Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502c995bff1f03d53150715064ffe532c9c1b9ba1654eea0e26848942f2c55b8
+oid sha256:470557fe420fea4bb68dbcd360edf9d8f39f07cf8f0ce95e0ad493fd4eb0956a
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caad3b59325831391fc7ecbad33f6e9f023d5cda1e11d181be94a46753c2411f
+oid sha256:c0c99471171f7169c7423e26ad75d0148f3e7189b5f049783be1aa6e359ca5dc
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c1599935195b131f027fefd904b1041b9f3c0cdd237e663cf0fb4a514fb2923
+oid sha256:7617ba3cf9e8ddb856448f9dbc39430954823c370dbeabbecf9999c7ef8bb520
 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": 0.03590664272890485,
+  "epoch": 0.0718132854578097,
   "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": 2.8394,
       "step": 9
+    },
+    {
+      "epoch": 0.04308797127468582,
+      "grad_norm": 1.9224225282669067,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.1593,
+      "step": 12
+    },
+    {
+      "epoch": 0.05385996409335727,
+      "grad_norm": 1.8815566301345825,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.604,
+      "step": 15
+    },
+    {
+      "epoch": 0.05745062836624776,
+      "eval_loss": 1.2865763902664185,
+      "eval_runtime": 14.3,
+      "eval_samples_per_second": 8.252,
+      "eval_steps_per_second": 4.126,
+      "step": 16
+    },
+    {
+      "epoch": 0.06463195691202872,
+      "grad_norm": 2.7661185264587402,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.298,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3305470584422400.0,
+  "total_flos": 6610941168844800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null