Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:449a0cd1c864ee7beffbedb10c4d94b6ac740697ab7f1c3fedb2b24234113f6c
+oid sha256:d81aff95ef2b49f0270d23d471759e2aeda1a53aa96db80e226aca95d2ff12a6
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c196d61fde9ca79c2b8320d6a67cc312669bbb5edfdb4463ec4e6542309ba08
+oid sha256:79df5b90e03f9325d217c2ff32dd9516804be0f39df6bfdd6b9831faa6bf79bc
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abaa9373bbe156c59363a08f9fb6a81f0701ec05adf8ddebf0a95d11c5c0d35c
+oid sha256:4338e60828af3efb3dbfac479ffbce4cf22f201f32dd76c072dd2215e2af458f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020956123117223315,
+  "epoch": 0.04191224623444663,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 28.268,
       "eval_steps_per_second": 14.222,
       "step": 2
+    },
+    {
+      "epoch": 0.03143418467583497,
+      "grad_norm": 53.52432632446289,
+      "learning_rate": 3e-05,
+      "loss": 152.0958,
+      "step": 3
+    },
+    {
+      "epoch": 0.04191224623444663,
+      "grad_norm": 88.83341217041016,
+      "learning_rate": 4e-05,
+      "loss": 159.5014,
+      "step": 4
+    },
+    {
+      "epoch": 0.04191224623444663,
+      "eval_loss": NaN,
+      "eval_runtime": 5.8211,
+      "eval_samples_per_second": 27.658,
+      "eval_steps_per_second": 13.915,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1302999393632256.0,
+  "total_flos": 2605998787264512.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null