Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eabac952144362e06e5038d22466558ecfc80b1c3460d48ad53cdedadbc92ef
+oid sha256:36219f4df01f6540de43e20af601c95b792f0e8b395a1faec9012b7942e4bc37
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f15680ec5d975078f2eab9b86ba0790c3f2779737ea0dbc67e51f7cde46cab
+oid sha256:585f9ab65b3cbf0614231a35f714d5862e5c46100460503306f45bca7fc5a217
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b466971bc56e50d45ed53ec8544dcc547c522ab03e3c19ab6c40616db98b9af2
+oid sha256:aa8a3d63161f76c741ed27e5548e0954b55bada46f17ff65da09dc9004692f5a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1996614c6c53967c1177fd38254c7aeb2afcca06720e7eecf62b90cd631403c
+oid sha256:78a060285bfc64e2914a2dfa3484550144c9851d788510de86ca8a657edce764
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5194805194805194,
+  "epoch": 0.7792207792207793,
   "eval_steps": 15,
-  "global_step": 30,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 4.438,
       "eval_steps_per_second": 0.595,
       "step": 30
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.7083372473716736,
+      "learning_rate": 9.516722391687902e-05,
+      "loss": 2.5942,
+      "step": 33
+    },
+    {
+      "epoch": 0.6233766233766234,
+      "grad_norm": 0.6996327042579651,
+      "learning_rate": 9.38524223653626e-05,
+      "loss": 2.648,
+      "step": 36
+    },
+    {
+      "epoch": 0.6753246753246753,
+      "grad_norm": 0.7574095726013184,
+      "learning_rate": 9.239105265402525e-05,
+      "loss": 2.5124,
+      "step": 39
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.7147637605667114,
+      "learning_rate": 9.078799912580304e-05,
+      "loss": 2.652,
+      "step": 42
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "grad_norm": 0.8316633701324463,
+      "learning_rate": 8.904861967412703e-05,
+      "loss": 2.5992,
+      "step": 45
+    },
+    {
+      "epoch": 0.7792207792207793,
+      "eval_loss": 0.6810405254364014,
+      "eval_runtime": 21.865,
+      "eval_samples_per_second": 4.436,
+      "eval_steps_per_second": 0.595,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.545618673631232e+17,
+  "total_flos": 2.318428010446848e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null