Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06a288d66f41ae1cab29cb7af52be5371834ad3f32f4eabfe3e0cf09b1846a08
+oid sha256:5d8782bc461e8b015fe740a65535aa25fa75d17415539d401610c2b1d9d0a7d6
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eed9294f5bcb676d69a7f7204ed2a39ae8754693599ccf55dddaa1ee3961ad1
+oid sha256:235a0f308146e6cf8a010693b5fab3580941eaf94971f2b643d8c142d33ce1e0
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76a9f89e960cac0452a77d3db9f5d20ff25daffc7df7f340fe51556fcbd9bfed
+oid sha256:5266bdd4b52a1b86fdc9530ab1dabc1ae80542c8a6e21489d8e104bd2d986b44
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21649484536082475,
+  "epoch": 0.24742268041237114,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 6.809,
       "eval_steps_per_second": 0.862,
       "step": 63
+    },
+    {
+      "epoch": 0.2268041237113402,
+      "grad_norm": 2.0945565700531006,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.8955,
+      "step": 66
+    },
+    {
+      "epoch": 0.23711340206185566,
+      "grad_norm": 2.2720227241516113,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.9467,
+      "step": 69
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "grad_norm": 1.7193487882614136,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.9671,
+      "step": 72
+    },
+    {
+      "epoch": 0.24742268041237114,
+      "eval_loss": 0.7079923748970032,
+      "eval_runtime": 72.1273,
+      "eval_samples_per_second": 6.794,
+      "eval_steps_per_second": 0.86,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1900710513737728e+17,
+  "total_flos": 2.516008518549504e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null