Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f34248fee66e861d07ec7ab4120fd465b14908d0e559a12feba47956c1d7f9f
+oid sha256:06b7377243dadd52b15e8628b07a6751149fc216682f00c4bad7e2fa1eced8f6
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea9fd7a8409fedcad052e0ff83734859f9201df640e8e8ae9efeae4b4e85ba77
+oid sha256:9683d37973e9fde77b6d6655fbae7fa08669912c216882cca51f3d4994c3a8c1
 size 41119636

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": 0.131009867730422,
+  "epoch": 0.16796136888515642,
   "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": 23.695,
       "eval_steps_per_second": 11.847,
       "step": 39
+    },
+    {
+      "epoch": 0.13436909510812514,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2932,
+      "step": 40
+    },
+    {
+      "epoch": 0.13772832248582825,
+      "grad_norm": NaN,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.5242,
+      "step": 41
+    },
+    {
+      "epoch": 0.1410875498635314,
+      "grad_norm": 0.3238716125488281,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.9333,
+      "step": 42
+    },
+    {
+      "epoch": 0.1444467772412345,
+      "grad_norm": 0.3042464852333069,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.9319,
+      "step": 43
+    },
+    {
+      "epoch": 0.14780600461893764,
+      "grad_norm": 0.31937065720558167,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.8955,
+      "step": 44
+    },
+    {
+      "epoch": 0.15116523199664078,
+      "grad_norm": 0.30120527744293213,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9155,
+      "step": 45
+    },
+    {
+      "epoch": 0.1545244593743439,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.735,
+      "step": 46
+    },
+    {
+      "epoch": 0.15788368675204703,
+      "grad_norm": NaN,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.5965,
+      "step": 47
+    },
+    {
+      "epoch": 0.16124291412975017,
+      "grad_norm": 0.3180822730064392,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.9638,
+      "step": 48
+    },
+    {
+      "epoch": 0.16460214150745328,
+      "grad_norm": NaN,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.9644,
+      "step": 49
+    },
+    {
+      "epoch": 0.16796136888515642,
+      "grad_norm": 0.3325708508491516,
+      "learning_rate": 0.0,
+      "loss": 0.9511,
+      "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": 5.126672385205862e+16,
+  "total_flos": 6.57265690411008e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null