Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0dc74eb4f1664d79e8ca2ad4c0dcaf65b8ebee3025e61594d69d01fb996247d
+oid sha256:328faf494edd10b13e41db154ed048b702c17b9ccbc5c23e546bdc1fe9922c7f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa94faad5f7c2fac41c1d3489928c35288395f9537c10cdb8f345784281ca99
+oid sha256:30fca5bb017a17ab092c6dd50cded3c8b8d747efde3211075d3e56b9cb117207
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74d3fe4297fd36d6939c92e784b1ab4781c227d97ebf023707e527bcbb1c9fe4
+oid sha256:75a202b6ef127b2f370e29b02a695f7e35fad888ae4707bbaedeec3926ad69a8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d102a8b779e588307a5ff1ccea3e1e9ce6254fd84338a3b83b04cad35c2649e7
+oid sha256:9bbe372fc24045f3af45b8a1f0a38bf204533a38daba940e611e0a4525dedf0a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0012437810945273632,
+  "epoch": 0.0018656716417910447,
   "eval_steps": 1000,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,13 +307,163 @@
       "learning_rate": 0.00011157894736842105,
       "loss": 1.647,
       "step": 50
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010947368421052633,
+      "loss": 1.5989,
+      "step": 51
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010736842105263158,
+      "loss": 1.5857,
+      "step": 52
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 1.0283,
+      "step": 53
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 1.6175,
+      "step": 54
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010105263157894738,
+      "loss": 1.6465,
+      "step": 55
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.894736842105263e-05,
+      "loss": 1.6387,
+      "step": 56
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.68421052631579e-05,
+      "loss": 1.6037,
+      "step": 57
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 1.7261,
+      "step": 58
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.263157894736843e-05,
+      "loss": 1.6225,
+      "step": 59
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.052631578947369e-05,
+      "loss": 1.273,
+      "step": 60
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.842105263157894e-05,
+      "loss": 1.5125,
+      "step": 61
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.631578947368421e-05,
+      "loss": 1.4634,
+      "step": 62
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 1.5137,
+      "step": 63
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 1.6608,
+      "step": 64
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8e-05,
+      "loss": 1.7165,
+      "step": 65
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.789473684210526e-05,
+      "loss": 1.4347,
+      "step": 66
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.578947368421054e-05,
+      "loss": 1.9672,
+      "step": 67
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 1.2761,
+      "step": 68
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.157894736842105e-05,
+      "loss": 1.6604,
+      "step": 69
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.947368421052632e-05,
+      "loss": 1.3673,
+      "step": 70
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.736842105263159e-05,
+      "loss": 1.6446,
+      "step": 71
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.526315789473685e-05,
+      "loss": 1.6273,
+      "step": 72
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 1.657,
+      "step": 73
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 1.689,
+      "step": 74
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.894736842105263e-05,
+      "loss": 1.5599,
+      "step": 75
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 2841070876655616.0,
+  "total_flos": 4329984398917632.0,
   "trial_name": null,
   "trial_params": null
 }