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:e6942a0b8fc6c44fc2daa155bff7d37ae8a51d626917f36a2df8231aa0628ccf
+oid sha256:8e3a94d91f4d4b779b37bc8fda34395104c98b9e87507a663488f3c451e20c36
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7566731baea0d1426f7df87484fb97a4bccac8a04401ccbe2e0ba294637517e
+oid sha256:f7b8a73f6a0ce65ba5c27ce37578a08e67e1a76a7ecb87a1f10c60fe809590a9
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd55801f4f1f6c8099b7618def020d8cd0dfd9ec3ef51ae0ef59c1850c2f11ef
+oid sha256:062f1d4e547b52e8ecdeed4781910de8fd03426f0ed66ee3788621f0266a46ea
 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": 0.029779517037319844,
+  "epoch": 0.0381788679965639,
   "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": 38.087,
       "eval_steps_per_second": 19.043,
       "step": 39
+    },
+    {
+      "epoch": 0.03054309439725112,
+      "grad_norm": 4.678173065185547,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.2103,
+      "step": 40
+    },
+    {
+      "epoch": 0.0313066717571824,
+      "grad_norm": 4.426128387451172,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 7.455,
+      "step": 41
+    },
+    {
+      "epoch": 0.032070249117113675,
+      "grad_norm": 5.750243186950684,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.0289,
+      "step": 42
+    },
+    {
+      "epoch": 0.032833826477044956,
+      "grad_norm": 5.712514400482178,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 10.2319,
+      "step": 43
+    },
+    {
+      "epoch": 0.033597403836976236,
+      "grad_norm": 4.766389846801758,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 7.6648,
+      "step": 44
+    },
+    {
+      "epoch": 0.03436098119690751,
+      "grad_norm": 5.167623996734619,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.2538,
+      "step": 45
+    },
+    {
+      "epoch": 0.03512455855683879,
+      "grad_norm": 5.637135982513428,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 6.7357,
+      "step": 46
+    },
+    {
+      "epoch": 0.03588813591677007,
+      "grad_norm": 4.531375885009766,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 6.535,
+      "step": 47
+    },
+    {
+      "epoch": 0.036651713276701345,
+      "grad_norm": 6.260673522949219,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 8.6059,
+      "step": 48
+    },
+    {
+      "epoch": 0.037415290636632625,
+      "grad_norm": 5.334906578063965,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 8.5101,
+      "step": 49
+    },
+    {
+      "epoch": 0.0381788679965639,
+      "grad_norm": 4.816957950592041,
+      "learning_rate": 0.0,
+      "loss": 8.5046,
+      "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": 2.232921591329587e+16,
+  "total_flos": 2.8708991888523264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null