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:c55ff86e0ae25aee7bf76ee5320d106b71ffe6996ff86f479872f62044c86395
+oid sha256:bd6c7458a83ea284862aa32f5e893226cdb84fae65779d2e66a39e45bbf0df64
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71d8ccc34b7e9c43ec3753479358362fafb23b7ac6ac63a48a6d1ed4776b6a8
+oid sha256:62885f3d23e623d0b8efcd090a1ab0a231d359b875638617520d6f7cf184efee
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90b49e55746f1efde0c49b53b1686f55fab15d8870510125361a613a63a60f9c
+oid sha256:877be02e72c90068c53b4cd4ac5f76683c34f6c6e1f29413737e7203851c9d33
 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": 0.02406015037593985,
+  "epoch": 0.0481203007518797,
   "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": 13.415,
       "eval_steps_per_second": 6.707,
       "step": 2
+    },
+    {
+      "epoch": 0.03609022556390978,
+      "grad_norm": 13.518844604492188,
+      "learning_rate": 3e-05,
+      "loss": 42.5714,
+      "step": 3
+    },
+    {
+      "epoch": 0.0481203007518797,
+      "grad_norm": 2.489936113357544,
+      "learning_rate": 4e-05,
+      "loss": 27.216,
+      "step": 4
+    },
+    {
+      "epoch": 0.0481203007518797,
+      "eval_loss": 2.0373122692108154,
+      "eval_runtime": 10.4333,
+      "eval_samples_per_second": 13.419,
+      "eval_steps_per_second": 6.709,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5065926676316160.0,
+  "total_flos": 1.013185335263232e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null