Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cad94fcec5e3bb546233e1eae356ed43e3d49ea1dea33068e21e02972680d61
+oid sha256:dd08e9492459977c008106e17d295479b09ddbc731924ae14917a9175eb613a0
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a909467496e952419f8239ee4e17228ad82ee4d24dfb96d3d2298f9d7e28fdf
+oid sha256:1f335d7283f0cbe6929bd097e3b049a8794cde4f37eb271b74ccc9b86d782331
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4faae14a1aa6472da1e35d90c3eeeb0dd65ba4a4be7087c6d32cacd0c607e1b
+oid sha256:1f6aaadfc3a2995ea3bff4c91194faec2c49a54ff830cb39f07c142f67055ad8
 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": 0.7476635514018691,
+  "epoch": 0.8411214953271028,
   "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": 520.643,
       "eval_steps_per_second": 69.419,
       "step": 40
+    },
+    {
+      "epoch": 0.7850467289719626,
+      "grad_norm": 0.12438107281923294,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3694,
+      "step": 42
+    },
+    {
+      "epoch": 0.8411214953271028,
+      "grad_norm": 0.1044248566031456,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3692,
+      "step": 45
+    },
+    {
+      "epoch": 0.8411214953271028,
+      "eval_loss": 10.36966609954834,
+      "eval_runtime": 0.1736,
+      "eval_samples_per_second": 518.406,
+      "eval_steps_per_second": 69.121,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4462026424320.0,
+  "total_flos": 5019779727360.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null