Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99294e9aaee4608588c575eb818274e3b8f571a3e9647c7706d76f486e1c4191
+oid sha256:64f582474f4a585678c483ac9fff1f2efcec06042b0a0c19e1e1cd7fec71027e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aafc86b0beccde8235997842bb0ceaf2ebf4b988d7c6779cd338f7b9ea817b0
+oid sha256:994cf1b5b32fbf07cc830c8ccc63aaaf1e553017f8c351309d8100ebe998867a
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332759cf7b5cf921f7c9ebfe29466512b01ff3dba8f0377398688b0a48981a95
+oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d20cdfdd80bd4f7336e0d1d85ea3a727e6acd58210dc60f9f2cd451325f653
+oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006696428571428571,
+  "epoch": 0.013392857142857142,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 13.979,
       "eval_steps_per_second": 1.747,
       "step": 9
+    },
+    {
+      "epoch": 0.008928571428571428,
+      "grad_norm": 4.432471752166748,
+      "learning_rate": 4.993910125649561e-05,
+      "loss": 7.6704,
+      "step": 12
+    },
+    {
+      "epoch": 0.011160714285714286,
+      "grad_norm": 5.1014227867126465,
+      "learning_rate": 4.962019382530521e-05,
+      "loss": 7.1247,
+      "step": 15
+    },
+    {
+      "epoch": 0.013392857142857142,
+      "grad_norm": 6.452256202697754,
+      "learning_rate": 4.9031542398457974e-05,
+      "loss": 6.7864,
+      "step": 18
+    },
+    {
+      "epoch": 0.013392857142857142,
+      "eval_loss": 6.469050884246826,
+      "eval_runtime": 161.9588,
+      "eval_samples_per_second": 13.979,
+      "eval_steps_per_second": 1.747,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3353971104088064e+16,
+  "total_flos": 2.670794220817613e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null