Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82b6c062750989e13cc6c31f673eb28ae7f34054528935e3efb54a06b33e193f
+oid sha256:2304d5ffc39c9f6e2498e7ffea78ad68a184ab2480b76bece47ecb403f4cfe35
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6b498b711ec5f0e8abf6d80fe36e5c89263ba6a857852931649201f8325b09
+oid sha256:84eb25bfc92b1128bb8bccdba8e3c4047bf63ad06b52282e6fdc3429bf313091
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a2b4355f0adc64fc321dace50424cb5a3dd3e04ef257930c533b857151ab4c
+oid sha256:b323befaf7852070089466e42bb3c84b599d8ed98c38f16e18b9f391b5b4b968
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
+oid sha256:e9573e9d18ad7803441c819253e1705231d5811c0e4f29747c0574440f588f00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2288135593220339,
+  "epoch": 0.3050847457627119,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,28 @@
       "eval_samples_per_second": 18.891,
       "eval_steps_per_second": 2.384,
       "step": 27
+    },
+    {
+      "epoch": 0.2542372881355932,
+      "grad_norm": 0.6635559797286987,
+      "learning_rate": 0.0001442909649383465,
+      "loss": 0.9048,
+      "step": 30
+    },
+    {
+      "epoch": 0.2966101694915254,
+      "grad_norm": 0.6447595357894897,
+      "learning_rate": 0.0001373602209226909,
+      "loss": 0.8876,
+      "step": 35
+    },
+    {
+      "epoch": 0.3050847457627119,
+      "eval_loss": 0.8686102032661438,
+      "eval_runtime": 22.2429,
+      "eval_samples_per_second": 18.882,
+      "eval_steps_per_second": 2.383,
+      "step": 36
     }
   ],
   "logging_steps": 5,
@@ -93,7 +115,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.18612518101975e+16,
+  "total_flos": 5.543787401891021e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null