Training in progress, step 5500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:014fee06c40abe14189555c9ed4b025e6ee8cd4e072236a6535f45528f8d6229
+oid sha256:eee800c1bc1a385857c0b9c6aa18cea9670566ce58b0d0d47446e427448e27f7
 size 8137792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd913717e7a6e4112d3543f341b7a262c1da4ae52ac1ad2834e5b246991f9026
+oid sha256:9dc24a5ac8897e08a64447e32074cfd3cc46bc9990c6d3a03306d3db2e69756b
 size 16386426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:924549db5c8fa7c6722b2717239f1aff8fd1b5bfacb8266579f90ebe96787e6a
+oid sha256:bef661152f5dbc25921eaa549c8976d9b6dfa96e5c5bfe16ecb5feb37653bd90
 size 15006

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80145150a24a2d588a25fa8b47e99a841735b6543ce3ee2a1cf42f0c87555d79
+oid sha256:8439fc926be3293d7241108816262c1af25c649e5af052c2a6f82b24035c47a4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 10.798312763630683,
+  "epoch": 10.998281518512732,
   "eval_steps": 500,
-  "global_step": 5400,
+  "global_step": 5500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -465,6 +465,21 @@
       "learning_rate": 6.400000000000001e-05,
       "loss": 1.2461,
       "step": 5400
+    },
+    {
+      "epoch": 10.998281518512732,
+      "grad_norm": 0.20144224166870117,
+      "learning_rate": 6.333333333333333e-05,
+      "loss": 1.2468,
+      "step": 5500
+    },
+    {
+      "epoch": 10.998281518512732,
+      "eval_loss": 1.112711787223816,
+      "eval_runtime": 780.4643,
+      "eval_samples_per_second": 19.888,
+      "eval_steps_per_second": 2.487,
+      "step": 5500
     }
   ],
   "logging_steps": 100,
@@ -484,7 +499,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.427956875458249e+18,
+  "total_flos": 8.584031846646415e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null