Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67fbc02091950196e9fa721e055f81fb79a3cbd03df0a64d1f0775e935f6b515
+oid sha256:2e8ab1a2824a6faf6f3a377bb88d17f7234fab6931475be2c088ed3eaa3b4f98
 size 598799664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:908ea104b72ec5774c027822f1f835c94af7515797b79b781a272b830c1791fa
+oid sha256:8ebc856d007f522c2090ea515f49183632dc302ef7a3bd56e2eee10957b0d3f0
 size 167923706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9734b39420282b78982ea070209fd83bff6546db9388f0335cc2dfa0968f7de0
+oid sha256:2fef718c3dca7761bb2f89ed5a815a6dc1b58ec2203c7e914a62a57cb6ea24f1
 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": 0.015203344735841885,
+  "epoch": 0.03040668947168377,
   "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": 7.0066,
       "step": 9
+    },
+    {
+      "epoch": 0.018244013683010263,
+      "grad_norm": 1.9478191137313843,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 6.8108,
+      "step": 12
+    },
+    {
+      "epoch": 0.02280501710376283,
+      "grad_norm": 1.9225983619689941,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 6.6399,
+      "step": 15
+    },
+    {
+      "epoch": 0.024325351577347016,
+      "eval_loss": 1.6876885890960693,
+      "eval_runtime": 32.1892,
+      "eval_samples_per_second": 8.605,
+      "eval_steps_per_second": 4.318,
+      "step": 16
+    },
+    {
+      "epoch": 0.027366020524515394,
+      "grad_norm": 1.5004922151565552,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 6.5679,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2622105216614400.0,
+  "total_flos": 5211434118021120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null