Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c1cf25f2e64a762812b766bfbd6094c2648247b4bedd6dd277bb80850dc8b59
+oid sha256:8bc37cd1fda8dfd1b39b977dec0658a3efa655517ac13e180a02093a5408beca
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0581a613fa7f7250999bc47adf76301a517c7eda8c7c6c9b9847257e5783a54
+oid sha256:5271ff8559b10b2c4535ccd083bde78232e76af49079888202ed48428f4cdb2b
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd4864e9f309f8e6c83f1076e0c0fa52b90cea112acff1a81371b246c70bc386
+oid sha256:f4fdcf50e4107dcde767ba8774e49b404a9d984ae9f0c993407d902c3b221015
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4748858447488584,
+  "epoch": 0.7123287671232876,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 19.329,
       "eval_steps_per_second": 10.085,
       "step": 26
+    },
+    {
+      "epoch": 0.4931506849315068,
+      "grad_norm": 0.8352602124214172,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 2.2883,
+      "step": 27
+    },
+    {
+      "epoch": 0.5114155251141552,
+      "grad_norm": 1.067049503326416,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 1.8978,
+      "step": 28
+    },
+    {
+      "epoch": 0.5296803652968036,
+      "grad_norm": 0.9249391555786133,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 2.0507,
+      "step": 29
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 1.3743081092834473,
+      "learning_rate": 0.0001,
+      "loss": 2.141,
+      "step": 30
+    },
+    {
+      "epoch": 0.5662100456621004,
+      "grad_norm": 1.0360537767410278,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 2.0678,
+      "step": 31
+    },
+    {
+      "epoch": 0.5844748858447488,
+      "grad_norm": 1.2677396535873413,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.4418,
+      "step": 32
+    },
+    {
+      "epoch": 0.6027397260273972,
+      "grad_norm": 1.047782301902771,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 2.0606,
+      "step": 33
+    },
+    {
+      "epoch": 0.6210045662100456,
+      "grad_norm": 1.4692909717559814,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.1455,
+      "step": 34
+    },
+    {
+      "epoch": 0.639269406392694,
+      "grad_norm": 1.2505451440811157,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.4692,
+      "step": 35
+    },
+    {
+      "epoch": 0.6575342465753424,
+      "grad_norm": 1.357511043548584,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 2.1996,
+      "step": 36
+    },
+    {
+      "epoch": 0.6757990867579908,
+      "grad_norm": 1.1560858488082886,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 2.1283,
+      "step": 37
+    },
+    {
+      "epoch": 0.6940639269406392,
+      "grad_norm": 1.3388383388519287,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.1192,
+      "step": 38
+    },
+    {
+      "epoch": 0.7123287671232876,
+      "grad_norm": 0.9266037940979004,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 2.0413,
+      "step": 39
+    },
+    {
+      "epoch": 0.7123287671232876,
+      "eval_loss": 2.1001837253570557,
+      "eval_runtime": 1.2054,
+      "eval_samples_per_second": 19.081,
+      "eval_steps_per_second": 9.955,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5438843085914112.0,
+  "total_flos": 8260884309737472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null