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:b97da3dee8f926f10a0755f2a580e1147fb1e5e97d9db0c71b8f9b39fecfca6d
+oid sha256:aa7195f4dda21dad2a467109e670a3a6e2577fe5ea469d36f3ebb0e856b4f6cc
 size 3029024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:820e02faed666f6f41e40a8b97b2fff9be920ddef4250d5fc5dd84ad419c3136
+oid sha256:91e7795cfa3a38197bb3414c404d5795d09d107f8d95a22142d3ed245d907cd5
 size 1663290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0897a16a47e7eef56851f281f3b9135740b6fdb7cb031a3f0df1601e9c11710
+oid sha256:7a0e4ce3ad5bf553f6053fd3f7c81391f47a630679113bc7ac3ecea8868321a4
 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": 0.45584045584045585,
+  "epoch": 0.5128205128205128,
   "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": 117.27,
       "eval_steps_per_second": 15.055,
       "step": 40
+    },
+    {
+      "epoch": 0.47863247863247865,
+      "grad_norm": 2.7736527919769287,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.3498,
+      "step": 42
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 4.598160266876221,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.3898,
+      "step": 45
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "eval_loss": 2.3354244232177734,
+      "eval_runtime": 1.2683,
+      "eval_samples_per_second": 116.688,
+      "eval_steps_per_second": 14.98,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 33033195356160.0,
+  "total_flos": 37284992778240.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null