Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7fd699c55557ed55070429a00f0683c6e4782303df524e0788ed06fef3cf8c0
+oid sha256:e613f930d547332863452957fb45aa99653ab5ed08a4ec2af7186169d6916eef
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae78be996d1f5d59a47198d4c0588e6633e2a4e293e3706e977b2391ef5bd4ac
+oid sha256:a92016c661f957cfa6230a067c03e51d428c5fc5cc949b26801ad3821f179411
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49644ad8f5452e53758ca52013eb3650a3941bcec6083d72c46c935a677f7d88
+oid sha256:455977057132821379da92f1a77f9b1f540991d9dd7c684ba956aca72c970f71
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005361473979830646,
+  "epoch": 0.006127398834092166,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 13.837,
       "eval_steps_per_second": 1.73,
       "step": 63
+    },
+    {
+      "epoch": 0.005616782264584486,
+      "grad_norm": 2.7122933864593506,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 4.4688,
+      "step": 66
+    },
+    {
+      "epoch": 0.005872090549338326,
+      "grad_norm": 2.925189971923828,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 4.428,
+      "step": 69
+    },
+    {
+      "epoch": 0.006127398834092166,
+      "grad_norm": 2.7338027954101562,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 4.3209,
+      "step": 72
+    },
+    {
+      "epoch": 0.006127398834092166,
+      "eval_loss": 1.1138705015182495,
+      "eval_runtime": 1429.7869,
+      "eval_samples_per_second": 13.842,
+      "eval_steps_per_second": 1.73,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.859441830245171e+16,
+  "total_flos": 1.0125076377423053e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null