Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd637795ad111ef70b495c53c5ee3f6c9ab1bf37f2f623639de451aa4b435e8
+oid sha256:9984484c45e1e501d23dec4df93343ee26488c441f7ac338cb47b8764742acaa
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0589bef2af7fd5efb81f672f725f339530ffe4da9d7b7e8c748abdd4a9089716
+oid sha256:255301e620bffc8bc135024979cfa5c2559cd2664ee94525d8353c4fc5b6b4ff
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0a52bb46f51e660abcb041b0b835241189b691ea4109f2665f135f52d27aa2
+oid sha256:b52a51c3b4c01f9b630403ebb6928c43e1ecb011855669002547cf6d66e6c4a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03418803418803419,
+  "epoch": 0.038461538461538464,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 6.538,
       "eval_steps_per_second": 0.819,
       "step": 40
+    },
+    {
+      "epoch": 0.035897435897435895,
+      "grad_norm": 1.7005305290222168,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.0872,
+      "step": 42
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 1.8922603130340576,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.437,
+      "step": 45
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "eval_loss": 0.5421185493469238,
+      "eval_runtime": 301.2894,
+      "eval_samples_per_second": 6.542,
+      "eval_steps_per_second": 0.82,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.030418891538432e+17,
+  "total_flos": 1.159221252980736e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null