Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5124df57b2ed45fffb411669a3a985e856d5b6c82393ba4f1d94e024d5b557c2
+oid sha256:a01fc0b5aa9b24bb603baa06c9bbc6618e9160faa305e3b387707a3b7907d978
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba18d0bd944e9c2d035d504db97e922deb4be52d1d776bc51872efec3aa73690
+oid sha256:13d0214725796057b273c27bd8afc1e2bb4a776953fe5629aa13a377deda5bb4
 size 118090

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edebc115283b0d5273c85e1fc1434b7aa1992f62a3e91f56f0619e60b981c84e
+oid sha256:9cfaa812e4e772e2bea19a70de52bcb51d93084a77c635a5159573155257182c
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49685ea38b51bffb46bd2014185602864b5ec440144c3e89798dae470ede9799
+oid sha256:98c5d68680c3959b31f754e032a712c855d8cfb82a81c8724efeaab58e5bfcbc
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c115d869360fb0e8b86ff4b928f716326ea8c8e318512b4651434c18a33fdc6
+oid sha256:7ce80496f5ff016a991c7347d19ed4c4662d4190bb5444368af73527e582b904
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008505812305075135,
+  "epoch": 0.001701162461015027,
   "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": 155.113,
       "eval_steps_per_second": 38.804,
       "step": 3
+    },
+    {
+      "epoch": 0.0011341083073433513,
+      "grad_norm": 0.10966996103525162,
+      "learning_rate": 4e-05,
+      "loss": 10.3891,
+      "step": 4
+    },
+    {
+      "epoch": 0.001417635384179189,
+      "grad_norm": 0.10431879758834839,
+      "learning_rate": 5e-05,
+      "loss": 10.3901,
+      "step": 5
+    },
+    {
+      "epoch": 0.001701162461015027,
+      "grad_norm": 0.1112552359700203,
+      "learning_rate": 6e-05,
+      "loss": 10.3879,
+      "step": 6
+    },
+    {
+      "epoch": 0.001701162461015027,
+      "eval_loss": 10.386096000671387,
+      "eval_runtime": 19.5641,
+      "eval_samples_per_second": 151.809,
+      "eval_steps_per_second": 37.978,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 627629359104.0,
+  "total_flos": 1255258718208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null