Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dd6e1c52d6e42dec3dd2c1057fce4abceb0e37f73b967a9cb698c2738b1e550
+oid sha256:fea354e32aee4794b21df0a6849e16a9f576f690bbaebd87aaee47a0c2f4a923
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc8448203620cbe4041023e11b4d9ff6c63b5499fc5769e254bfc778c39309d
+oid sha256:c638dfc8b7d2a1403503706de251c6df17363593f9f1a36bf01e2dae72382186
 size 164464564

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7093d71015ea15f57870e821d0868484fcbed74130e00bf84f631cbdac093e1c
+oid sha256:2944517e129c06a852c49794503048fba5f59a295db889beed8dbb938a2814b3
 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": 0.002467977985636368,
+  "epoch": 0.003290637314181824,
   "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": 19.83,
       "eval_steps_per_second": 4.958,
       "step": 150
+    },
+    {
+      "epoch": 0.0026325098513454593,
+      "grad_norm": 1.0844966173171997,
+      "learning_rate": 0.0002,
+      "loss": 1.6134,
+      "step": 160
+    },
+    {
+      "epoch": 0.0027970417170545504,
+      "grad_norm": 0.7255051732063293,
+      "learning_rate": 0.0002,
+      "loss": 1.5103,
+      "step": 170
+    },
+    {
+      "epoch": 0.002961573582763642,
+      "grad_norm": 1.0039361715316772,
+      "learning_rate": 0.0002,
+      "loss": 1.5299,
+      "step": 180
+    },
+    {
+      "epoch": 0.003126105448472733,
+      "grad_norm": 0.8159350752830505,
+      "learning_rate": 0.0002,
+      "loss": 1.3751,
+      "step": 190
+    },
+    {
+      "epoch": 0.003290637314181824,
+      "grad_norm": 0.9161156415939331,
+      "learning_rate": 0.0002,
+      "loss": 1.4981,
+      "step": 200
+    },
+    {
+      "epoch": 0.003290637314181824,
+      "eval_loss": 1.5143574476242065,
+      "eval_runtime": 1291.2982,
+      "eval_samples_per_second": 19.818,
+      "eval_steps_per_second": 4.955,
+      "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": 5.27255432331264e+16,
+  "total_flos": 7.03007243108352e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null