Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39ad19d4ff55bb6e76de985063137ffd18e8e13f93eb49bb0b5d4f2a9a318d6c
+oid sha256:67b9ca819b8eb3d6adef4f898f9a65fabf47d02bd1a7b1bdd06299f095960648
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d948daa268390bc29373fcb01221a7fb089b0c83f3400a559459fda2aadeb666
+oid sha256:f216fb383050efb8a8eda8072a42062277a006056951fe1c6d610c99be838f51
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16f7ed894f58d41c91ef3f3f4ed73496ebf0d1e5795c541af0d81dc3ee5e58b3
+oid sha256:b70a15b7847c8e61838121a6622a5b2d0734a021df91c806730421aab2237ead
 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": 0.011168384879725086,
+  "epoch": 0.022336769759450172,
   "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": 6.602,
       "eval_steps_per_second": 3.308,
       "step": 10
+    },
+    {
+      "epoch": 0.01288659793814433,
+      "grad_norm": 63.61037826538086,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 4.2074,
+      "step": 15
+    },
+    {
+      "epoch": 0.01718213058419244,
+      "grad_norm": 57.09468078613281,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.4869,
+      "step": 20
+    },
+    {
+      "epoch": 0.01718213058419244,
+      "eval_loss": 0.79156494140625,
+      "eval_runtime": 75.4961,
+      "eval_samples_per_second": 6.504,
+      "eval_steps_per_second": 3.258,
+      "step": 20
+    },
+    {
+      "epoch": 0.02147766323024055,
+      "grad_norm": 65.97125244140625,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.9544,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2891905146814464.0,
+  "total_flos": 5696176804331520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null