Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9528cbecdf7311a107d81a2d7fd268aba073f24cd8d8b952311fd67d20715b39
+oid sha256:4358333b092a5b897949997cbbf9b61adc69450b396119722cb969560f2fb2c0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdfa742ec4d63d8d3be718d619f690ffa212f3382dd97c30aad068077308a5bc
+oid sha256:d9fcf500cbc93e7190195034b4cd8b8ca4b065f78be23c4b0ce6fb2f79f1417a
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66b91c15fcc1dacae4f6561325f826728a576faa214585d067b9ec2b776e0f43
+oid sha256:1e8317d7314ec1052421a4ea6b628d076a2c516100f4091e8fe874ef45b29de2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cc46ef59b9e1231a47de2e90601d146d12785232f3662a094b0f8bb0c9fc1eb
+oid sha256:aa30ff24895d9065ec982c80ee00c11ba58454c5c8ed3141979512515ba8379e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014179033935154552,
+  "epoch": 0.018905378580206068,
   "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": 0.00017258064516129034,
       "loss": 1.7393,
       "step": 75
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001721774193548387,
+      "loss": 1.7071,
+      "step": 76
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00017177419354838711,
+      "loss": 1.5009,
+      "step": 77
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00017137096774193548,
+      "loss": 1.658,
+      "step": 78
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001709677419354839,
+      "loss": 1.6428,
+      "step": 79
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00017056451612903226,
+      "loss": 1.7405,
+      "step": 80
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00017016129032258065,
+      "loss": 1.7162,
+      "step": 81
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016975806451612904,
+      "loss": 1.6236,
+      "step": 82
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016935483870967742,
+      "loss": 1.5788,
+      "step": 83
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016895161290322581,
+      "loss": 1.5383,
+      "step": 84
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001685483870967742,
+      "loss": 1.8091,
+      "step": 85
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001681451612903226,
+      "loss": 1.4177,
+      "step": 86
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016774193548387098,
+      "loss": 1.6378,
+      "step": 87
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016733870967741935,
+      "loss": 1.5325,
+      "step": 88
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016693548387096776,
+      "loss": 1.4395,
+      "step": 89
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016653225806451612,
+      "loss": 1.577,
+      "step": 90
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016612903225806454,
+      "loss": 1.7508,
+      "step": 91
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001657258064516129,
+      "loss": 1.5263,
+      "step": 92
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016532258064516132,
+      "loss": 1.6134,
+      "step": 93
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016491935483870968,
+      "loss": 1.9328,
+      "step": 94
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016451612903225807,
+      "loss": 1.7819,
+      "step": 95
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016411290322580646,
+      "loss": 1.8635,
+      "step": 96
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016370967741935485,
+      "loss": 1.4804,
+      "step": 97
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016330645161290324,
+      "loss": 1.6171,
+      "step": 98
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016290322580645163,
+      "loss": 1.6722,
+      "step": 99
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00016250000000000002,
+      "loss": 1.5711,
+      "step": 100
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 4680603935686656.0,
+  "total_flos": 6196389445877760.0,
   "trial_name": null,
   "trial_params": null
 }