Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:491a85e52754c204fbbc5f96bfedcee4ddafe068bd289444940199bf57c2ea45
+oid sha256:9af69331e6703f8e689c23faae3940291c573298e282ff79383cd49609d34913
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2652a3ea0dd0d7b0386fc59cf98ccb42f7c22c825ac1ea78f7ad7052b093c7
+oid sha256:ecb3b3017608a14ecd05c5f89e4470e20ee681365ed443fd779dc9084d6d7760
 size 253144

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:765f00579080865a80c94886839d8d44d0303619ef7b173cecbf3788727daa76
+oid sha256:9146137084714cb3ebd8baa838c1a6aac1566ffe61fe4112df04b86234651a59
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd917408cfda52d665212e473ffeb6e4ad99322caafe392985e297a7d59e165f
+oid sha256:65684ed0dae5b914842e2f3d5706818c762bb36504ec1e9acc73e6a8a12d70b0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aed018b404510e16bbee82ae0c0011108d38cad85e1922256c8dd93dd2654e19
+oid sha256:2105c4ad61a54f089459061bd8ee2e79156be45e484cd8849b323b5f66da7477
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff59d6e0b27c0323ee595a341faf981a693407ce99033ce3e73b73f065f00ab8
+oid sha256:82ee9e7cce115f29f30e97f6c607cd7522a9ad93a1c5e75c5666a5673824cf03
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3875598086124402,
+  "epoch": 0.430622009569378,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 764.228,
       "eval_steps_per_second": 23.899,
       "step": 81
+    },
+    {
+      "epoch": 0.4019138755980861,
+      "grad_norm": 0.08259936422109604,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3114,
+      "step": 84
+    },
+    {
+      "epoch": 0.41626794258373206,
+      "grad_norm": 0.08639667928218842,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 10.3115,
+      "step": 87
+    },
+    {
+      "epoch": 0.430622009569378,
+      "grad_norm": 0.08296097069978714,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3116,
+      "step": 90
+    },
+    {
+      "epoch": 0.430622009569378,
+      "eval_loss": 10.310672760009766,
+      "eval_runtime": 1.8404,
+      "eval_samples_per_second": 764.503,
+      "eval_steps_per_second": 23.908,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 72284828073984.0,
+  "total_flos": 80316475637760.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null