    {
+      "epoch": 0.0008430419764650782,
+      "grad_norm": 0.8475580215454102,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.012,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3802172328247296.0,
+  "total_flos": 7697080566939648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null