Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb6a4fed679b987fdd6c1e514e12783fdc4f737376eb4b04338030202eeaf51
+oid sha256:bb91894eea61be9591c5260d00b9087ca0a6dc46ed94817c80b9ac44cd7a4928
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5686cb6b29c74162cda5eeab27e04bc794839101edd1164532f1ef6501cc92e
+oid sha256:ccfb0262f5605d908c08bf81441c98603371dff0a3c4c1bd7198d3fac51b5cdc
 size 40570324

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc6744b325cd384360f7b14d680bd163370492cc218f39a964db4cc1af7949ce
+oid sha256:ea231484ac1b98a7125d6e8d0b95909881ffacf49ef075416e6a79403dab6801
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2fc8fc3c3a73bde08c51775569706a19912af94a0a9a24838efcaf468a96508
+oid sha256:13ea27ae447e821a5834e6e9c924c90c4dcecfc1b5b04cb8436fa3beb393cc9f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02038597444957869,
+  "epoch": 0.02718129926610492,
   "eval_steps": 1000,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -457,13 +457,163 @@
       "learning_rate": 5.68421052631579e-05,
       "loss": 1.8428,
       "step": 75
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.4736842105263165e-05,
+      "loss": 2.1565,
+      "step": 76
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.2631578947368424e-05,
+      "loss": 2.0893,
+      "step": 77
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.052631578947369e-05,
+      "loss": 1.7193,
+      "step": 78
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.842105263157895e-05,
+      "loss": 2.0253,
+      "step": 79
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.6315789473684214e-05,
+      "loss": 1.8999,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.421052631578947e-05,
+      "loss": 1.9748,
+      "step": 81
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.210526315789474e-05,
+      "loss": 2.0023,
+      "step": 82
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 1.9539,
+      "step": 83
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.789473684210527e-05,
+      "loss": 1.6427,
+      "step": 84
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.578947368421053e-05,
+      "loss": 1.8795,
+      "step": 85
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.368421052631579e-05,
+      "loss": 1.9835,
+      "step": 86
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.157894736842105e-05,
+      "loss": 2.0199,
+      "step": 87
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.9473684210526314e-05,
+      "loss": 2.1671,
+      "step": 88
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.7368421052631583e-05,
+      "loss": 1.6357,
+      "step": 89
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.5263157894736845e-05,
+      "loss": 1.8582,
+      "step": 90
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 2.3157894736842107e-05,
+      "loss": 2.0198,
+      "step": 91
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.105263157894737e-05,
+      "loss": 1.5241,
+      "step": 92
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.8947368421052634e-05,
+      "loss": 2.3354,
+      "step": 93
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.6842105263157896e-05,
+      "loss": 1.8607,
+      "step": 94
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.4736842105263157e-05,
+      "loss": 2.3244,
+      "step": 95
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.2631578947368422e-05,
+      "loss": 1.811,
+      "step": 96
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 1.7307,
+      "step": 97
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 1.7182,
+      "step": 98
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 6.315789473684211e-06,
+      "loss": 1.9487,
+      "step": 99
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 1.9158,
+      "step": 100
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 629145890537472.0,
+  "total_flos": 855403008294912.0,
   "trial_name": null,
   "trial_params": null
 }