Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d999a720a09a97737c26ce32c21e5de5b4236cd63a1695d94a7bc8d6c5a21a
+oid sha256:616dbab98413ecf9f418e8f9ae38a59bc94bfaa0690ecd1ef7bd6b7ab7fe954c
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:209d76bf0744d4004c63d6a5b7dbd566ff13b3ceceead4003541fd1453451a41
+oid sha256:b9bdbef78055f0b958f7e9945f72b126a773e39fb9a0c28d8f42dee0597fe998
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ce98eb3bd4988150839f3fd43c14f767dcb0ee749e6ebd7a2ba356a470c3bd7
+oid sha256:6bfb33689cdbfcab2c5cb7201fa1f0004af1ad986aca9716dbf0639bc4ce981c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09955328653477984,
+  "epoch": 0.1276324186343331,
   "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": 8.733,
       "eval_steps_per_second": 4.393,
       "step": 39
+    },
+    {
+      "epoch": 0.1021059349074665,
+      "grad_norm": 0.742786705493927,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 5.2024,
+      "step": 40
+    },
+    {
+      "epoch": 0.10465858328015316,
+      "grad_norm": 0.637015163898468,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 4.9553,
+      "step": 41
+    },
+    {
+      "epoch": 0.10721123165283983,
+      "grad_norm": 0.6206537485122681,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 4.4764,
+      "step": 42
+    },
+    {
+      "epoch": 0.10976388002552648,
+      "grad_norm": 0.7534269690513611,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 5.0251,
+      "step": 43
+    },
+    {
+      "epoch": 0.11231652839821314,
+      "grad_norm": 0.642451286315918,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 4.9982,
+      "step": 44
+    },
+    {
+      "epoch": 0.1148691767708998,
+      "grad_norm": 0.6466948986053467,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 5.0004,
+      "step": 45
+    },
+    {
+      "epoch": 0.11742182514358647,
+      "grad_norm": 0.6484655141830444,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 4.6644,
+      "step": 46
+    },
+    {
+      "epoch": 0.11997447351627313,
+      "grad_norm": 0.6601917147636414,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 4.7506,
+      "step": 47
+    },
+    {
+      "epoch": 0.1225271218889598,
+      "grad_norm": 0.6565570831298828,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 5.1511,
+      "step": 48
+    },
+    {
+      "epoch": 0.12507977026164646,
+      "grad_norm": 0.6291937232017517,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 4.7335,
+      "step": 49
+    },
+    {
+      "epoch": 0.1276324186343331,
+      "grad_norm": 0.6736301183700562,
+      "learning_rate": 0.0,
+      "loss": 5.0993,
+      "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": 2.6329597083648e+16,
+  "total_flos": 3.37188711038976e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null