Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:909b083afcbdfc3382c1b7c8320875f3f64ad0a3ff31fea68e544590814501c9
+oid sha256:53afecfd67a91d4a2aad3f5db113c466a27cefef8ad7eed9563ae676d06dfacf
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b61e5ddab0bc1de7716bba07aad768398dc4c0221373cf9bcf1b349ea85a7f
+oid sha256:47ae655c264990c9098a5ec4b548e8af336ad66329e8984acb61f0da136baa1f
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3093311cde9ca58b8a5ff2c5cb16f96d74bc8f909add43bd289243be11a0e4
+oid sha256:950c5cceb85e460a2a6d67642a8393ef4a1e5902e2c55873fdcea4b712960518
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.049225159525979945,
+  "epoch": 0.05742935278030994,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 4.523,
       "eval_steps_per_second": 0.565,
       "step": 54
+    },
+    {
+      "epoch": 0.05195989061075661,
+      "grad_norm": 9.884892463684082,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 3.4851,
+      "step": 57
+    },
+    {
+      "epoch": 0.054694621695533276,
+      "grad_norm": 8.605599403381348,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 4.5235,
+      "step": 60
+    },
+    {
+      "epoch": 0.05742935278030994,
+      "grad_norm": 8.588393211364746,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 3.8852,
+      "step": 63
+    },
+    {
+      "epoch": 0.05742935278030994,
+      "eval_loss": 0.9350164532661438,
+      "eval_runtime": 408.6463,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 0.565,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4273528823231283e+17,
+  "total_flos": 1.6629012643813786e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null