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:d3c7e7b15cf5bba11ba97f1535b9145966441de194bfa932e84483c4d6826d27
+oid sha256:07a46ed5298399c37f30ba81f0f4192a6fd1237b2d6b520794d4b9627f52953c
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a4b11058853192d1e287397ceb1e676d0a272afd675b1331ac6bbefc0685f8
+oid sha256:645f7ef00c370ce6f27ac7ff5e94850a7051879f0de94bbc380600badab51489
 size 501028338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85834ac3e90069542097fb220b33e7e34b360c94231d65ad3245d515255b91f5
+oid sha256:c949c6e825e9b6cc6e61770439637c62f618ab7c470350a60558b82879992b12
 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": 0.024891101431238332,
+  "epoch": 0.049782202862476664,
   "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": 2.8128,
       "step": 9
+    },
+    {
+      "epoch": 0.029869321717486,
+      "grad_norm": 1.0205752849578857,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.8206,
+      "step": 12
+    },
+    {
+      "epoch": 0.037336652146857496,
+      "grad_norm": 1.2089874744415283,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.5974,
+      "step": 15
+    },
+    {
+      "epoch": 0.03982576228998133,
+      "eval_loss": 0.6483936905860901,
+      "eval_runtime": 33.7553,
+      "eval_samples_per_second": 5.036,
+      "eval_steps_per_second": 2.518,
+      "step": 16
+    },
+    {
+      "epoch": 0.044803982576229,
+      "grad_norm": 1.031661033630371,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.53,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6506484439449600.0,
+  "total_flos": 1.30129688788992e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null