Training in progress, step 220, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1143902ff3564e4c1002e08abff0e3901f7b2864ff1561402b11204e5362411
+oid sha256:3078213dcd15bc291dc37ca3077f9efb155cb015e2ecfc039f1079c016cd9a50
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db52ebf37465555ffb2a88505ae648a96569156a76709768fa9d1a22d929c602
+oid sha256:684dc57c1e94460d88f7247e65733810667abcc8211761ae7f175a94fb2a5c38
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1160b60ff5f8d1ce07bd99cf7c1f641950e24f450dc82b69252f6b166db4c3
+oid sha256:70a160794c42b620b052ded8acee8ed084ab34b149aee53004744c1a7084b810
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f012eba30607df0ae053cd324d767650b13de6ae604fa48d8a90e45bcf2f90
+oid sha256:a258940d20544cb994c096c67b2810560f36bc1c5c956be9ea4d5468f6460551
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00015565050236199636,
+  "epoch": 0.00017121555259819602,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 220,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,13 @@
       "learning_rate": 3.316666666666667e-05,
       "loss": 3.0499,
       "step": 200
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 6.314597129821777,
+      "learning_rate": 3.65e-05,
+      "loss": 2.8568,
+      "step": 220
     }
   ],
   "logging_steps": 20,
@@ -84,7 +91,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 985164675969024.0,
+  "total_flos": 1070150797246464.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null