Training in progress, step 153, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a720b6a6c737c244779f324a7a933055b8a6b1988a5156e8fd556928b0ac95dd
+oid sha256:fcdf10964fbea563f7585add757a1eded783fdea527b5b19c6c581195c5c3eb6
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef617551b0809384d4da27a93c36dcd3801b5789a571da1dce0485f8e7f3302
+oid sha256:5d9ce8f5d2c229bb84c86a6f32a33598b0f8c59ea40233c2dca6776e522db316
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e554c518f56e093745f46f37d2f62ebbef88c44083698dc01d4c782697c6d2b
+oid sha256:8376b1a21f60d7891b89de2e0d8b9ab5dc44b12e00ba3ecc733ed71c6230518d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd0ef2a827b219b75915f5a88a30c53ebe86f536eec93a6252baab983329eb7
+oid sha256:7d99dc7a150ff6ed818c8735e9e9061e757b4b841b8d74bde2c9d7a2195ff136
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03490535771575232,
+  "epoch": 0.03926852743022137,
   "eval_steps": 17,
-  "global_step": 136,
+  "global_step": 153,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -394,6 +394,56 @@
       "eval_samples_per_second": 13.281,
       "eval_steps_per_second": 1.661,
       "step": 136
+    },
+    {
+      "epoch": 0.03541867179980751,
+      "grad_norm": 0.3809681534767151,
+      "learning_rate": 2.405152131093926e-05,
+      "loss": 2.3106,
+      "step": 138
+    },
+    {
+      "epoch": 0.03618864292589028,
+      "grad_norm": 0.3716019093990326,
+      "learning_rate": 2.196424713241637e-05,
+      "loss": 2.3156,
+      "step": 141
+    },
+    {
+      "epoch": 0.03695861405197305,
+      "grad_norm": 0.3578968048095703,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 2.2621,
+      "step": 144
+    },
+    {
+      "epoch": 0.03772858517805582,
+      "grad_norm": 0.37218406796455383,
+      "learning_rate": 1.800157297483417e-05,
+      "loss": 2.3245,
+      "step": 147
+    },
+    {
+      "epoch": 0.03849855630413859,
+      "grad_norm": 0.3655867278575897,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 2.2425,
+      "step": 150
+    },
+    {
+      "epoch": 0.03926852743022137,
+      "grad_norm": 0.33499404788017273,
+      "learning_rate": 1.435357758543015e-05,
+      "loss": 2.2394,
+      "step": 153
+    },
+    {
+      "epoch": 0.03926852743022137,
+      "eval_loss": 2.2859363555908203,
+      "eval_runtime": 494.1942,
+      "eval_samples_per_second": 13.28,
+      "eval_steps_per_second": 1.661,
+      "step": 153
     }
   ],
   "logging_steps": 3,
@@ -413,7 +463,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.004061139364741e+17,
+  "total_flos": 2.2578649349750784e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null