Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c260e5c0e8276d42d03a9a162c85270b7e1958064ce937c1d144c5375f9e59c
+oid sha256:0f27b06a4429d582368faeb5a9bafa77b2bde4f957d710da2d6745bd23f7a4f3
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a844b2abc40a617542b6e0dcb797905924b76e181ce5648f7b5dc0134abb898e
+oid sha256:2e340da27dc3cd961dd6902ff26de65f329badb470baeb96ed6ba799e03cb84f
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4bb0b5e6b7c80ecb411483c99281e80a04c0d48447d5eb2f3553b64ba3373a
+oid sha256:872f36967f4d997d0c5dd872feffb71ac01f371c16dc11e14af15fdd83fa10ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04454597372929754,
+  "epoch": 0.05711022272986865,
   "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": 17.072,
       "eval_steps_per_second": 8.559,
       "step": 39
+    },
+    {
+      "epoch": 0.045688178183894916,
+      "grad_norm": 1.4337252378463745,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.6615,
+      "step": 40
+    },
+    {
+      "epoch": 0.04683038263849229,
+      "grad_norm": 2.4315760135650635,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 1.6314,
+      "step": 41
+    },
+    {
+      "epoch": 0.047972587093089665,
+      "grad_norm": 1.203702688217163,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.8346,
+      "step": 42
+    },
+    {
+      "epoch": 0.04911479154768703,
+      "grad_norm": 1.5174435377120972,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 2.453,
+      "step": 43
+    },
+    {
+      "epoch": 0.05025699600228441,
+      "grad_norm": 1.5862349271774292,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.4518,
+      "step": 44
+    },
+    {
+      "epoch": 0.05139920045688178,
+      "grad_norm": 1.9814674854278564,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.2862,
+      "step": 45
+    },
+    {
+      "epoch": 0.052541404911479156,
+      "grad_norm": 1.388089656829834,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 2.4998,
+      "step": 46
+    },
+    {
+      "epoch": 0.05368360936607653,
+      "grad_norm": 2.509852409362793,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 2.025,
+      "step": 47
+    },
+    {
+      "epoch": 0.0548258138206739,
+      "grad_norm": 1.247580885887146,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 1.6155,
+      "step": 48
+    },
+    {
+      "epoch": 0.05596801827527127,
+      "grad_norm": 3.717909097671509,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 2.2619,
+      "step": 49
+    },
+    {
+      "epoch": 0.05711022272986865,
+      "grad_norm": 1.8729993104934692,
+      "learning_rate": 0.0,
+      "loss": 1.9623,
+      "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": 1.401054255120384e+16,
+  "total_flos": 1.7810011717632e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null