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:c350e1f2133ebde280250f16e555217050fbcdd181b4658a3fed0009cfdbe4b3
+oid sha256:3cad94fcec5e3bb546233e1eae356ed43e3d49ea1dea33068e21e02972680d61
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fc8e1e90760c6e0f40101fb231cafce2834dd861dfedea311821459d265768a
+oid sha256:1a909467496e952419f8239ee4e17228ad82ee4d24dfb96d3d2298f9d7e28fdf
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005d9a86e0834fe0802ab2e1c3fa9eca806e3cae26d1cbb14ab848a758219c13
+oid sha256:a4faae14a1aa6472da1e35d90c3eeeb0dd65ba4a4be7087c6d32cacd0c607e1b
 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": 0.6542056074766355,
+  "epoch": 0.7476635514018691,
   "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": 517.918,
       "eval_steps_per_second": 69.056,
       "step": 35
+    },
+    {
+      "epoch": 0.6728971962616822,
+      "grad_norm": 0.10105115175247192,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 10.3709,
+      "step": 36
+    },
+    {
+      "epoch": 0.7289719626168224,
+      "grad_norm": 0.12131473422050476,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 10.3694,
+      "step": 39
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "eval_loss": 10.370113372802734,
+      "eval_runtime": 0.1729,
+      "eval_samples_per_second": 520.643,
+      "eval_steps_per_second": 69.419,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3904273121280.0,
+  "total_flos": 4462026424320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null