Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed1e8e98a3b0d7bce1a489d41abc4051b77ab2faf969fe9e00495bff7c8e7a7
+oid sha256:053b25998acf6b9d81403212598b058bd79d27106d7546699086412826216afb
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec97a4bae5f4f421b91055d6bdc92e652cefa73fee36b383f4a4ff523b4765a
+oid sha256:b3129fd8b5808adfd7215fb57353ae058f5133dc9b1efdf38f972f075697f8f7
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f537d6df07787c716bf4621ea221744763bd88e92a07f95d1fa6f6a06d8ac757
+oid sha256:0a016715ccb0112ab1394743f94acfb298ac9ccf9cd4cd745ca6d3b1bffe35a3
 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": 0.39518682710576314,
+  "epoch": 0.506649778340722,
   "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": 42.441,
       "eval_steps_per_second": 21.348,
       "step": 39
+    },
+    {
+      "epoch": 0.4053198226725776,
+      "grad_norm": 1.2004624605178833,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1043,
+      "step": 40
+    },
+    {
+      "epoch": 0.415452818239392,
+      "grad_norm": 0.6554136872291565,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.059,
+      "step": 41
+    },
+    {
+      "epoch": 0.42558581380620647,
+      "grad_norm": 2.516598701477051,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2211,
+      "step": 42
+    },
+    {
+      "epoch": 0.4357188093730209,
+      "grad_norm": 0.694494366645813,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0519,
+      "step": 43
+    },
+    {
+      "epoch": 0.44585180493983534,
+      "grad_norm": 0.9121596217155457,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0693,
+      "step": 44
+    },
+    {
+      "epoch": 0.4559848005066498,
+      "grad_norm": 0.816668689250946,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0688,
+      "step": 45
+    },
+    {
+      "epoch": 0.4661177960734642,
+      "grad_norm": 0.7210935354232788,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0747,
+      "step": 46
+    },
+    {
+      "epoch": 0.47625079164027867,
+      "grad_norm": 0.6753107309341431,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0283,
+      "step": 47
+    },
+    {
+      "epoch": 0.4863837872070931,
+      "grad_norm": 0.4177698791027069,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0249,
+      "step": 48
+    },
+    {
+      "epoch": 0.49651678277390754,
+      "grad_norm": 1.1643296480178833,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.1529,
+      "step": 49
+    },
+    {
+      "epoch": 0.506649778340722,
+      "grad_norm": 1.1032949686050415,
+      "learning_rate": 0.0,
+      "loss": 0.0554,
+      "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