Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c2ec4aaf73e828babd394219c77d4f76823d217a4bd1b859e0e965353902b5
+oid sha256:ba3cbc5d45b1ee32049c2be07b02914c7ed4b7af93093cb7d81666537fdce93c
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccbd319421ed7631b79cac9357ffeee8eaf309311a5284715ba0cc1dec1687f
+oid sha256:fedbd33761527622068a9867b22e44fa672365b26f7f0f3281a787b6120d0682
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49644ad8f5452e53758ca52013eb3650a3941bcec6083d72c46c935a677f7d88
+oid sha256:455977057132821379da92f1a77f9b1f540991d9dd7c684ba956aca72c970f71
 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": 0.011139598620811599,
+  "epoch": 0.012730969852356113,
   "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": 14.096,
       "eval_steps_per_second": 1.763,
       "step": 63
+    },
+    {
+      "epoch": 0.011670055697993105,
+      "grad_norm": 4.007390022277832,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.8367,
+      "step": 66
+    },
+    {
+      "epoch": 0.012200512775174609,
+      "grad_norm": 3.7783989906311035,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.7552,
+      "step": 69
+    },
+    {
+      "epoch": 0.012730969852356113,
+      "grad_norm": 4.115812301635742,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.573,
+      "step": 72
+    },
+    {
+      "epoch": 0.012730969852356113,
+      "eval_loss": 0.6983979940414429,
+      "eval_runtime": 674.9598,
+      "eval_samples_per_second": 14.112,
+      "eval_steps_per_second": 1.765,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.859441830245171e+16,
+  "total_flos": 1.0125076377423053e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null