Training in progress, step 130, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9b95bc471cc3fea848c45abf3ec644b179a80655080267108d364c7410a07b
+oid sha256:c25138bad319d0c4c5729b1b2847d0a2e2c73a87f4ff6b0b44feb716aa4c3a8f
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd86cd5aaff0df3defda957eee1d5e98476a0bed9dff47a67adde018538ba72
+oid sha256:2691cfe587c2386184fe60bd924e63496f82a3568d470a15f8f6b2aa87d5bf3d
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9dfcfa634c3d602fbb32d8617cc1f5299a65b972221d7081152805a0ea9f6b3
+oid sha256:ae02f105e3120f5249e0cc5f5ee89c3c7189b19796356620717a201b623d87a1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a9f08177ba433a82ec0fa599b737a453ff55e83dd9d31c6fddaf5bc4b0a0b3
+oid sha256:4f9bc32841f0c3d8bc8ea90b0bc3413eece3c955acd985fe2913112493248454
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.032400996953752426,
+  "epoch": 0.03600110772639158,
   "eval_steps": 13,
-  "global_step": 117,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -360,6 +360,42 @@
       "eval_samples_per_second": 13.206,
       "eval_steps_per_second": 1.652,
       "step": 117
+    },
+    {
+      "epoch": 0.033231791747438386,
+      "grad_norm": 2.4200942516326904,
+      "learning_rate": 1.090842587659851e-05,
+      "loss": 1.3846,
+      "step": 120
+    },
+    {
+      "epoch": 0.034062586541124346,
+      "grad_norm": 2.8469035625457764,
+      "learning_rate": 8.899896227604509e-06,
+      "loss": 1.4455,
+      "step": 123
+    },
+    {
+      "epoch": 0.0348933813348103,
+      "grad_norm": 1.944390892982483,
+      "learning_rate": 7.077560319906695e-06,
+      "loss": 1.419,
+      "step": 126
+    },
+    {
+      "epoch": 0.03572417612849626,
+      "grad_norm": 2.8275833129882812,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.3674,
+      "step": 129
+    },
+    {
+      "epoch": 0.03600110772639158,
+      "eval_loss": 0.34357109665870667,
+      "eval_runtime": 460.8114,
+      "eval_samples_per_second": 13.198,
+      "eval_steps_per_second": 1.651,
+      "step": 130
     }
   ],
   "logging_steps": 3,
@@ -379,7 +415,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9026089571935846e+17,
+  "total_flos": 2.0955308444614656e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null