Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177f379ac4f3a55cdc46bad358f634345fb4edd634b438dde48fb6fd4e9bba5d
+oid sha256:19565e26d49366d150c478b63bc25efe92909010559f76e85507d29dd208d0c0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307b8d9361c4ee046a6d10490a5b571311acf5bc6c6ace29f55e3d41f04f5c32
+oid sha256:6ea0137f454269d19c6c897022152da60f037a2815bfd764406571a1f29e3cda
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d261144361ea855362212b7f0dabe43e1421a9588798268bc613afe8fd7dd4d0
+oid sha256:f478f0c85c1033258c058dbb270fd910f4cfcd4116020451b8423efc28027c55
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007614213197969543,
+  "epoch": 0.015228426395939087,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 14.263,
       "eval_steps_per_second": 7.132,
       "step": 3
+    },
+    {
+      "epoch": 0.01015228426395939,
+      "grad_norm": 2.8737056255340576,
+      "learning_rate": 8e-05,
+      "loss": 1.9663,
+      "step": 4
+    },
+    {
+      "epoch": 0.012690355329949238,
+      "grad_norm": 2.812922954559326,
+      "learning_rate": 0.0001,
+      "loss": 2.5981,
+      "step": 5
+    },
+    {
+      "epoch": 0.015228426395939087,
+      "grad_norm": 3.180525302886963,
+      "learning_rate": 0.00012,
+      "loss": 2.5543,
+      "step": 6
+    },
+    {
+      "epoch": 0.015228426395939087,
+      "eval_loss": 5.608060359954834,
+      "eval_runtime": 11.8629,
+      "eval_samples_per_second": 13.993,
+      "eval_steps_per_second": 6.997,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 554869274443776.0,
+  "total_flos": 1202216761294848.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null