Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641a21cedbd62d76de6b8e76e53706738ef7659a695239fe7f69a29625827de5
+oid sha256:93921e634bc6673a73bd6ebb2938a93357768a6c99dcc9edd13403f6978e46a8
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e03d96d9877c8f77f685428dfa3ab76538cd465cd417fce18e2fec44fe40bacc
+oid sha256:023971267dd3c330e8c239e57c5969e79e48b0ddd254a377f7997db009655554
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e6579874485b23c70c75df1980183043c6d4000a5e71c69e02f035621c4945
+oid sha256:8077dc599d0e2178961c634ebb1554fd0bb63f56537a068f9b3ec5adbcb0bb0f
 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": 0.0004296455424274973,
+  "epoch": 0.0008592910848549946,
   "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": 6.22,
       "eval_steps_per_second": 3.11,
       "step": 10
+    },
+    {
+      "epoch": 0.0004957448566471123,
+      "grad_norm": 0.33622804284095764,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.018,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006609931421961497,
+      "grad_norm": 0.374787837266922,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.9683,
+      "step": 20
+    },
+    {
+      "epoch": 0.0006609931421961497,
+      "eval_loss": 0.9721865057945251,
+      "eval_runtime": 2046.2259,
+      "eval_samples_per_second": 6.226,
+      "eval_steps_per_second": 3.113,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008262414277451872,
+      "grad_norm": 0.4773717522621155,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.9747,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4193987824975872.0,
+  "total_flos": 8428693978349568.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null