Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d63e65df89b347d2b541054b272b6a19f241d8b73dd9139a24e4ab744e3d01
+oid sha256:4a3543f4e5bd078beba570d5745a45a246a1e951429b417e8359cf2821362796
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db49ac0e45e45499484f48cbe8f894187c07cca13e8742bd0e56592d56529dbf
+oid sha256:7755f2da965022367da7226127267c47838725c2b28082989bc01d3528bff76b
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf7e826ecf59df8dfab5ce1482a707845fd694e7ec08d3ce67674a900528122
+oid sha256:6bac162d0d465793ae018f840b2d4ec5d89408f3aa97a4569adf5e87ec7ffc48
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1fa12db6e65a79cc008f6035c457ab68bb8c45c7fe7a2790ea24e528e6b743
+oid sha256:a4b679dfcad285902b67d18379c2cc1ca0aebfc7646cb33fa82a3fb8ed15c820
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07627118644067797,
+  "epoch": 0.15254237288135594,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 18.894,
       "eval_steps_per_second": 2.384,
       "step": 9
+    },
+    {
+      "epoch": 0.0847457627118644,
+      "grad_norm": 0.8837136626243591,
+      "learning_rate": 7.5e-05,
+      "loss": 1.1313,
+      "step": 10
+    },
+    {
+      "epoch": 0.1271186440677966,
+      "grad_norm": 0.7536290287971497,
+      "learning_rate": 0.0001125,
+      "loss": 1.0435,
+      "step": 15
+    },
+    {
+      "epoch": 0.15254237288135594,
+      "eval_loss": 0.9707416296005249,
+      "eval_runtime": 22.2197,
+      "eval_samples_per_second": 18.902,
+      "eval_steps_per_second": 2.385,
+      "step": 18
     }
   ],
   "logging_steps": 5,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4330878998085632e+16,
+  "total_flos": 2.7907501206798336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null