Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd8c19f6ea3888e2ad5a49c8d91b85f245ef022c848c28c8fc64158033dd94f
+oid sha256:f59b60906ec12bb38e609a79a6c419746d3e93f38f8c7cec144c89489fee4df2
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60ef5d4221e36f2aae349222fb44230e11513285e98c5e9a73c18f2ba88c855f
+oid sha256:d6df7a57dc4e210891437de232e0fbb1cff6456ae507bc1519dade500f1ef870
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a98b2b218679ba712e6baf988604902b43544a52267439d578c868f840d4661
+oid sha256:114224757da4962caeb43ca028494d28dd2ae4bb1d66d3f9f0e7c56b11d317a1
 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": 0.04265208475734791,
+  "epoch": 0.05468215994531784,
   "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": 51.834,
       "eval_steps_per_second": 25.934,
       "step": 39
+    },
+    {
+      "epoch": 0.043745727956254275,
+      "grad_norm": 22.722843170166016,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.415,
+      "step": 40
+    },
+    {
+      "epoch": 0.04483937115516063,
+      "grad_norm": 20.1871395111084,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 8.9222,
+      "step": 41
+    },
+    {
+      "epoch": 0.045933014354066985,
+      "grad_norm": 19.610918045043945,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 7.8748,
+      "step": 42
+    },
+    {
+      "epoch": 0.04702665755297334,
+      "grad_norm": 19.86541175842285,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 9.8181,
+      "step": 43
+    },
+    {
+      "epoch": 0.0481203007518797,
+      "grad_norm": 15.583364486694336,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 8.7584,
+      "step": 44
+    },
+    {
+      "epoch": 0.04921394395078606,
+      "grad_norm": 19.862598419189453,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.7709,
+      "step": 45
+    },
+    {
+      "epoch": 0.05030758714969241,
+      "grad_norm": 22.887357711791992,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 9.1935,
+      "step": 46
+    },
+    {
+      "epoch": 0.05140123034859877,
+      "grad_norm": 20.946556091308594,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 6.5477,
+      "step": 47
+    },
+    {
+      "epoch": 0.05249487354750513,
+      "grad_norm": 19.912525177001953,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 7.5449,
+      "step": 48
+    },
+    {
+      "epoch": 0.053588516746411484,
+      "grad_norm": 17.380966186523438,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 7.0048,
+      "step": 49
+    },
+    {
+      "epoch": 0.05468215994531784,
+      "grad_norm": 26.645334243774414,
+      "learning_rate": 0.0,
+      "loss": 13.126,
+      "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": 1.897868608457933e+16,
+  "total_flos": 2.40962761654272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null