Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3f03d03ad5b765d043126fd38ff9cc4c5878ca062de27acb4a37e2619f11e5a
+oid sha256:526fda155baa5b41f117b17c28abd6435bb13a1639aa8ee1f4bd12deee2cab85
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d886dd0c8f9450468b5eb4f080520d6cd380cf772bc6ad2574b08713a9beb1f2
+oid sha256:0d0966261aee9f88ccc47f5b4cf680d514accb1f224a33d563b0d6fd2d23ca5a
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86ea9ecf8212256f66985dffc850d572baa911b54e6e606a48d0462b43101b11
+oid sha256:8daa47e5fa0e9a4f77b5b5a605545412b886dd6ab0a09e6b5cf492469c6c3e16
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08053691275167785,
+  "epoch": 0.1610738255033557,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 1.785,
       "eval_steps_per_second": 1.785,
       "step": 3
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 28.508464813232422,
+      "learning_rate": 8e-05,
+      "loss": 10.0268,
+      "step": 4
+    },
+    {
+      "epoch": 0.1342281879194631,
+      "grad_norm": 48.71175765991211,
+      "learning_rate": 0.0001,
+      "loss": 10.3586,
+      "step": 5
+    },
+    {
+      "epoch": 0.1610738255033557,
+      "grad_norm": 33.29041290283203,
+      "learning_rate": 0.00012,
+      "loss": 7.615,
+      "step": 6
+    },
+    {
+      "epoch": 0.1610738255033557,
+      "eval_loss": 4.839656829833984,
+      "eval_runtime": 4.4948,
+      "eval_samples_per_second": 1.78,
+      "eval_steps_per_second": 1.78,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1231436170395648.0,
+  "total_flos": 2462872340791296.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null