Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d3617919bf909928ee5d712956dec1d425d2b9cb16b43c851298a724c160032
+oid sha256:5370294eccd835e415b06aca1329f3ba95203ce6abc5d1b91fd296554fab045c
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:782deca458c0b71ef8515d675a07f48b4f089136f6aa061a1fd0f5a5775a666d
+oid sha256:26e297718164d7ba553e6ac0308791bfbaf5385318430d91c6a3c8aedb31ad21
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e65eb58cf79922efc87a5b44bfa56ed1c2e0a5bc75a6378e384f50cac903c4aa
+oid sha256:9bb89f519660885eea9b51fea75f75a0333612dcf1d1635b7f07fb4145227be2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
+oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017080330931411796,
+  "epoch": 0.021350413664264746,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 3.898,
       "eval_steps_per_second": 1.949,
       "step": 36
+    },
+    {
+      "epoch": 0.01850369184236278,
+      "grad_norm": 11.163553237915039,
+      "learning_rate": 0.00017343225094356855,
+      "loss": 22.5554,
+      "step": 39
+    },
+    {
+      "epoch": 0.019927052753313763,
+      "grad_norm": 13.20541763305664,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 22.9775,
+      "step": 42
+    },
+    {
+      "epoch": 0.021350413664264746,
+      "grad_norm": 10.816298484802246,
+      "learning_rate": 0.00015555702330196023,
+      "loss": 22.2379,
+      "step": 45
+    },
+    {
+      "epoch": 0.021350413664264746,
+      "eval_loss": 0.6865644454956055,
+      "eval_runtime": 673.7961,
+      "eval_samples_per_second": 10.537,
+      "eval_steps_per_second": 5.269,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8965646597842534e+17,
+  "total_flos": 2.373171030093988e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null