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:cf5b29cd43b9ab3c558c82981647b4f7922d2b1c6ac4e4127c1ba7053cf68b19
+oid sha256:0453cf8d5181fcd51b07cb736c60a81a607ead0cf3b9610012db0a4cf8e65a1d
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d3ed1b2ce4783f085d7510dfbb28461860806cf97bf6ea3815c32a13ec976ca
+oid sha256:14945ccab2df95457ad12322054292ee40b5326821ce1897fc114a15f8b0328c
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42e4d0276ac2fb70e5c0593f417f2d935273357ff980559b410f61ea4ea09832
+oid sha256:29843bac3ae7f15549b97859e26d118657b48715b2439ab9d58c3760f6e8b44c
 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": 0.02265326348577092,
+  "epoch": 0.025484921421492283,
   "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": 12.499,
       "eval_steps_per_second": 3.127,
       "step": 40
+    },
+    {
+      "epoch": 0.023785926660059464,
+      "grad_norm": 3.726226329803467,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.8956,
+      "step": 42
+    },
+    {
+      "epoch": 0.025484921421492283,
+      "grad_norm": 3.9398977756500244,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.8685,
+      "step": 45
+    },
+    {
+      "epoch": 0.025484921421492283,
+      "eval_loss": 3.9185895919799805,
+      "eval_runtime": 237.9499,
+      "eval_samples_per_second": 12.498,
+      "eval_steps_per_second": 3.127,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.034054314983424e+16,
+  "total_flos": 6.788311104356352e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null