Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b3e11a66a38207ce99a54b043aef4de1c80c60958eb4667d09a90773551c794
+oid sha256:958104a8c8de5d86af3cfee119cbd1072106113cd5a4c4c4c48ff6ba0dfa637a
 size 2185308216

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51957ad7b37db647e51475cf7904e7241eb51c2bf90022448091c132ba60ff2c
+oid sha256:1f7f0253f7a972fe4e03ed54ef0e8b8cacef9ea54dd451849ebec4d4a5411e7c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6286a07b356beb4b76bbb49982b1e35c009b260102e0a6e40f5c518c1a9550e1
+oid sha256:2473e3f0cdeaec175405ecd9445d31a2555140f93345e9697e36f79691326a30
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005883684091423399,
+  "epoch": 0.011767368182846799,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 7.72,
       "eval_steps_per_second": 3.864,
       "step": 10
+    },
+    {
+      "epoch": 0.006788866259334691,
+      "grad_norm": 0.38589227199554443,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.3773,
+      "step": 15
+    },
+    {
+      "epoch": 0.009051821679112922,
+      "grad_norm": 0.36434707045555115,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.3543,
+      "step": 20
+    },
+    {
+      "epoch": 0.009051821679112922,
+      "eval_loss": 0.3476487696170807,
+      "eval_runtime": 121.2735,
+      "eval_samples_per_second": 7.677,
+      "eval_steps_per_second": 3.843,
+      "step": 20
+    },
+    {
+      "epoch": 0.011314777098891152,
+      "grad_norm": 0.3032950460910797,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.3064,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4623913136947200.0,
+  "total_flos": 9386543668002816.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null