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:cf1ef681bacc89a848700eeaa4ef92416ef6e365bf799a8e2fa4dfe44c59282e
+oid sha256:f0dc74eb4f1664d79e8ca2ad4c0dcaf65b8ebee3025e61594d69d01fb996247d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45185dea832327b9d68a06373b811b428124e11655ef59d9751c97288f635b17
+oid sha256:2fa94faad5f7c2fac41c1d3489928c35288395f9537c10cdb8f345784281ca99
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8342d6f38894c838a543183f90853fe4cfc9a7f7a735ec728b9f9f2daf305e32
+oid sha256:74d3fe4297fd36d6939c92e784b1ab4781c227d97ebf023707e527bcbb1c9fe4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3102e3be46ad9a9b5ceee743993b1b6ad0818bd4c7d22888f9c7d0317f12b2bd
+oid sha256:d102a8b779e588307a5ff1ccea3e1e9ce6254fd84338a3b83b04cad35c2649e7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006218905472636816,
+  "epoch": 0.0012437810945273632,
   "eval_steps": 1000,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,13 +157,163 @@
       "learning_rate": 0.00016421052631578948,
       "loss": 1.7079,
       "step": 25
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00016210526315789473,
+      "loss": 1.4506,
+      "step": 26
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00016,
+      "loss": 1.673,
+      "step": 27
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00015789473684210527,
+      "loss": 1.5159,
+      "step": 28
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00015578947368421052,
+      "loss": 1.8044,
+      "step": 29
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001536842105263158,
+      "loss": 1.311,
+      "step": 30
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00015157894736842108,
+      "loss": 1.5876,
+      "step": 31
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00014947368421052633,
+      "loss": 1.5843,
+      "step": 32
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00014736842105263158,
+      "loss": 1.7256,
+      "step": 33
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 1.5446,
+      "step": 34
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001431578947368421,
+      "loss": 1.9188,
+      "step": 35
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00014105263157894736,
+      "loss": 1.6284,
+      "step": 36
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00013894736842105264,
+      "loss": 1.6446,
+      "step": 37
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 1.5255,
+      "step": 38
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00013473684210526317,
+      "loss": 1.4796,
+      "step": 39
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00013263157894736842,
+      "loss": 1.8069,
+      "step": 40
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001305263157894737,
+      "loss": 1.5269,
+      "step": 41
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00012842105263157895,
+      "loss": 1.3387,
+      "step": 42
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 1.3193,
+      "step": 43
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 1.6728,
+      "step": 44
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00012210526315789474,
+      "loss": 1.5991,
+      "step": 45
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00012,
+      "loss": 1.6619,
+      "step": 46
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00011789473684210525,
+      "loss": 1.4312,
+      "step": 47
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00011578947368421053,
+      "loss": 1.4846,
+      "step": 48
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.0001136842105263158,
+      "loss": 1.3929,
+      "step": 49
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00011157894736842105,
+      "loss": 1.647,
+      "step": 50
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 1319123636748288.0,
+  "total_flos": 2841070876655616.0,
   "trial_name": null,
   "trial_params": null
 }