Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a595ab8d0501db585f02e5044fa57e61fcac8cca3667878ad850a07e524b4e
+oid sha256:158b59b088d9e4102d6980a95e49bd76d284fd8aa4cee95bfab2f2ef44851982
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f21feea2e2f7292f02c7822951aa623f6cf71bda055968e00277d00429c41ed
+oid sha256:3df03bfe471d96aa40d3a3614213ee1ae1aa37dd508ffcaa6fb8dee23587ceb9
 size 86889042

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2f0c5f75e18f8cb763d8ea5434e79bf35d98af96676e76ac16c35aac4009f48
+oid sha256:6ef0281527db1a7092e344d658b16faf0f0d248b31b0fd2f143c85afbb18c88f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0024,
+  "epoch": 0.0032,
   "eval_steps": 500,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,76 @@
       "learning_rate": 0.00017435897435897436,
       "loss": 0.7906,
       "step": 30
+    },
+    {
+      "epoch": 0.00248,
+      "grad_norm": 0.6179051995277405,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.4689,
+      "step": 31
+    },
+    {
+      "epoch": 0.00256,
+      "grad_norm": 0.42703530192375183,
+      "learning_rate": 0.00017230769230769234,
+      "loss": 0.4424,
+      "step": 32
+    },
+    {
+      "epoch": 0.00264,
+      "grad_norm": 0.5435040593147278,
+      "learning_rate": 0.00017128205128205128,
+      "loss": 0.3853,
+      "step": 33
+    },
+    {
+      "epoch": 0.00272,
+      "grad_norm": 0.45631420612335205,
+      "learning_rate": 0.00017025641025641026,
+      "loss": 0.4006,
+      "step": 34
+    },
+    {
+      "epoch": 0.0028,
+      "grad_norm": 0.48986274003982544,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.557,
+      "step": 35
+    },
+    {
+      "epoch": 0.00288,
+      "grad_norm": 0.4985139071941376,
+      "learning_rate": 0.00016820512820512823,
+      "loss": 0.7894,
+      "step": 36
+    },
+    {
+      "epoch": 0.00296,
+      "grad_norm": 0.5833737850189209,
+      "learning_rate": 0.0001671794871794872,
+      "loss": 0.6526,
+      "step": 37
+    },
+    {
+      "epoch": 0.00304,
+      "grad_norm": 0.3877828121185303,
+      "learning_rate": 0.00016615384615384617,
+      "loss": 0.5351,
+      "step": 38
+    },
+    {
+      "epoch": 0.00312,
+      "grad_norm": 0.48045578598976135,
+      "learning_rate": 0.00016512820512820512,
+      "loss": 0.5696,
+      "step": 39
+    },
+    {
+      "epoch": 0.0032,
+      "grad_norm": 0.47378939390182495,
+      "learning_rate": 0.0001641025641025641,
+      "loss": 0.7905,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -236,7 +306,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8053805909950464.0,
+  "total_flos": 1.0616812747358208e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null