Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc3635c3af9aba380d4c1118c9f79227cb06f9e8de884f97564a0bcada0efed
+oid sha256:8bb699ff64fb24d304e193ad43ec6740e382285999c6f483735269a91500e087
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f42f6965441e3678cc635c8f133da948e72ebb61d05d423ed048d820326b4740
+oid sha256:9c352042bfb55c872cdcc4318acdfc3a259b315a418cacb02e41bd76a810e0ad
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0021bdd5d4dfd189ca068b881930f409d18a94214a1f01661c34c771e5929764
+oid sha256:280141c6f94bbee6f01303701cf680c7f55c54f1006c82e61cf8a9e3cc155e7b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002455610124669437,
+  "epoch": 0.004911220249338874,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 7.179,
       "eval_steps_per_second": 3.589,
       "step": 10
+    },
+    {
+      "epoch": 0.0028333962976955043,
+      "grad_norm": 2.264620780944824,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.2726,
+      "step": 15
+    },
+    {
+      "epoch": 0.0037778617302606727,
+      "grad_norm": 1.8826525211334229,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.8682,
+      "step": 20
+    },
+    {
+      "epoch": 0.0037778617302606727,
+      "eval_loss": 0.4691351652145386,
+      "eval_runtime": 310.6736,
+      "eval_samples_per_second": 7.178,
+      "eval_steps_per_second": 3.589,
+      "step": 20
+    },
+    {
+      "epoch": 0.004722327162825841,
+      "grad_norm": 1.2390393018722534,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.5787,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3492946726754304.0,
+  "total_flos": 7021903213578240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null