Training in progress, step 6500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8034eb35b6abf7233f82f1126750cd4084150606300cf2c5ae3bf93175d3b39
+oid sha256:346392cdbc25047c37c3f67a99466fa2153ca5464573ce0ababa89e2933a6370
 size 4372840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96eb615941ea3597bbf0aaa095c7f24855ecb22cebbce16c9845b1f25d6bcbb4
+oid sha256:de1af9afe33c3cb3ab09ed4d65965258c6c25c0e30a2b922f5bea3827f152a29
 size 8810554

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca4923839c8c30bca8e3ace20149e5880a298e0542997085cf6edcc4f33d27b1
+oid sha256:a4193a5120ae53509ae725187f22e9bb5171043d726ce12c4b12d5f7a94303b5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef2a74d2caf7ff65ce7e4fe13424bc721549e6922a4ebcdc9e414dd7479fd3b1
+oid sha256:3fa28b915fe4fef00acc50dadcdde0c7aab3d993fa136f0bcc4129399c89113c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9113001215066828,
+  "epoch": 0.9872417982989065,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,21 @@
       "eval_samples_per_second": 5.722,
       "eval_steps_per_second": 5.722,
       "step": 6000
+    },
+    {
+      "epoch": 0.9872417982989065,
+      "grad_norm": 0.4322833716869354,
+      "learning_rate": 2.551640340218712e-07,
+      "loss": 1.4513,
+      "step": 6500
+    },
+    {
+      "epoch": 0.9872417982989065,
+      "eval_loss": 1.3799034357070923,
+      "eval_runtime": 5.5646,
+      "eval_samples_per_second": 5.751,
+      "eval_steps_per_second": 5.751,
+      "step": 6500
     }
   ],
   "logging_steps": 500,
@@ -206,7 +221,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.93378243313664e+17,
+  "total_flos": 2.09493096923136e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null