Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db84560640f91efc56e844bdea8afc675bd95bceca3d42f9d5f0bb4ec2cdacf9
+oid sha256:7e09d1d300d7dcd4e382ff72e7924ef6b9bca66b4e5d810a27cda3693e33de86
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4909eccaab426430b3fe8c5f4a3b4d1a4f547347c178f7cf549085791a7703fd
+oid sha256:7523714a9958ff8938294936bfd01d897220e490eb175cb7a3409c80733c21fe
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875cc80f5d170fa1121c26562fc04de720d828ce782c9d29bd2e7b6e67614c5a
+oid sha256:b0b5265eca0f1b80fa74df31167c9740f8dbc34b19adfc7d5eefc35310f0a33a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02023608768971332,
+  "epoch": 0.025295109612141653,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 18.188,
       "eval_steps_per_second": 2.276,
       "step": 36
+    },
+    {
+      "epoch": 0.021922428330522766,
+      "grad_norm": 0.1566758006811142,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.7573,
+      "step": 39
+    },
+    {
+      "epoch": 0.023608768971332208,
+      "grad_norm": 0.16109135746955872,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.7655,
+      "step": 42
+    },
+    {
+      "epoch": 0.025295109612141653,
+      "grad_norm": 0.15883490443229675,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.765,
+      "step": 45
+    },
+    {
+      "epoch": 0.025295109612141653,
+      "eval_loss": 0.7461237907409668,
+      "eval_runtime": 164.7581,
+      "eval_samples_per_second": 18.19,
+      "eval_steps_per_second": 2.276,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8810271250251776e+16,
+  "total_flos": 2.351283906281472e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null