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:b39424892d2b750e22eaa5c0216a3d5de439c4f797acbb4f9c456ba34c8a355e
+oid sha256:adac11fe9b13bf1b76ad183dcdd7e81553c07712d98750b3a009b0fde4a8f61b
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802ed36b7afa5017c93a6fd3510a67856790006ca5398e785e74ab898f545ef4
+oid sha256:2f08485c8ba652d542301fa3d085478be8bed85616b2bcb26abf83e95f4faea3
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d6b797df47639e9d56f9b6739dd1a2f36c0e6d770b9652f614b93b6b7b4046
+oid sha256:887c396fe906e451edd5dc1fa4bc857e822a44e9109e8deb2d1acfa642c3f206
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8074483b54111bf60815c86124b01e5486a0c97c3c0bcc7642d6609b17e4381b
+oid sha256:c6c6ef871b14e9c2b6e6517244b08d50c3b172209dbf2c7f2f35e5b70f657975
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022006235099944985,
+  "epoch": 0.024451372333272204,
   "eval_steps": 34,
-  "global_step": 45,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -338,6 +338,41 @@
       "learning_rate": 0.00019618256431728194,
       "loss": 9.9237,
       "step": 45
+    },
+    {
+      "epoch": 0.02249526254661043,
+      "grad_norm": 9.941431195118076e+18,
+      "learning_rate": 0.0001956604419500441,
+      "loss": 8.1136,
+      "step": 46
+    },
+    {
+      "epoch": 0.022984289993275873,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 9.7949,
+      "step": 47
+    },
+    {
+      "epoch": 0.023473317439941317,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019451838281608197,
+      "loss": 10.1889,
+      "step": 48
+    },
+    {
+      "epoch": 0.02396234488660676,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019389883606150566,
+      "loss": 8.871,
+      "step": 49
+    },
+    {
+      "epoch": 0.024451372333272204,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019324722294043558,
+      "loss": 10.5181,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -357,7 +392,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.920158541807616e+16,
+  "total_flos": 1.102239837978624e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null