Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0559b6be4577e6505c674c1d64a0fe28a81db911c8572cbf258123cc67c75a0c
+oid sha256:b688fb183c8567d60f826590c26990b88ae727875924f3e51488aa191413fd96
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28568bba818770492fa3450bb4994fa67fff313f84f9eb844b1862d14dc1ef5
+oid sha256:0eedb5c2de3bbb4d4e6e04874245ac3fb948783d7813dd64449f293f6fc77434
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2b1cb1b881b2c5d20961baae5b2d3881fe6eec1e7679ede3e5223de0ac55407
+oid sha256:1f7d20f34a9608ed2f797be8f3c51af7c2efbe128e378e73bfe7a3a6a12e1f52
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0125,
+  "epoch": 0.013888888888888888,
   "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": 148.167,
       "eval_steps_per_second": 74.084,
       "step": 9
+    },
+    {
+      "epoch": 0.013888888888888888,
+      "grad_norm": 9.973316192626953,
+      "learning_rate": 0.0002,
+      "loss": 10.0926,
+      "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": 19106560475136.0,
+  "total_flos": 21229511639040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null