Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b518381e436f9f7902f44562b3b2cea8ccfec9b231fabd9f353eab77a4231349
+oid sha256:b38da1d6f83078ffa6998d70685418b98526db2465fe1e04cda66335f2c5607e
 size 161714

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b768c453a99e7b6dc00d3c52d03af65eb4935ccba26774cfdefd95e9acff1f3
+oid sha256:24a51f1c1cee3c36fccf73836363d1680ff595f8d18e767dd4e9e311314ec8ee
 size 64750

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aca601cc331a87eee7a832e141a13869177225edb786e1de300173561df264a
+oid sha256:f9a7bea3fb41d6d5f4efc8570aa90e54f0331340dbfa35b3127e889d48fdc780
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01782346284420973,
+  "epoch": 0.023576009053187477,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 481.718,
       "eval_steps_per_second": 240.967,
       "step": 189
+    },
+    {
+      "epoch": 0.017917766880422483,
+      "grad_norm": 0.13090693950653076,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 6.8943,
+      "step": 190
+    },
+    {
+      "epoch": 0.01886080724254998,
+      "grad_norm": 0.09565740823745728,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 6.8892,
+      "step": 200
+    },
+    {
+      "epoch": 0.01980384760467748,
+      "grad_norm": 0.11801844090223312,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 6.8864,
+      "step": 210
+    },
+    {
+      "epoch": 0.02074688796680498,
+      "grad_norm": 0.08444403111934662,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 6.8881,
+      "step": 220
+    },
+    {
+      "epoch": 0.02168992832893248,
+      "grad_norm": 0.12999576330184937,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 6.8917,
+      "step": 230
+    },
+    {
+      "epoch": 0.022632968691059976,
+      "grad_norm": 0.146150603890419,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 6.8889,
+      "step": 240
+    },
+    {
+      "epoch": 0.023576009053187477,
+      "grad_norm": 0.11315950006246567,
+      "learning_rate": 0.0,
+      "loss": 6.89,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 158529226752.0,
+  "total_flos": 209614528512.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null