Training in progress, step 16, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2296860903650cf2c063ab3cc58c75fdd1727d124d61ab777ec9e8b03687eb2b
+oid sha256:83f95ac312a53b2b1e37a2a1a0e6bc5cddbc7bc08eca720057376c302fd1a8e9
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ba7e4c6371ae18c985c4981fa4a588908a4229a3582c7631b9438898e9f1d65
+oid sha256:a0c8161e8e5681b86049a052bac0f569052ade09319433589f7aa50cceefee2f
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbd5f705556af6c4905a9230e1091eac50f4f4174bf382609d59bf53f367f4a4
+oid sha256:2eee07d3fc4d8a0abcc37fc9f663b2748ef62d5b07c21e50a8324927531b82b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e33da60be502927a2afa2046e81eb3da1ce22fa49e674a279bab92f8b0f7cf7
+oid sha256:605d23f463d574da26fdafa2a2fc396d0b00160053ea75ca175c5c8e6f2990e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2800875273522976,
+  "epoch": 0.5601750547045952,
   "eval_steps": 8,
-  "global_step": 8,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 134.703,
       "eval_steps_per_second": 68.046,
       "step": 8
+    },
+    {
+      "epoch": 0.3150984682713348,
+      "grad_norm": 0.10614413022994995,
+      "learning_rate": 9e-05,
+      "loss": 10.3741,
+      "step": 9
+    },
+    {
+      "epoch": 0.4201312910284464,
+      "grad_norm": 0.11337128281593323,
+      "learning_rate": 0.00012,
+      "loss": 10.3761,
+      "step": 12
+    },
+    {
+      "epoch": 0.5251641137855579,
+      "grad_norm": 0.10311492532491684,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 10.3712,
+      "step": 15
+    },
+    {
+      "epoch": 0.5601750547045952,
+      "eval_loss": 10.371430397033691,
+      "eval_runtime": 0.7202,
+      "eval_samples_per_second": 134.683,
+      "eval_steps_per_second": 68.036,
+      "step": 16
     }
   ],
   "logging_steps": 3,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3421444767744.0,
+  "total_flos": 6856254554112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null