Training in progress, step 160, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:184e18cfcd9552369bf51740f68926e3162f9bdbb01d2b69fbb0ec79edd52a45
+oid sha256:a758220ef8bbff8c6d1485db235840ad8309e777eecc16a2a36538d98a5d0984
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971f78334d57716402776ec08101e08f7885ef96295540a7de3ac17f04991f8b
+oid sha256:a604243df1dc8a4ee575d18a1d0d45254a9a949ce6f6f087a9c9a807f2dd45ff
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfad5b1db434a4570e357f1971d87bf80fdc19c2e91af8a74bce9bbf251a95cc
+oid sha256:befd409d384ef0f0f1c800aced192285a039968aa574627a06cdbfeed65d40df
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40d5e94eed411043d006187ef3d57f655338dfd7cfaaf34e38342dbbae53acc
+oid sha256:1fb3a39b961047b7cdf3f3152552e802c79a68dc6cf0def914d9209b6b209d37
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7,
+  "epoch": 0.8,
   "eval_steps": 20,
-  "global_step": 140,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,43 @@
       "eval_samples_per_second": 378.767,
       "eval_steps_per_second": 63.254,
       "step": 140
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.7675061821937561,
+      "learning_rate": 7.978377054339498e-07,
+      "loss": 19.789096069335937,
+      "step": 145
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.6245450973510742,
+      "learning_rate": 6.699508557723032e-07,
+      "loss": 19.786654663085937,
+      "step": 150
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.6990048289299011,
+      "learning_rate": 5.511495904178221e-07,
+      "loss": 19.784368896484374,
+      "step": 155
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6921213269233704,
+      "learning_rate": 4.4224544247577535e-07,
+      "loss": 19.664630126953124,
+      "step": 160
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.07252380952380952,
+      "eval_loss": 9.85792350769043,
+      "eval_runtime": 2.5752,
+      "eval_samples_per_second": 388.323,
+      "eval_steps_per_second": 64.85,
+      "step": 160
     }
   ],
   "logging_steps": 5,