Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77c0b07a1693c278db2af7b9f4d343a723c232d7f179141b52ee15eb2114c068
+oid sha256:27d6b352e9a38ea55cc7fb0d2296087a0eec23c313d0182ee650709ff92f9c6a
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ff2424e166be88b6de658c1da9053374c83d52bb762e37134b9b8617ab8b0f
+oid sha256:33309403b7ae9daaf6c49eedbecea4112faae6cf47b34886ced64b045e725840
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deabd56c17b610f6d8e6c3c09d2dcb705e4d72db3bc1813e41a578dadc2811d7
+oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bedc6307a5e33c9ada0599345089662b71de7faf79562d8c952efe37fda8ce81
+oid sha256:eee81c5e75673c3b9060a012dcd6537b28a2cc9b4464a9db8908848717dda896
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02663115845539281,
+  "epoch": 0.05326231691078562,
   "eval_steps": 10,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 148.011,
       "eval_steps_per_second": 74.471,
       "step": 10
+    },
+    {
+      "epoch": 0.05326231691078562,
+      "grad_norm": 1.1728761196136475,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 44.3899,
+      "step": 20
+    },
+    {
+      "epoch": 0.05326231691078562,
+      "eval_loss": 11.089601516723633,
+      "eval_runtime": 1.0747,
+      "eval_samples_per_second": 147.954,
+      "eval_steps_per_second": 74.442,
+      "step": 20
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 14568652800.0,
+  "total_flos": 29324083200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null