Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db6fb4a2aa7d542b006d930aad3c9e5c12d0aa28cc27d199bf5a4788e477b15
+oid sha256:6d43358df4a1c7314764ba0fe2ed5a5870e45a57353391b613fde581e836ab3b
 size 692169624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f949d9ba52af4b5ffb3a6a46d88c69e83cd000414c6970337b3a30bbd4610019
+oid sha256:4f2f0b2e53da0cb78e0898addd7f0d7ee9740bb889f24778ce0e19d2e9a7d309
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27f5e2500362b73e47f5681fd7a7663702665386d5af57fd9a924c1cc3fc44b
+oid sha256:27c798405ea53bdde5a57e4140c86669e859c2276c92a1b14a686d703b68d844
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011049723756906077,
+  "epoch": 0.022099447513812154,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 6.685,
       "eval_steps_per_second": 0.838,
       "step": 9
+    },
+    {
+      "epoch": 0.014732965009208104,
+      "grad_norm": 2.557511568069458,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 3.3922,
+      "step": 12
+    },
+    {
+      "epoch": 0.01841620626151013,
+      "grad_norm": 2.2613649368286133,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 2.6714,
+      "step": 15
+    },
+    {
+      "epoch": 0.022099447513812154,
+      "grad_norm": 2.2691195011138916,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 2.8087,
+      "step": 18
+    },
+    {
+      "epoch": 0.022099447513812154,
+      "eval_loss": 0.7028216123580933,
+      "eval_runtime": 205.2466,
+      "eval_samples_per_second": 6.685,
+      "eval_steps_per_second": 0.838,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.5312705439072256e+16,
+  "total_flos": 5.062541087814451e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null