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:edc9eaa64dec5c07dcd468d8f1803138339a3ae31a1c5ae68616457b55771289
+oid sha256:6ede2c8630156f4d30493e5f75fca203cde379edb2f9d20ff1d68af351efc3d9
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37dd0619b284c33e2a1b33dd612132d8130eac5a88b33a162943db5be3346b2e
+oid sha256:ecd73ed0b22797ad7080565bc487ff05b4271d36414f8cacb84d9d5e4f569b54
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96a464897d18d2f2ccf05e846c1054fa66e18da8e69d55ca3b097eaaff40019
+oid sha256:b77ec1d9059fbf29655439de7be3898314e6d6e711dfa2949a49c214c62651ad
 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": 0.0037094281298299847,
+  "epoch": 0.0074188562596599695,
   "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": 2.324,
       "eval_steps_per_second": 2.324,
       "step": 3
+    },
+    {
+      "epoch": 0.004945904173106646,
+      "grad_norm": 29.271102905273438,
+      "learning_rate": 8e-05,
+      "loss": 5.6493,
+      "step": 4
+    },
+    {
+      "epoch": 0.0061823802163833074,
+      "grad_norm": 34.93131637573242,
+      "learning_rate": 0.0001,
+      "loss": 3.9794,
+      "step": 5
+    },
+    {
+      "epoch": 0.0074188562596599695,
+      "grad_norm": 30.170530319213867,
+      "learning_rate": 0.00012,
+      "loss": 4.9902,
+      "step": 6
+    },
+    {
+      "epoch": 0.0074188562596599695,
+      "eval_loss": 3.892670154571533,
+      "eval_runtime": 73.758,
+      "eval_samples_per_second": 2.318,
+      "eval_steps_per_second": 2.318,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2225661850681344.0,
+  "total_flos": 4451323701362688.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null