Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d348b33b833d7118abd3f100d70b7d313a866228f2cf4973c56e51eb2c58a5
+oid sha256:9fe65eb23721f7220a89c33aa8147d2305f1f2c11469d788b4ee14d373df4d3b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92614455d6b4f9fea1720ef0d7522eb53064139c2983b463ad81c13613377dc3
+oid sha256:d1468f00d1b00dedafbb3a3f0d6aa7b53ec1c5f4cf90c80df61d973d4dfe2b89
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:884ce308a4b9046b63daa8471de316c7b3c332361554edb94ea15c1aef43590c
+oid sha256:e0498481dc13586eb056bf15062506f1ff8e314200eb2c09558f026d1062ec3a
 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": 0.6881720430107527,
+  "epoch": 0.8602150537634409,
   "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": 8.962,
       "eval_steps_per_second": 4.506,
       "step": 36
+    },
+    {
+      "epoch": 0.7455197132616488,
+      "grad_norm": 1.3893134593963623,
+      "learning_rate": 0.00017343225094356855,
+      "loss": 1.9008,
+      "step": 39
+    },
+    {
+      "epoch": 0.8028673835125448,
+      "grad_norm": 1.3943053483963013,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 1.8282,
+      "step": 42
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 1.3723570108413696,
+      "learning_rate": 0.00015555702330196023,
+      "loss": 1.8482,
+      "step": 45
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "eval_loss": 1.8272418975830078,
+      "eval_runtime": 19.7474,
+      "eval_samples_per_second": 8.963,
+      "eval_steps_per_second": 4.507,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.148510102234071e+17,
+  "total_flos": 2.6856376277925888e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null