Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:555f6c24353ec539973100e7bfc13b40acddc736e985e61e9cd4571108dd48dc
+oid sha256:9a2021356a5d0ec02bec53ddeca167712eb8152ff805af07d1d0d28529477247
 size 33572288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc1edad10bde5d5395a638792df9226cdaef5bac19506647b29750dfc8f968ef
+oid sha256:e31879ed71c274452bbda6a54da33007c20b85091b089adfa0c10ee8cb763ce1
 size 67216698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:585fddc4777b08565c6c3d5891526e512f43b18c6849f7dfec648d08d9b7a952
+oid sha256:80c21c7c5c6bed36f1e7b5a430ea5722c2257ea00a632c24bd72e7f6c8675c89
 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": 0.0004704720010350384,
+  "epoch": 0.0009409440020700768,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 51.91,
       "eval_steps_per_second": 25.955,
       "step": 10
+    },
+    {
+      "epoch": 0.0005645664012420461,
+      "grad_norm": 1.854500412940979,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 8.4177,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007057080015525577,
+      "grad_norm": 2.6493282318115234,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 8.3907,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007057080015525577,
+      "eval_loss": 2.0367188453674316,
+      "eval_runtime": 172.7142,
+      "eval_samples_per_second": 51.82,
+      "eval_steps_per_second": 25.91,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008468496018630691,
+      "grad_norm": 1.9623610973358154,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 8.0375,
+      "step": 18
+    },
+    {
+      "epoch": 0.0009409440020700768,
+      "eval_loss": 1.9632492065429688,
+      "eval_runtime": 172.4725,
+      "eval_samples_per_second": 51.892,
+      "eval_steps_per_second": 25.946,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 743814079709184.0,
+  "total_flos": 1431278607925248.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null