Training in progress, step 2300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:055fd433c57023d8f3f3c37b55c8f39f2d8077912e134692fb941c6ceaa8d3dc
+oid sha256:94a713a86db9bc34c528c6763676b2e9676016e96bba39c7c2e03eaf126fffc1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbe51d851f87fabe3efe2cf47380bdab3d4f11372f14e9aba710c1d3de441c53
+oid sha256:2261868c6954ecdb451d51c4263a3a640fb890cc9ad4bda9eea7b416eecfe6a6
 size 86889891

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45629f184581a841028a390b65e4a83cde165e4a2e3ebdc305433d36f49e75fa
+oid sha256:b63f58365c36b384841d3486f19ccc049afbeca015953eea42b0a028ab5db1e5
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a266efa0354b84cf6f8d9c45932823d37b45f72a0a6eed92e2200991f546c93
+oid sha256:24c37c5ce6445ba76eedd205387afe38c559919e2dbf727211d57a19ea6eb076
 size 1465

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.568153440952301,
-  "best_model_checkpoint": "./learnhub-checkpoints/checkpoint-2200",
-  "epoch": 1.7468994939974203,
+  "best_metric": 0.5583065748214722,
+  "best_model_checkpoint": "./learnhub-checkpoints/checkpoint-2300",
+  "epoch": 1.8262724476634586,
   "eval_steps": 100,
-  "global_step": 2200,
+  "global_step": 2300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -799,6 +799,42 @@
       "eval_samples_per_second": 1.333,
       "eval_steps_per_second": 0.667,
       "step": 2200
+    },
+    {
+      "epoch": 1.76674273241393,
+      "grad_norm": 12.30846881866455,
+      "learning_rate": 7.576544106808069e-05,
+      "loss": 3.5414,
+      "step": 2225
+    },
+    {
+      "epoch": 1.7865859708304397,
+      "grad_norm": 12.009100914001465,
+      "learning_rate": 7.369882483478906e-05,
+      "loss": 3.515,
+      "step": 2250
+    },
+    {
+      "epoch": 1.8064292092469492,
+      "grad_norm": 12.45872974395752,
+      "learning_rate": 7.1644207769797e-05,
+      "loss": 3.5223,
+      "step": 2275
+    },
+    {
+      "epoch": 1.8262724476634586,
+      "grad_norm": 11.39327335357666,
+      "learning_rate": 6.960252723410829e-05,
+      "loss": 3.6319,
+      "step": 2300
+    },
+    {
+      "epoch": 1.8262724476634586,
+      "eval_loss": 0.5583065748214722,
+      "eval_runtime": 797.5799,
+      "eval_samples_per_second": 1.33,
+      "eval_steps_per_second": 0.666,
+      "step": 2300
     }
   ],
   "logging_steps": 25,
@@ -818,7 +854,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1632407311591014e+17,
+  "total_flos": 2.26136386033238e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null