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:d75f6d58b52b19e33a9201cfe90d39b1c0ea115a61337cddc1bb747a095d45d3
+oid sha256:82d4b7506a3bdd6a5f716c83b0fe0378e520bb20fbd738371ac1f1bdf75ac19a
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b7cca31449f07d349d6a85e8208701efe19d69e843bab59d62fa305d9e6c52
+oid sha256:cccf801c3932dacac1e25e7b943883f26eeb77519858549b37a95d4ae67c2fb5
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea790a6d7ded2d403b9f6bb0e490729d25eeb947822fcee7d950e6fe6a5a2385
+oid sha256:6bca983b309063a996168bc9ba0246dee10aad731d5eafae85ac843af75455c4
 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": 0.028279654359780047,
+  "epoch": 0.031421838177533384,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -94,6 +94,13 @@
       "eval_samples_per_second": 24.653,
       "eval_steps_per_second": 12.327,
       "step": 9
+    },
+    {
+      "epoch": 0.031421838177533384,
+      "grad_norm": 4.115271091461182,
+      "learning_rate": 0.0002,
+      "loss": 2.8524,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -108,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 216490963894272.0,
+  "total_flos": 240545515438080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null