Training in progress, step 6000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e471fb4d0cd1d95173562f1828c9f3f708bd8ab1915bec2d660d41d7e144cf8e
+oid sha256:c69edaf91c86caf6a7a0fd42996899325e932c7927930f0bbb216780ecee6505
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cce281935235f3e132e8b31ded5fc4771d1e681b9e5d038a2e24e34f5759d23
+oid sha256:788a1d6cd203b01bb14f4804f15ed88e7a7c43e26dd6d552eee5a686613ecee8
 size 3497859804

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fca74ac1d9771b30f4d791442ccabecf99d1bc0261c17c880b2114870d813ec1
+oid sha256:95b37961c6d0193de06c3efbf48a168df2b148e000c09c167a07902751b74f66
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0120481927710845,
+  "epoch": 3.285870755750274,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -392,6 +392,41 @@
       "learning_rate": 4.090373113821281e-05,
       "loss": 0.553,
       "step": 5500
+    },
+    {
+      "epoch": 3.0668127053669223,
+      "grad_norm": 1.5551363229751587,
+      "learning_rate": 3.9031095201980976e-05,
+      "loss": 0.3049,
+      "step": 5600
+    },
+    {
+      "epoch": 3.12157721796276,
+      "grad_norm": 1.7245244979858398,
+      "learning_rate": 3.717449111186025e-05,
+      "loss": 0.3081,
+      "step": 5700
+    },
+    {
+      "epoch": 3.176341730558598,
+      "grad_norm": 1.4479619264602661,
+      "learning_rate": 3.5336632428740265e-05,
+      "loss": 0.3103,
+      "step": 5800
+    },
+    {
+      "epoch": 3.2311062431544357,
+      "grad_norm": 2.026216745376587,
+      "learning_rate": 3.352020531574527e-05,
+      "loss": 0.3035,
+      "step": 5900
+    },
+    {
+      "epoch": 3.285870755750274,
+      "grad_norm": 1.2143455743789673,
+      "learning_rate": 3.172786461221279e-05,
+      "loss": 0.3146,
+      "step": 6000
     }
   ],
   "logging_steps": 100,
@@ -411,7 +446,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6426657083853537e+18,
+  "total_flos": 2.8822031507389317e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null