Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b36801039b7203e635bd732adfe2072950c5cb8ae24fc72ed41baaf8ef26a7
+oid sha256:cbc48534101af08c793cc5261662c01182bf1add9b30de59eb24e6ce8a2f35e1
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa08011ebbddcd3c98b59dc11ecdf630ca480d488560a7080664387e8358c055
+oid sha256:72132f9e0deabf3a07411f569680ec393dbcc21cf8de0d1979e0ffc242ebbcd1
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fea276383daa6be11cb41bcf079e20917a66b8a1df06264809ff50445c989c9
+oid sha256:70bb08e79cd87e26411515d4cfe540a1dfafd998745c321dfb4680b9ed334a58
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028145229383619477,
+  "epoch": 0.03752697251149264,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 273.837,
       "eval_steps_per_second": 136.918,
       "step": 150
+    },
+    {
+      "epoch": 0.030021578009194107,
+      "grad_norm": 0.053444866091012955,
+      "learning_rate": 0.0002,
+      "loss": 10.3482,
+      "step": 160
+    },
+    {
+      "epoch": 0.03189792663476874,
+      "grad_norm": 0.040338512510061264,
+      "learning_rate": 0.0002,
+      "loss": 10.3474,
+      "step": 170
+    },
+    {
+      "epoch": 0.03377427526034337,
+      "grad_norm": 0.049476925283670425,
+      "learning_rate": 0.0002,
+      "loss": 10.3492,
+      "step": 180
+    },
+    {
+      "epoch": 0.035650623885918005,
+      "grad_norm": 0.050676729530096054,
+      "learning_rate": 0.0002,
+      "loss": 10.3483,
+      "step": 190
+    },
+    {
+      "epoch": 0.03752697251149264,
+      "grad_norm": 0.034670390188694,
+      "learning_rate": 0.0002,
+      "loss": 10.3478,
+      "step": 200
+    },
+    {
+      "epoch": 0.03752697251149264,
+      "eval_loss": 10.347277641296387,
+      "eval_runtime": 8.1913,
+      "eval_samples_per_second": 273.948,
+      "eval_steps_per_second": 136.974,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3701472460800.0,
+  "total_flos": 4949305098240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null