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:a61782b8acdd212d7f8e54236156cc8fbbc9ae201b2eb5a5047396a24f5adde5
+oid sha256:6bf8ae972af11f668559bb08b04015ffd3644ebdc724085a829c79571270a204
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61bf198ee1140b5436dba92a7b4c340adab529125f702643df4be9ef075c8b85
+oid sha256:8491a1e6f11d6229fe72932a0fe7bb4e797c61efe7bd5dc9ba48b7c851bf6f6c
 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": 0.015902230729588455,
+  "epoch": 0.0185526025178532,
   "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": 14.502,
       "eval_steps_per_second": 1.813,
       "step": 54
+    },
+    {
+      "epoch": 0.01678568799234337,
+      "grad_norm": 6.218847751617432,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 3.5507,
+      "step": 57
+    },
+    {
+      "epoch": 0.017669145255098283,
+      "grad_norm": 6.713202953338623,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.2378,
+      "step": 60
+    },
+    {
+      "epoch": 0.0185526025178532,
+      "grad_norm": 6.8192548751831055,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 3.4102,
+      "step": 63
+    },
+    {
+      "epoch": 0.0185526025178532,
+      "eval_loss": 0.8609820604324341,
+      "eval_runtime": 394.5997,
+      "eval_samples_per_second": 14.496,
+      "eval_steps_per_second": 1.812,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.597138352327885e+16,
+  "total_flos": 8.863328077715866e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null