Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdae13e8231a3a0b22a1a0f44d1c39bb4e8cd5a86ba21fd05280221f08f687b6
+oid sha256:da34647703224a9f662b568e9c6ac938877f751c29ff7c900992680b81d9cfac
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b43d2e450a76e4a908689c1a1e50d6c551af925d8ca406764b869f85ad183679
+oid sha256:caadb536e9ebbd0dc5e86b403b64c40a9bba1000243c7940de28e02b455bb0b7
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b703739f5454d2894fcbb8e649647ab136cbeb65534f344ebd4100fb9a50e7
+oid sha256:d000b4df7c48eb60558df333b0b72870a8d302bfff400709f913ef5a3e459d94
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.28169014084507044,
+  "epoch": 0.32193158953722334,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 6.328,
       "eval_steps_per_second": 0.818,
       "step": 35
+    },
+    {
+      "epoch": 0.289738430583501,
+      "grad_norm": 0.05079665035009384,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0047,
+      "step": 36
+    },
+    {
+      "epoch": 0.31388329979879276,
+      "grad_norm": 0.053295738995075226,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0069,
+      "step": 39
+    },
+    {
+      "epoch": 0.32193158953722334,
+      "eval_loss": 0.006381278857588768,
+      "eval_runtime": 33.0314,
+      "eval_samples_per_second": 6.327,
+      "eval_steps_per_second": 0.817,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.04841693722837e+17,
+  "total_flos": 1.1992682951029555e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null