Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b3a6143cf407cb072ab9cac3ba89eb179ab64b176e84dd1c0661aadd1ff0d6a
+oid sha256:835dd4d239ffa3dc25a3e721a77669aaa6c0336f25918baedba1c4b83f5741ba
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67e22455ba59dfbab988be608fd904788817a8d8acc140ceb1a045125d5e4523
+oid sha256:15a73092b18465b224a432d22c7244f1f1a89638e3c7996ff3511cfdbd565bea
 size 127788180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81724f6b9c5247f3a62cf570fa01adcf6cc8b5fd453850cfb8aab6bd795e61c
+oid sha256:0bee46af572f61407aa9a7b20e92421fb600a82cce0c7e6a5c223ecd6e0bf626
 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": 0.13888270643222791,
+  "epoch": 0.17805475183618963,
   "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": 4.264,
       "eval_steps_per_second": 2.137,
       "step": 39
+    },
+    {
+      "epoch": 0.1424438014689517,
+      "grad_norm": 1.3451905250549316,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8144,
+      "step": 40
+    },
+    {
+      "epoch": 0.1460048965056755,
+      "grad_norm": 1.5614116191864014,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.8939,
+      "step": 41
+    },
+    {
+      "epoch": 0.1495659915423993,
+      "grad_norm": 1.434024453163147,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.1714,
+      "step": 42
+    },
+    {
+      "epoch": 0.15312708657912308,
+      "grad_norm": 1.9399369955062866,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 2.3259,
+      "step": 43
+    },
+    {
+      "epoch": 0.15668818161584688,
+      "grad_norm": 1.6020128726959229,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.3047,
+      "step": 44
+    },
+    {
+      "epoch": 0.16024927665257066,
+      "grad_norm": 1.3612734079360962,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0302,
+      "step": 45
+    },
+    {
+      "epoch": 0.16381037168929447,
+      "grad_norm": 1.40798819065094,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.9763,
+      "step": 46
+    },
+    {
+      "epoch": 0.16737146672601824,
+      "grad_norm": 1.7111047506332397,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 2.0167,
+      "step": 47
+    },
+    {
+      "epoch": 0.17093256176274205,
+      "grad_norm": 1.519776701927185,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 2.0705,
+      "step": 48
+    },
+    {
+      "epoch": 0.17449365679946582,
+      "grad_norm": 1.4649944305419922,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.8096,
+      "step": 49
+    },
+    {
+      "epoch": 0.17805475183618963,
+      "grad_norm": 1.449601173400879,
+      "learning_rate": 0.0,
+      "loss": 1.6536,
+      "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": 3.969864967598899e+17,
+  "total_flos": 5.08957047128064e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null