Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc2f36fedd765e5d1f9b570d28a00c7d79ecc2fcfdd3d3f929b9becf9f87a8a
+oid sha256:94dc55614a47dc74ce9754237c7ea45cb7b14f253992cf2763e6e60bdf995c22
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a51298471d8824e62b642ff7fc8903a12092fd82e1f4d435816512347109e7a
+oid sha256:f0f4e2f48e835479aaf79738ab161adb36cc3c6de347dddfb5ed2f81e9f085c2
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d6b093e0c4c8b051f5b9e0d212403e2828523b63325a698accc0ed53ad100b1
+oid sha256:970692caa867a85ad5143a11673c0a1eafd0aaa61e02122a9a1ea48f567151af
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d162f01aa043f9810802c3a765a643409e22677d06ecb4e3f1f9962ebaab1f5c
+oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2826855123674912,
+  "epoch": 0.5653710247349824,
   "eval_steps": 4,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,21 @@
       "eval_samples_per_second": 535.754,
       "eval_steps_per_second": 66.969,
       "step": 4
+    },
+    {
+      "epoch": 0.45229681978798586,
+      "eval_loss": 11.007291793823242,
+      "eval_runtime": 0.2641,
+      "eval_samples_per_second": 454.303,
+      "eval_steps_per_second": 56.788,
+      "step": 8
+    },
+    {
+      "epoch": 0.5653710247349824,
+      "grad_norm": 28.9281063079834,
+      "learning_rate": 5e-05,
+      "loss": 176.7641,
+      "step": 10
     }
   ],
   "logging_steps": 10,
@@ -42,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 839097778176.0,
+  "total_flos": 1697485160448.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null