Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70641b75a24f1905ea3041488857c83c86285e6bb826b69e9d8602b6309b8550
+oid sha256:afee915f87f2e94742bb550655633d8ec6b805de369250a7eda0ae6982551dd1
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:619b7e0f4381d83682e22e320752df54a30df85bb540bf33d4a04e8f0012e653
+oid sha256:b435f298829f2671d87292a611d9ba1c4086cc08ffaad0ae7300dd43cd92de0e
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2828d79a8bfdc705c4be7a188bf42698dbef96bc353b2ee5b661629dc0009e73
+oid sha256:0d14899a6fda525c1e04dcf859ac7775e84db61bc829198793b3cea5eac3dba2
 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": 0.006127182808875662,
+  "epoch": 0.007002494638715042,
   "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": 23.678,
       "eval_steps_per_second": 2.961,
       "step": 35
+    },
+    {
+      "epoch": 0.006302245174843538,
+      "grad_norm": 5.374086856842041,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 1.0343,
+      "step": 36
+    },
+    {
+      "epoch": 0.0068274322727471665,
+      "grad_norm": 3.7836270332336426,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.8489,
+      "step": 39
+    },
+    {
+      "epoch": 0.007002494638715042,
+      "eval_loss": 0.9912478923797607,
+      "eval_runtime": 406.1961,
+      "eval_samples_per_second": 23.686,
+      "eval_steps_per_second": 2.962,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4878706270994432e+16,
+  "total_flos": 1.7011854123466752e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null