Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36cb19536a0ee12ba49afa380ccf1fe42bf2babf1ab11886688b238a01ddf2f1
+oid sha256:1178168b28c25756aa4281636b07615bd568deb155c023af2357b810c89b6bd8
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c2e866352e6cb817611d33e434459e9b3504c82f49d59cd12a975eb6f753aa
+oid sha256:6b192370dcddd6f809f0285a706150377cc69a841ba60e767265a26908398199
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27035ea1efd96357598ccd3bea9cecacd80035eaa6d3792153213c56e73abd54
+oid sha256:b12cb19739dc8815fca38fee9b664feb211b45b4f898b0912e895eff0e96da92
 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": 0.04986149584487535,
+  "epoch": 0.055401662049861494,
   "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": 66.363,
       "eval_steps_per_second": 33.182,
       "step": 9
+    },
+    {
+      "epoch": 0.055401662049861494,
+      "grad_norm": 21.534534454345703,
+      "learning_rate": 0.00014,
+      "loss": 10.6711,
+      "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": 4886913613824.0,
+  "total_flos": 5429904015360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null