Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f62d082ff721377f163513844a0a2c133918e3265352c0c260824a7187ce609
+oid sha256:31462713fff36412b1be0201a5a9021cc0e512e0b5bc15ad23d7e921ced35ad9
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4c98010861fca31a6387eb4da153afb0bce18935ea14901de36ef26b34b0d3d
+oid sha256:8a2084c21796dbb2c0579c3051017c6b49d4a7c3784f9fc73fc86f4b0a02a4da
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
+oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
 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": 0.0011275148867199887,
+  "epoch": 0.0022550297734399774,
   "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": 95.399,
       "eval_steps_per_second": 47.699,
       "step": 2
+    },
+    {
+      "epoch": 0.001691272330079983,
+      "grad_norm": 8.634726524353027,
+      "learning_rate": 3e-05,
+      "loss": 6.6183,
+      "step": 3
+    },
+    {
+      "epoch": 0.0022550297734399774,
+      "grad_norm": 8.554905891418457,
+      "learning_rate": 4e-05,
+      "loss": 6.3897,
+      "step": 4
+    },
+    {
+      "epoch": 0.0022550297734399774,
+      "eval_loss": NaN,
+      "eval_runtime": 32.0976,
+      "eval_samples_per_second": 93.091,
+      "eval_steps_per_second": 46.546,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 259438606811136.0,
+  "total_flos": 518877213622272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null