Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6aef3b78c60ccd69b3838a916b82a045de002670b3785b12865a9504f53edf
+oid sha256:f5a353ae7aeb0c1f6a2a0ac58882bdc1c5265e10cc023151955bb015d3e54a1b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57858b4f297e252bd308e3d39e9acfa9813b947214beb2c0b0bd0cfa95607a38
+oid sha256:81e8fb347e704230e504d7cc48965644ed302c71de2875b3086f69905b023a65
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0a880b94d9b8f1377e86006043b94121eb1c447497937e3f4ae33277dae97f
+oid sha256:9f16f3b8874379bf8e1e039ef0bfa9f44be83be43b977ccd15b78395a275f501
 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": 0.018702513150204558,
+  "epoch": 0.037405026300409115,
   "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": 4.177,
       "eval_steps_per_second": 2.1,
       "step": 2
+    },
+    {
+      "epoch": 0.028053769725306838,
+      "grad_norm": 32.84296417236328,
+      "learning_rate": 3e-05,
+      "loss": 110.9102,
+      "step": 3
+    },
+    {
+      "epoch": 0.037405026300409115,
+      "grad_norm": 35.27595520019531,
+      "learning_rate": 4e-05,
+      "loss": 115.7492,
+      "step": 4
+    },
+    {
+      "epoch": 0.037405026300409115,
+      "eval_loss": 7.080971717834473,
+      "eval_runtime": 48.7623,
+      "eval_samples_per_second": 3.712,
+      "eval_steps_per_second": 1.866,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2532979444285440.0,
+  "total_flos": 5065958888570880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null