Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420428b38b02edcd164466f40df233165fe9136c21a9bd292d7442b21a30a1de
+oid sha256:7cc3c6801de8d9a6c37c89923ea37363b658905d8d1977b2b77580ce4551df8f
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f648fa3454d0e006a2a7e52ac0f25493a492a469781ae97ba92365d1d5346e2
+oid sha256:5eefe3ff68b3c6cfb34c3f7456d6d89aae9b5345d20a0d0dc042c494b9db9e45
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a186e6fbbf643cd450783673c1b85df341f2faa791193de2c51c7d521f1f614
+oid sha256:6d45bc6c19d4bd83dc75229014b5bfc982acdfb2f629816ac618fba1ba939555
 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": 0.001206468527412357,
+  "epoch": 0.002412937054824714,
   "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": 8.852,
       "eval_steps_per_second": 4.427,
       "step": 10
+    },
+    {
+      "epoch": 0.0013920790700911812,
+      "grad_norm": 14.867263793945312,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 8.3446,
+      "step": 15
+    },
+    {
+      "epoch": 0.0018561054267882415,
+      "grad_norm": 11.387835502624512,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 5.7081,
+      "step": 20
+    },
+    {
+      "epoch": 0.0018561054267882415,
+      "eval_loss": 4.9822258949279785,
+      "eval_runtime": 512.3945,
+      "eval_samples_per_second": 8.855,
+      "eval_steps_per_second": 4.428,
+      "step": 20
+    },
+    {
+      "epoch": 0.002320131783485302,
+      "grad_norm": 12.567839622497559,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 4.1337,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3964497004855296.0,
+  "total_flos": 8016125812015104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null