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:e30f4a7951c6d9eb963d54f969a94726192588ec3bc35c8a8561bfc2558712b1
+oid sha256:efa657266f8effc747dc4edf19be3918f7add5d52570b06e5b7ae045b23c7bad
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28f666dc35a95aafe80c665e048431d29366ac0f0ded752326327b83bf0b7f7c
+oid sha256:b71759db28b5198317ada0ded18a43353d65000ac9fa92f829cef7d9f618ee32
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405836a400b8251bcce9b8fe6f90aa7292a17fe1c9aabea40a7456bde4466310
+oid sha256:581d97fe6008a9750885156089f6b4a1a7e93a5fc902dbf2e649e73c10e3e254
 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": 0.0021195940162230466,
+  "epoch": 0.004239188032446093,
   "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": 18.868,
       "eval_steps_per_second": 9.438,
       "step": 10
+    },
+    {
+      "epoch": 0.0024456854033342843,
+      "grad_norm": 0.12383808940649033,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.9318,
+      "step": 15
+    },
+    {
+      "epoch": 0.003260913871112379,
+      "grad_norm": 0.13035127520561218,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.0568,
+      "step": 20
+    },
+    {
+      "epoch": 0.003260913871112379,
+      "eval_loss": 1.0532459020614624,
+      "eval_runtime": 137.4005,
+      "eval_samples_per_second": 18.799,
+      "eval_steps_per_second": 9.403,
+      "step": 20
+    },
+    {
+      "epoch": 0.004076142338890474,
+      "grad_norm": 0.15136367082595825,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.9642,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 601111148888064.0,
+  "total_flos": 1195827498319872.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null