Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f942aba4483a84f276c2ec27d555213e022d60da22987fd3e4c80707ddc2830
+oid sha256:dfe2fb418afccaf64c1013ab63252ae75ed038bd4282a446118b3bf60fab6ea7
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:995dc70b5919ef7339deff602b1ce12af038cecfa9022bcb4af0842c8fa8e906
+oid sha256:2969e162bbaff7f0a99ac88fe368121d9e90b20e296928c80a039efae1319837
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5fedbc5bbf423a75d433c87d6481c2c61bc0c628368aa55379c00c043929f7
+oid sha256:a96ec98b03d2103c39025046aa0a135811765566c4aedce7d9cac444d8384b2d
 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": 0.0002157380939539399,
+  "epoch": 0.0004314761879078798,
   "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": 36.627,
       "eval_steps_per_second": 18.314,
       "step": 10
+    },
+    {
+      "epoch": 0.00024892856994685375,
+      "grad_norm": 2.8913145065307617,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.088,
+      "step": 15
+    },
+    {
+      "epoch": 0.00033190475992913833,
+      "grad_norm": 5.755887985229492,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.4491,
+      "step": 20
+    },
+    {
+      "epoch": 0.00033190475992913833,
+      "eval_loss": 0.2670595943927765,
+      "eval_runtime": 689.8036,
+      "eval_samples_per_second": 36.781,
+      "eval_steps_per_second": 18.391,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004148809499114229,
+      "grad_norm": 5.549856185913086,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.9362,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 395608389058560.0,
+  "total_flos": 783752468889600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null