Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c61a13d663d773c74fa8b36c72e1431ebf9cd271e9282391111e52151d52b2
+oid sha256:d280670662de8e5da13acf35ac6153206fb3c4b207e935cc1e2299b8c836f445
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd18025b932ac0357eb201ad8d9476a484fa40d354ee1b644139b59b883e1485
+oid sha256:60aa2c362346f92b2f19516735742b4e8e33056d93e5804f99c0129938706a47
 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": 0.09303712539138213,
+  "epoch": 0.11927836588638735,
   "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": 42.522,
       "eval_steps_per_second": 21.261,
       "step": 39
+    },
+    {
+      "epoch": 0.09542269270910989,
+      "grad_norm": 0.2588385045528412,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0422,
+      "step": 40
+    },
+    {
+      "epoch": 0.09780826002683764,
+      "grad_norm": 0.3525508940219879,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0671,
+      "step": 41
+    },
+    {
+      "epoch": 0.10019382734456538,
+      "grad_norm": 0.25098052620887756,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0409,
+      "step": 42
+    },
+    {
+      "epoch": 0.10257939466229313,
+      "grad_norm": 0.3437732458114624,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0647,
+      "step": 43
+    },
+    {
+      "epoch": 0.10496496198002088,
+      "grad_norm": 0.1902293562889099,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0407,
+      "step": 44
+    },
+    {
+      "epoch": 0.10735052929774862,
+      "grad_norm": 0.2526785135269165,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0433,
+      "step": 45
+    },
+    {
+      "epoch": 0.10973609661547637,
+      "grad_norm": 0.33351102471351624,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0559,
+      "step": 46
+    },
+    {
+      "epoch": 0.11212166393320412,
+      "grad_norm": 0.23994620144367218,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0366,
+      "step": 47
+    },
+    {
+      "epoch": 0.11450723125093186,
+      "grad_norm": 0.23394052684307098,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0506,
+      "step": 48
+    },
+    {
+      "epoch": 0.11689279856865961,
+      "grad_norm": 0.25432488322257996,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0285,
+      "step": 49
+    },
+    {
+      "epoch": 0.11927836588638735,
+      "grad_norm": 0.21557337045669556,
+      "learning_rate": 0.0,
+      "loss": 0.0358,
+      "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": 2.570603760451584e+16,
+  "total_flos": 3.2956458467328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null