Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782d27fc4c6305dfb2b5c65c95bd188ba4e5fa3fc5c38b5a3518649f475bf1dd
+oid sha256:b4e70eaea36e557ccaad59c39e66fcca9bdc0d0d5299126863eb2136f7742de4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051e094100790644028ba2db283d3976b13b4d0ba87e0ea28eaa896870e1a710
+oid sha256:681b9a3c017f51d23d63cfa771b07651de0ea6f520809cdfb0f7484a51dd5777
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55743e330b33b6dab007b0a23ad920cc13acf142db90f3910f8e9a63b3040f5b
+oid sha256:3202c18da649b1f0e77c873cd6f028f8e87862db021d3d223b235a7e44b92729
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
+oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011486331265793705,
+  "epoch": 0.01722949689869056,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 18.575,
       "eval_steps_per_second": 9.293,
       "step": 100
+    },
+    {
+      "epoch": 0.012634964392373075,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.7792,
+      "step": 110
+    },
+    {
+      "epoch": 0.013783597518952447,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.014932230645531817,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.3379,
+      "step": 130
+    },
+    {
+      "epoch": 0.01608086377211119,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 1.1498,
+      "step": 140
+    },
+    {
+      "epoch": 0.01722949689869056,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.499,
+      "step": 150
+    },
+    {
+      "epoch": 0.01722949689869056,
+      "eval_loss": NaN,
+      "eval_runtime": 98.6846,
+      "eval_samples_per_second": 18.574,
+      "eval_steps_per_second": 9.292,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7226672717692928e+16,
+  "total_flos": 2.592790026387456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null