Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:042945f16a17a459d87953399ea1a2abb1b006971581e2320284fd8b4f703685
+oid sha256:358f96c17c98d60449f965f8fc86dfb03dff2632db83540e5c56633c0758e917
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84036c912122fcc1929ce921db81001c768bd741955224a2848ab42f700b9f20
+oid sha256:b65dd6f7ca7b16cfaed51f82e22dcb9a0d00db68efe65a8fb37fba6cca543d71
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f81634af63009bf1a378ed0c44c0336f57a044af94ea02f6aaa12848ad1a0599
+oid sha256:0c91d00fc95d6d02ec458ef0780b20469cc41aeb6d39aa82c7d909001438a2b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007053844345168116,
+  "epoch": 0.009405125793557489,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 49.296,
       "eval_steps_per_second": 6.166,
       "step": 15
+    },
+    {
+      "epoch": 0.00846461321420174,
+      "grad_norm": 0.6084182262420654,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.2561,
+      "step": 18
+    },
+    {
+      "epoch": 0.009405125793557489,
+      "eval_loss": 1.14651358127594,
+      "eval_runtime": 72.6867,
+      "eval_samples_per_second": 49.28,
+      "eval_steps_per_second": 6.163,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3199721778708480.0,
+  "total_flos": 4266295704944640.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null