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:a77eb6a06e2a35f4b1705e26d218bf2f2feda3145e811beb44ce25cfa8d51c26
+oid sha256:9078a52db19b470ba6bbce68db89f22174bf8443ad82159129e32192a706f25b
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec4287016483fb356e958468356b34336f4aa3668cf659a9d2ae4b4b5d928e96
+oid sha256:9f3e81f368a9f9ece9d39f743bf2bb44ea9a06791bb9e9b34ac735a2f5cfe93e
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d799f504d9e96669c3b322ccf044cf42ed69181feb6c152cba674fa2359f08
+oid sha256:8b3f32ce9472813d7cc4998dd6f54d487ccf79d88132a529ec2b28324f14a0f2
 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": 0.043478260869565216,
+  "epoch": 0.04830917874396135,
   "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": 55.697,
       "eval_steps_per_second": 27.849,
       "step": 9
+    },
+    {
+      "epoch": 0.04830917874396135,
+      "grad_norm": 4.518380641937256,
+      "learning_rate": 0.0002,
+      "loss": 44.0229,
+      "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": 748783927296.0,
+  "total_flos": 831982141440.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null