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:bb737bbf803684458da376d145449dbad76ffa48b1d48ed38a438933147d495f
+oid sha256:78b9574547553a123bd81cd609791de0743edd8d7610498441fff166e1f663fa
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb52086ff4487ae3718f264a09afb779728f26cad9b2a2bb8d62aff5ea56f1a3
+oid sha256:dc5b3514b3028f64b3591b7861f58fb7ab9927613827f507626d5b0549c8f1f2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3b3b57475d7121f4863fb9eecae03865b458e1b56620b5ee3bb01afb198405
+oid sha256:5981f72b5e7edf3d1d1fa2a795d367f560ddbdfdb6f50824315e8382d8f92fa4
 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": 0.35046728971962615,
+  "epoch": 0.4672897196261682,
   "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": 22.036,
       "eval_steps_per_second": 11.079,
       "step": 150
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "grad_norm": 0.8210671544075012,
+      "learning_rate": 0.0002,
+      "loss": 0.3825,
+      "step": 160
+    },
+    {
+      "epoch": 0.397196261682243,
+      "grad_norm": 0.7392200231552124,
+      "learning_rate": 0.0002,
+      "loss": 0.3859,
+      "step": 170
+    },
+    {
+      "epoch": 0.4205607476635514,
+      "grad_norm": 1.0374455451965332,
+      "learning_rate": 0.0002,
+      "loss": 0.3204,
+      "step": 180
+    },
+    {
+      "epoch": 0.4439252336448598,
+      "grad_norm": 1.1081548929214478,
+      "learning_rate": 0.0002,
+      "loss": 0.3013,
+      "step": 190
+    },
+    {
+      "epoch": 0.4672897196261682,
+      "grad_norm": 1.3603465557098389,
+      "learning_rate": 0.0002,
+      "loss": 0.3228,
+      "step": 200
+    },
+    {
+      "epoch": 0.4672897196261682,
+      "eval_loss": 0.3465375602245331,
+      "eval_runtime": 8.2205,
+      "eval_samples_per_second": 22.018,
+      "eval_steps_per_second": 11.07,
+      "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": 4.332604251281818e+16,
+  "total_flos": 5.766016543594906e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null