Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3867d6e1f7546998ee00279522287263e6daa66b1313eb18963dbd0ef476e8a8
+oid sha256:b05ef4a560b16a7e68546159cfea88e88c8ac7f47e227b0ca1676633df02cc69
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01462e4291dca3a0adb96d7134fa5c615e0d883572f2f13d21dbd1f24582518f
+oid sha256:9a0cbed09d3989b54f2a4bf3b92c1d00309355780455f35c549d581bfc30a67e
 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": 0.14953271028037382,
+  "epoch": 0.29906542056074764,
   "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": 30.841,
       "eval_steps_per_second": 16.091,
       "step": 2
+    },
+    {
+      "epoch": 0.22429906542056074,
+      "grad_norm": 65.19701385498047,
+      "learning_rate": 3e-05,
+      "loss": 126.2791,
+      "step": 3
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "grad_norm": 68.43965148925781,
+      "learning_rate": 4e-05,
+      "loss": 123.7978,
+      "step": 4
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "eval_loss": NaN,
+      "eval_runtime": 0.7661,
+      "eval_samples_per_second": 30.021,
+      "eval_steps_per_second": 15.663,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1302986508730368.0,
+  "total_flos": 2605973017460736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null