Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26e8be1789f8c49496926f0791b3d61053eae453e57ed965e31d4c51619fdf66
+oid sha256:168371c5611f347096819a5d40285abdbb52866135e6d827c0744ec8f68d6a95
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda2d0c2eff7ef1a5ef07fb2d374e083dc015711b10e642c6b5615dc96cbf5b5
+oid sha256:5116b2d9a646eb1bb533b580b78788a1c248e5cd070a6cb77356ef0ea130fc44
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4138b821d9c89fa1a1358214da9b1d8edb06b1a8e110707d57ada3bcf105a107
+oid sha256:f2e11f130c9ff2b44f7e4f99c64cd27329874f2597bd0727f766f82514a06feb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2507030936118923,
+  "epoch": 0.32141422257934915,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 27.394,
       "eval_steps_per_second": 3.424,
       "step": 30
+    },
+    {
+      "epoch": 0.2571313780634793,
+      "grad_norm": 0.17056262493133545,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.982,
+      "step": 40
+    },
+    {
+      "epoch": 0.2571313780634793,
+      "eval_loss": 1.969922423362732,
+      "eval_runtime": 38.2122,
+      "eval_samples_per_second": 27.426,
+      "eval_steps_per_second": 3.428,
+      "step": 40
+    },
+    {
+      "epoch": 0.32141422257934915,
+      "grad_norm": 0.1600278913974762,
+      "learning_rate": 0.0,
+      "loss": 1.9708,
+      "step": 50
+    },
+    {
+      "epoch": 0.32141422257934915,
+      "eval_loss": 1.9691742658615112,
+      "eval_runtime": 38.2128,
+      "eval_samples_per_second": 27.425,
+      "eval_steps_per_second": 3.428,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.07877823348736e+16,
+  "total_flos": 6.463267094396928e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null