Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b9408bc7ef7c9eb39691a48a2cbf17ea3aa66efd2ed70d96fefd9eaea1fd4d
+oid sha256:550d11d2e0d45d6a0d008261bef62de4360b487f887046f596e045ccd6f0a6eb
 size 69782384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2ae751e30da587c3d3d0dd22c95e22ea9ddf0b79ad50be76f082a54ba47c78
+oid sha256:5388aad62ba3c6868bf12ad11bc022fae098f88cd35d07a7860da2b8bdeef209
 size 139790651

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab585d317fb34a298382906257f2b36e2319b2919ce54e839f6bee5c2efb361b
+oid sha256:bc5c5eb75b44b8144a33c4463d137bd72be57e280cc3f9d5750a61e28416daac
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa65636b0fd309f3457173a286aced75e33b7c488917f478c3baadf2943a6311
+oid sha256:4597266b92ceab6117e6a70e4971c3980afac249cc4bfe8f85b293a0771ae1e4
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1600,
-  "best_metric": 2.1958162784576416,
-  "best_model_checkpoint": "./outputs/checkpoint-1600",
-  "epoch": 1.7372421281216068,
+  "best_global_step": 1800,
+  "best_metric": 2.1885855197906494,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 1.9543973941368078,
   "eval_steps": 200,
-  "global_step": 1600,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -296,6 +296,42 @@
       "eval_samples_per_second": 82.119,
       "eval_steps_per_second": 2.592,
       "step": 1600
+    },
+    {
+      "epoch": 1.791530944625407,
+      "grad_norm": 0.8802404403686523,
+      "learning_rate": 7.228664517545785e-05,
+      "loss": 2.1577,
+      "step": 1650
+    },
+    {
+      "epoch": 1.8458197611292073,
+      "grad_norm": 0.8591893911361694,
+      "learning_rate": 6.677308608327948e-05,
+      "loss": 2.161,
+      "step": 1700
+    },
+    {
+      "epoch": 1.9001085776330076,
+      "grad_norm": 0.8191171884536743,
+      "learning_rate": 6.137088176653491e-05,
+      "loss": 2.178,
+      "step": 1750
+    },
+    {
+      "epoch": 1.9543973941368078,
+      "grad_norm": 0.9448741674423218,
+      "learning_rate": 5.609813686323086e-05,
+      "loss": 2.1746,
+      "step": 1800
+    },
+    {
+      "epoch": 1.9543973941368078,
+      "eval_loss": 2.1885855197906494,
+      "eval_runtime": 7.3549,
+      "eval_samples_per_second": 81.85,
+      "eval_steps_per_second": 2.583,
+      "step": 1800
     }
   ],
   "logging_steps": 50,
@@ -324,7 +360,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.4811140929663795e+17,
+  "total_flos": 5.041672846318633e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null