Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb712faf6e70975bde60820c8f06e2f87597fa4a332dd2d3314a9ccdb1e55e4e
+oid sha256:fcd3a0eaf5f2ce9cde1c0d0e3d419588687c76e94ee1681016fe489b85393a54
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3127a99f2056582e89628fe1627c6449f7414e88942b204beef69227a73673c
+oid sha256:be7133af0a5af4c2118c63e10d2132ecb35d826f7652a17d0ce3984fc7527478
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:094837089fa2ed1c4f9dc6c25bac04422ed41c22630725ca5cdf86ffa65f03cf
+oid sha256:787ef78ee12881294c4aa83ed64603709fff88fc133de1a040e06eba2a245935
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002628888564334745,
+  "epoch": 0.0029209872937052722,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 2.372,
       "eval_steps_per_second": 2.372,
       "step": 9
+    },
+    {
+      "epoch": 0.0029209872937052722,
+      "grad_norm": 47.45390701293945,
+      "learning_rate": 0.00014,
+      "loss": 6.6697,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6328165488132096.0,
+  "total_flos": 7031294986813440.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null