Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43a5a8fd74b8fa36949c6c85f6bf7536f39c3fae50357aeb05ee427e9f519ddd
+oid sha256:2d85f12ce431a51ec6f19c695da5add1448192090ed55a47fc09ae90c2fb9452
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ca33750c8c901afb3d92362b9af0c219f62c7b56aeed68e6e7875a3cffac07
+oid sha256:79cad39bf69db8f514344133dd55d98ad17085d5f340ea24465e790540a80460
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ed823756481de62e690edd754f7f54a40e9e3e0ac2be069841e8f5c60b2c76c
+oid sha256:cbd2f6e463444356bddac32968462fbb7d07302b4789c6151e3ff1ab681295d1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.30393996247654786,
+  "epoch": 0.33771106941838647,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 13.666,
       "eval_steps_per_second": 3.462,
       "step": 81
+    },
+    {
+      "epoch": 0.3151969981238274,
+      "grad_norm": 0.004858713131397963,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0003,
+      "step": 84
+    },
+    {
+      "epoch": 0.32645403377110693,
+      "grad_norm": 0.002612839685752988,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0009,
+      "step": 87
+    },
+    {
+      "epoch": 0.33771106941838647,
+      "grad_norm": 0.015446677803993225,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0006,
+      "step": 90
+    },
+    {
+      "epoch": 0.33771106941838647,
+      "eval_loss": 0.001242813770659268,
+      "eval_runtime": 16.4726,
+      "eval_samples_per_second": 13.659,
+      "eval_steps_per_second": 3.46,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.758649175638016e+16,
+  "total_flos": 6.39849908404224e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null