Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6804b423ab579eac14abfe4a914746b5787222a8c5002b9bfcb979a342b3b30b
+oid sha256:703471b72faf9b452752ea3fc16099361e8621d25c714f672bbac359bc55751e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edb758723c8a090c620920b81781b67cfa1d34a1913cc9e4b83a08c4bf5b030e
+oid sha256:86ec04b6105fca4f1c0caacebac2c1488c5e1eaaea8010caefc8c7878614b272
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c72461d8b102f8348796119289aad1a7993b551f980fac40ec203302a5c72e0
+oid sha256:f8e9eae442f771da3806c99b5cd6522f74f754ffe88b669e7b10de01669cb969
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4339360222531293,
+  "epoch": 0.5563282336578581,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 6.984,
       "eval_steps_per_second": 3.492,
       "step": 39
+    },
+    {
+      "epoch": 0.44506258692628653,
+      "grad_norm": 0.26844772696495056,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.637,
+      "step": 40
+    },
+    {
+      "epoch": 0.4561891515994437,
+      "grad_norm": 0.3411906361579895,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.6441,
+      "step": 41
+    },
+    {
+      "epoch": 0.4673157162726008,
+      "grad_norm": 0.3042059540748596,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.584,
+      "step": 42
+    },
+    {
+      "epoch": 0.47844228094575797,
+      "grad_norm": 0.24161170423030853,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.653,
+      "step": 43
+    },
+    {
+      "epoch": 0.48956884561891517,
+      "grad_norm": 0.23014530539512634,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.6039,
+      "step": 44
+    },
+    {
+      "epoch": 0.5006954102920723,
+      "grad_norm": 0.23123666644096375,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6084,
+      "step": 45
+    },
+    {
+      "epoch": 0.5118219749652295,
+      "grad_norm": 0.24543774127960205,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.67,
+      "step": 46
+    },
+    {
+      "epoch": 0.5229485396383866,
+      "grad_norm": 0.2833655774593353,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.7551,
+      "step": 47
+    },
+    {
+      "epoch": 0.5340751043115438,
+      "grad_norm": 0.3481193780899048,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.6205,
+      "step": 48
+    },
+    {
+      "epoch": 0.545201668984701,
+      "grad_norm": 0.3575291037559509,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.6147,
+      "step": 49
+    },
+    {
+      "epoch": 0.5563282336578581,
+      "grad_norm": 0.3505605459213257,
+      "learning_rate": 0.0,
+      "loss": 0.6294,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.3146883247085978e+17,
+  "total_flos": 2.967549134241792e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null