Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f317f6a0c511a7f23df9645b98197df98f14034ccf063b9d4a1032532a6bce7
+oid sha256:ad79cb68a19f23fd51db735456509b9c8aebbcd54395a52f5465b66953dd30e0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3381d8f64e9fac412596e1a44b625ae5d48fddb41456467fe2b4583224ee9e2
+oid sha256:904356e2827ae5d6ca43fccfd05edf0264f2c20e3991e5784154bfcd4bebe404
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:891155de6377a4508f22e954f15f57ef4af67ae2e130e02796b781a8ce5af0a1
+oid sha256:20d92e2da927de0c21789d0c8191e427e9bc3b33c3c52072cf78958d2a2ceaf2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e3b504f4b478d50a181eaa2ef317405b60ed8d97be9beec3f1a5226df2330f
+oid sha256:6b28ee0addfe1fdb5c9554035d0aace280dc61b8aded9640b8ddc91a063558e8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003488710146332009,
+  "epoch": 0.0038763446070355654,
   "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": 5.963,
       "eval_steps_per_second": 2.984,
       "step": 9
+    },
+    {
+      "epoch": 0.0038763446070355654,
+      "grad_norm": 22.62554931640625,
+      "learning_rate": 0.0003,
+      "loss": 1.3425,
+      "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": 1.3353971104088064e+16,
+  "total_flos": 1.483774567120896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null