Training in progress, step 65, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa01364274ded5ec9a4d08f97c52de0069539f51c4125121359aeb7c88679625
+oid sha256:c48988e3503672bcd20efe09c5a1bafa0c5cbe364fd5f649d4030f5561ebd2c3
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eac30af77f67caccc493ca1ea1cccc925b6e62b50ceaff951fbb31647f07ce1
+oid sha256:63347c4edc0740f2f38642ed559ad0cf3aac574c28ee3881620e2607864a653e
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dfa3332294a25a14a5137921fc31f24176a29def678e629a1769ffeb46f154b
+oid sha256:893e1298e33ca8842633f58141fa81768aef1e0b4a74c16a299e4ee46dc662bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78248a64468e8e03af894427063f3f9a858b670b67d13949fb12f06211d294f4
+oid sha256:8977565a0b4b10da6945c32ba36caa3dc40fc9a4cdc4d66a537fb19aba96e0c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.029341646799926645,
+  "epoch": 0.03178678403325386,
   "eval_steps": 34,
-  "global_step": 60,
+  "global_step": 65,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -443,6 +443,41 @@
       "learning_rate": 0.00018502171357296144,
       "loss": 10.2129,
       "step": 60
+    },
+    {
+      "epoch": 0.02983067424659209,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018403440716378928,
+      "loss": 8.8496,
+      "step": 61
+    },
+    {
+      "epoch": 0.030319701693257536,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018301840308155507,
+      "loss": 10.0162,
+      "step": 62
+    },
+    {
+      "epoch": 0.03080872913992298,
+      "grad_norm": 5.941328178675974e+18,
+      "learning_rate": 0.00018197404829072215,
+      "loss": 9.124,
+      "step": 63
+    },
+    {
+      "epoch": 0.03129775658658842,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 9.6824,
+      "step": 64
+    },
+    {
+      "epoch": 0.03178678403325386,
+      "grad_norm": Infinity,
+      "learning_rate": 0.000179801722728024,
+      "loss": 9.5723,
+      "step": 65
     }
   ],
   "logging_steps": 1,
@@ -462,7 +497,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.3226878055743488e+17,
+  "total_flos": 1.4329117893722112e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null