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:c418002939df1ee3d6e563d074e73b24f51dbe844adf65c2aeece17df000e9dc
+oid sha256:7af72ed9912f7cc4130c92bae361eb5a8b56297e0a9c13ec4facb12c9dc448fd
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18dba5e7d1c4b712ac9510f3101db5c681c3e3c29966b1cefb5df6a5c4e15cf1
+oid sha256:bf103754680274f85000745c4b5b7f36ebb1eeef359174d82b7fe7ba7c324d6f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba60c260384233e5cb0e7bbfabb0bd75f441fc8b78b5fed933e9ca48341a17ab
+oid sha256:3d1b8821978c7450bd2cb49e068182933549eb330933b29022697a95533c47a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011695906432748537,
+  "epoch": 0.023391812865497075,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 7.2017,
       "step": 9
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 26.442575454711914,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 6.3222,
+      "step": 12
+    },
+    {
+      "epoch": 0.017543859649122806,
+      "grad_norm": 22.6745662689209,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 5.8747,
+      "step": 15
+    },
+    {
+      "epoch": 0.01871345029239766,
+      "eval_loss": 1.3965755701065063,
+      "eval_runtime": 47.1502,
+      "eval_samples_per_second": 7.656,
+      "eval_steps_per_second": 3.839,
+      "step": 16
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 55.49920654296875,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.2658,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3515651519938560.0,
+  "total_flos": 7031303039877120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null