Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:704acbda212196abe32b0917069da059a8d16ff3c8da4bba242bb7d196aedb99
+oid sha256:74c2ec4aaf73e828babd394219c77d4f76823d217a4bd1b859e0e965353902b5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01a5c7efe72979b1344ed58a551e0ac819eb88a325f957f382bc36aa206dbcf8
+oid sha256:7ccbd319421ed7631b79cac9357ffeee8eaf309311a5284715ba0cc1dec1687f
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87951bd1d28cfc789427636c05788fc21db0e7e40be21589b4278413c44c66bd
+oid sha256:49644ad8f5452e53758ca52013eb3650a3941bcec6083d72c46c935a677f7d88
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009548227389267085,
+  "epoch": 0.011139598620811599,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 14.094,
       "eval_steps_per_second": 1.762,
       "step": 54
+    },
+    {
+      "epoch": 0.010078684466448589,
+      "grad_norm": 3.9666662216186523,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.7154,
+      "step": 57
+    },
+    {
+      "epoch": 0.010609141543630095,
+      "grad_norm": 4.252094268798828,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.8792,
+      "step": 60
+    },
+    {
+      "epoch": 0.011139598620811599,
+      "grad_norm": 3.9958548545837402,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.8798,
+      "step": 63
+    },
+    {
+      "epoch": 0.011139598620811599,
+      "eval_loss": 0.7039853930473328,
+      "eval_runtime": 675.7018,
+      "eval_samples_per_second": 14.096,
+      "eval_steps_per_second": 1.763,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.59380728306729e+16,
+  "total_flos": 8.859441830245171e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null