Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:369d6f91d16eaebb6b9e7a4d3110a8c8d6f87f4226794e33a28b6645426e210d
+oid sha256:e1dd4ea258708c553d534d9ac4dc71d159340a4731ff4a583fae52c2d94a0816
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2b0abc111609da6eb7147fd196cced7f523168f93293ce56cf2b3feb6ebdae
+oid sha256:7e1451fb0f857a88d9316be096caaea7645cf8af83ba78d1a28c63d54b220cec
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 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": 0.01579426951503493,
+  "epoch": 0.02024906348081401,
   "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": 589.971,
       "eval_steps_per_second": 295.056,
       "step": 39
+    },
+    {
+      "epoch": 0.01619925078465121,
+      "grad_norm": 0.013766695745289326,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9299,
+      "step": 40
+    },
+    {
+      "epoch": 0.01660423205426749,
+      "grad_norm": 0.019628174602985382,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 11.9294,
+      "step": 41
+    },
+    {
+      "epoch": 0.01700921332388377,
+      "grad_norm": 0.016885703429579735,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.9285,
+      "step": 42
+    },
+    {
+      "epoch": 0.017414194593500052,
+      "grad_norm": 0.01529628038406372,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 11.9281,
+      "step": 43
+    },
+    {
+      "epoch": 0.01781917586311633,
+      "grad_norm": 0.01732531376183033,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.9294,
+      "step": 44
+    },
+    {
+      "epoch": 0.01822415713273261,
+      "grad_norm": 0.014228262938559055,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9297,
+      "step": 45
+    },
+    {
+      "epoch": 0.01862913840234889,
+      "grad_norm": 0.017510289326310158,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.9293,
+      "step": 46
+    },
+    {
+      "epoch": 0.019034119671965173,
+      "grad_norm": 0.015506377443671227,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 11.9295,
+      "step": 47
+    },
+    {
+      "epoch": 0.019439100941581453,
+      "grad_norm": 0.016405014321208,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 11.9275,
+      "step": 48
+    },
+    {
+      "epoch": 0.019844082211197732,
+      "grad_norm": 0.014786036685109138,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 11.9295,
+      "step": 49
+    },
+    {
+      "epoch": 0.02024906348081401,
+      "grad_norm": 0.016270695254206657,
+      "learning_rate": 0.0,
+      "loss": 11.929,
+      "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": 18433179648.0,
+  "total_flos": 23632281600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null