Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8af796852461cc176be90e4187efb78b50d8456ff97a7c3920ec97c495635df8
+oid sha256:bb4ff8c4fcbfb8ec18219f86e85b9a34e5515f242c1a40db774cf688c3669385
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb2700fbf2c1be55a713166971c1b46adf924902c4df2a0b2aefa8d3a5f92b1
+oid sha256:e53cbc7327d962e5ff2f7062674f313db9da2bef739d297d8d8f725326961e91
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aafc92b6894a569ec483aa68ec2123c627b5a8b5e36deb2feacd058bf0591342
+oid sha256:a0838baa93092d83ad0051b5ed69e3b7549dfe2e1368a92b9a44da63580c6334
 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": 0.007401170873064046,
+  "epoch": 0.009789908562254028,
   "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": 17.232,
       "eval_steps_per_second": 8.617,
       "step": 189
+    },
+    {
+      "epoch": 0.0074403305073130616,
+      "grad_norm": 0.696219801902771,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 1.9602,
+      "step": 190
+    },
+    {
+      "epoch": 0.007831926849803222,
+      "grad_norm": 0.7096570134162903,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 1.9504,
+      "step": 200
+    },
+    {
+      "epoch": 0.008223523192293384,
+      "grad_norm": 0.708854615688324,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 1.9364,
+      "step": 210
+    },
+    {
+      "epoch": 0.008615119534783545,
+      "grad_norm": 0.6878980994224548,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 1.9827,
+      "step": 220
+    },
+    {
+      "epoch": 0.009006715877273707,
+      "grad_norm": 0.7576802968978882,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 2.0235,
+      "step": 230
+    },
+    {
+      "epoch": 0.009398312219763868,
+      "grad_norm": 0.6273877620697021,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 1.9479,
+      "step": 240
+    },
+    {
+      "epoch": 0.009789908562254028,
+      "grad_norm": 0.6269112229347229,
+      "learning_rate": 0.0,
+      "loss": 1.9015,
+      "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": 3.5355787001856e+16,
+  "total_flos": 4.681106199045734e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null