Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f56c05f7d9e08abc69d058917676011b35db318cce421d52dcf09325a12889
+oid sha256:deef8309f7775dfae22cd187b5a740c4952a019695ef3a0705bd8f6f20bf2d21
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54a731e9e117593908e06806b29b0bcbafd29e2948f431ad02664e18932ed295
+oid sha256:cfd21b7ba44e39b389af26651f74cdf3733e798a1199dbe053135232ec20429a
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f6cda69bfbe0de119defc83e5da3ac5af16a274455608c670b1651222f7fc96
+oid sha256:408a06755b519bb846de2707ae71844004b4b1bde9426470048a53e0c32a92b3
 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": 0.2504472271914132,
+  "epoch": 0.28622540250447226,
   "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": 11.062,
       "eval_steps_per_second": 1.406,
       "step": 35
+    },
+    {
+      "epoch": 0.25760286225402507,
+      "grad_norm": 0.0844140574336052,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0055,
+      "step": 36
+    },
+    {
+      "epoch": 0.27906976744186046,
+      "grad_norm": 0.12384696304798126,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0257,
+      "step": 39
+    },
+    {
+      "epoch": 0.28622540250447226,
+      "eval_loss": 0.014691304415464401,
+      "eval_runtime": 21.3348,
+      "eval_samples_per_second": 11.062,
+      "eval_steps_per_second": 1.406,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.656780307070976e+16,
+  "total_flos": 5.322034636652544e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null