Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27143de200dcd7dd6333b34817bd3ebe89abd6d1c1b5ce0ed42ecd8ea334f31f
+oid sha256:e5a7c9ab9ca34ddc9e464d415e468c25fd925db5f70f8a8e107b6a055bd3ded1
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9227174b827248911bfd55fbea33636654f11ce07ab16a4d51074f68518cafd
+oid sha256:7a20888a879cf31c4a13dc3ecf491c2e0111f2e124da5c9cc06aaf691534a896
 size 263088

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:041e36e3c63dabfbb6e7d5573efecf709c639e3b8a104c7746cf31c9f4387091
+oid sha256:f8809c96bed7e6c896e7eff1b04f154442b7d50108eb01132ca9236ef709bbfd
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:061d0692fa8b539252cb5e5cc70a1ba2787f7f56c4ebcd691f0f3c1c7c15066b
+oid sha256:b799eb1351996defa336c883fefd88e74c06daab5df0bce4017e8c1479d94380
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43dca3ecd2ab47e84f0307855ded82435ba1673dc93e9b6f6d6bea2853047334
+oid sha256:2cc96250a43e632cb5ae9a7107ce24b7457153290af9cf9897e264556e71a99d
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e922b1e29817b9be2afe815bd82603354841818005001da4aa22780ae5012a2
+oid sha256:b6bdbf9f09105bc5b75430990cc4806889374b706a5d72a98a7a4c5572f58c90
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4435e50107632056c980bf5ca683b30daf6a7049b63cba2514277d76468ff4af
+oid sha256:121c075a7ce23987cdf5c15e739fd91b8847af12854b7686f3ca78a6bd4525e2
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35fe1b3fc01d2378ec9105ebaa2a9c3b381a9de368f76b148e172a17484465f8
+oid sha256:c1ed112ff99ef0735a0ef90c244ffe14da9ac21f00ecbe3f03d76ef8efc02f15
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f9eb59e5a76de855e9a75a5d2894e26ce2cdf8f8cf68a12da5845f2358c76a6
+oid sha256:823be00465c529ec2e81df753933cee16cc7fa8be0987893a34b063c1a819cb9
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a1a5a2d900e135b3cdfbf0d13da3726612a93b102df4fd225802b9fb4baec9
+oid sha256:a3820d50e85079de6cf344fe2d67b6b136bed4e19bda6730e22c79f77817e74a
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006585626869357627,
+  "epoch": 0.000987844030403644,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 638.006,
       "eval_steps_per_second": 79.787,
       "step": 6
+    },
+    {
+      "epoch": 0.0007683231347583898,
+      "grad_norm": 3.174706220626831,
+      "learning_rate": 0.00014,
+      "loss": 44.3363,
+      "step": 7
+    },
+    {
+      "epoch": 0.0008780835825810169,
+      "grad_norm": 3.3509459495544434,
+      "learning_rate": 0.00016,
+      "loss": 44.2819,
+      "step": 8
+    },
+    {
+      "epoch": 0.000987844030403644,
+      "grad_norm": 3.4119491577148438,
+      "learning_rate": 0.00018,
+      "loss": 44.2531,
+      "step": 9
+    },
+    {
+      "epoch": 0.000987844030403644,
+      "eval_loss": 11.040336608886719,
+      "eval_runtime": 24.0508,
+      "eval_samples_per_second": 638.024,
+      "eval_steps_per_second": 79.789,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1996757139456.0,
+  "total_flos": 2995135709184.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null