Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a5649af37a5b41c63084768a1b97fe2c7824ba93d6b701d238e6d3eb5057cb5
+oid sha256:c9370ba3a6a616948e834ed07049160266831edaea05d6ac35ae408229c2e69c
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33abc0744ee37e39335b097f2fa677c00f83290e70905490de1e9fa653eed444
+oid sha256:3a151bab58a9d720b0d62ef1c5bcc7eb0bbd01321fe5dd955b8e63984a450add
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da34c78130291294db5a3fabc49ae2052c77c00d49d84a9bcfb5b2ecf075aeed
+oid sha256:c3c1592ab32ec103447346ead6f8a193e5e7629d430f18114eb40d7c7f05d351
 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": 0.6299212598425197,
+  "epoch": 0.7086614173228346,
   "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": 5.265,
       "eval_steps_per_second": 0.689,
       "step": 40
+    },
+    {
+      "epoch": 0.6614173228346457,
+      "grad_norm": 0.6913183927536011,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 7.8228,
+      "step": 42
+    },
+    {
+      "epoch": 0.7086614173228346,
+      "grad_norm": 0.8218957781791687,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.9007,
+      "step": 45
+    },
+    {
+      "epoch": 0.7086614173228346,
+      "eval_loss": 1.9470714330673218,
+      "eval_runtime": 20.321,
+      "eval_samples_per_second": 5.265,
+      "eval_steps_per_second": 0.689,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1785416071970816e+17,
+  "total_flos": 1.320224204783616e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null