Training in progress, step 203, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2578d0630ecf659de062330437f2ab118f2bb6371e98b5d7f02cd4c84996cced
+oid sha256:9f673b7e0040e60617c69a88706873642e60534ff290592fcc0195a9df7ab81e
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0afae3ebba9d0af5bee6787ab79cbf9170b2f759d14ea54267d8db2a83507f
+oid sha256:f082ea210fd68387405176cad6ee88cfbd401951351d7c95447ac68b86b16bb0
 size 37430836

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a269a2cea20ade02f5153afabb9927aa1d806bfa877265376ea45d5823b7de
+oid sha256:ec95e73a62601dbe96f98abb332829d9f2af7677329a53ab141fd2b0805c4d17
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5404663923182441,
+  "epoch": 0.5569272976680384,
   "eval_steps": 500,
-  "global_step": 197,
+  "global_step": 203,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1386,6 +1386,48 @@
       "learning_rate": 0.00012651515151515153,
       "loss": 1.2623,
       "step": 197
+    },
+    {
+      "epoch": 0.5432098765432098,
+      "grad_norm": 0.15332822501659393,
+      "learning_rate": 0.00012575757575757575,
+      "loss": 1.2113,
+      "step": 198
+    },
+    {
+      "epoch": 0.5459533607681756,
+      "grad_norm": 0.15453462302684784,
+      "learning_rate": 0.000125,
+      "loss": 1.157,
+      "step": 199
+    },
+    {
+      "epoch": 0.5486968449931413,
+      "grad_norm": 0.18716047704219818,
+      "learning_rate": 0.00012424242424242425,
+      "loss": 1.1896,
+      "step": 200
+    },
+    {
+      "epoch": 0.551440329218107,
+      "grad_norm": 0.1628562957048416,
+      "learning_rate": 0.0001234848484848485,
+      "loss": 1.2035,
+      "step": 201
+    },
+    {
+      "epoch": 0.5541838134430727,
+      "grad_norm": 0.15352866053581238,
+      "learning_rate": 0.00012272727272727272,
+      "loss": 1.2529,
+      "step": 202
+    },
+    {
+      "epoch": 0.5569272976680384,
+      "grad_norm": 0.1607903093099594,
+      "learning_rate": 0.00012196969696969697,
+      "loss": 1.224,
+      "step": 203
     }
   ],
   "logging_steps": 1,
@@ -1405,7 +1447,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.4436699819317658e+17,
+  "total_flos": 2.5176887757982925e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null