Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fe00387c8dbaef535157eb30f0bc322098a5c356657460a48747989ff2a1f14
+oid sha256:3a865ca33a5e47f374a75c9fc60ef8d9da1d025e4f273e40678515edd30452bf
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79d34588b4502dd8b6b6d6ef921a73da9ae501f2685671a5ac65dfd30a1533a2
+oid sha256:3aed2516b11a99d1cc878870c216bedfced197dbb8bf0472d4bf847f32d092ef
 size 320082106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c634ec1feddbb2fb10e8538cd879c5f6ee136aebc9b8c375b6e4d57f003cbcfd
+oid sha256:763215bea5d1a4c574744e6c699e3f1500c51935002767db23d636da54b8f9a6
 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": 8.019353372806372e-05,
+  "epoch": 0.00016038706745612744,
   "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": 5.446,
       "eval_steps_per_second": 2.723,
       "step": 3
+    },
+    {
+      "epoch": 0.0001069247116374183,
+      "grad_norm": 0.5141913294792175,
+      "learning_rate": 8e-05,
+      "loss": 0.8591,
+      "step": 4
+    },
+    {
+      "epoch": 0.00013365588954677288,
+      "grad_norm": 0.3930897116661072,
+      "learning_rate": 0.0001,
+      "loss": 0.5014,
+      "step": 5
+    },
+    {
+      "epoch": 0.00016038706745612744,
+      "grad_norm": 0.4725160002708435,
+      "learning_rate": 0.00012,
+      "loss": 0.6867,
+      "step": 6
+    },
+    {
+      "epoch": 0.00016038706745612744,
+      "eval_loss": 0.7054961323738098,
+      "eval_runtime": 1446.2097,
+      "eval_samples_per_second": 5.446,
+      "eval_steps_per_second": 2.723,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1960374605709312.0,
+  "total_flos": 3920749211418624.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null