Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3880b7fbd04701276dc3b811a1180a8ace690b5a18ef55884d9ef8b429c54e5b
+oid sha256:7f6958982483993a00aa40a8d87de2e7b4b52e491369b4736ab24ddbc0dfc846
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a1403b45f05e1ce4c5c2c597ed0eae24e05809d13e26e11bd19cd0e30bedf2
+oid sha256:3d98d7bd7eb46683125a86f5931bca69925cc504784a56424c199b0bd84a46ac
 size 43122580

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": 0.06231967686093479,
+  "epoch": 0.0727062896710906,
   "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": 13.97,
       "eval_steps_per_second": 1.751,
       "step": 54
+    },
+    {
+      "epoch": 0.06578188113098672,
+      "grad_norm": 3.8922553062438965,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 7.6261,
+      "step": 57
+    },
+    {
+      "epoch": 0.06924408540103866,
+      "grad_norm": 3.532529830932617,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 7.799,
+      "step": 60
+    },
+    {
+      "epoch": 0.0727062896710906,
+      "grad_norm": 3.5513439178466797,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 7.5004,
+      "step": 63
+    },
+    {
+      "epoch": 0.0727062896710906,
+      "eval_loss": 1.9200663566589355,
+      "eval_runtime": 104.4709,
+      "eval_samples_per_second": 13.975,
+      "eval_steps_per_second": 1.752,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.571542172604826e+16,
+  "total_flos": 8.833465868038963e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null