Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:110354de9f1fbe78224e49bd68ac0d41025b8d9827e7fcfc3cae03bb48619820
+oid sha256:1eb7c8a017a3ef49b6118f506d46ec32adbb0c776386a53f68c7604902eb9055
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15a89a36c6f840bd70881cf9336402cecf552b899d525292a2bac2634a2b37e5
+oid sha256:ad0175cc34e6393516d09422e07a05b00d51239f94f657da8f76bbcfc25ceb74
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9d6d75058befc172d955b513ab0168892dc11f97735aa34d08e041b2de55ff
+oid sha256:5fdbb6c5c2f8a3babb3fc37d54b607fc9354b33540d06a0b7b5bf287462ca599
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008547008547008548,
+  "epoch": 0.01282051282051282,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,28 @@
       "eval_samples_per_second": 6.54,
       "eval_steps_per_second": 0.82,
       "step": 10
+    },
+    {
+      "epoch": 0.010256410256410256,
+      "grad_norm": 5.805121421813965,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 4.5561,
+      "step": 12
+    },
+    {
+      "epoch": 0.01282051282051282,
+      "grad_norm": 2.3249106407165527,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.43,
+      "step": 15
+    },
+    {
+      "epoch": 0.01282051282051282,
+      "eval_loss": 0.795749306678772,
+      "eval_runtime": 301.5134,
+      "eval_samples_per_second": 6.537,
+      "eval_steps_per_second": 0.819,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.57604722884608e+16,
+  "total_flos": 3.86407084326912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null