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:afee68c4cfaaf6b8cd20275f8c90ed251cf16d37374144e9a0b0a60faa5b47b6
+oid sha256:1b74265b17ca020ad147ba93efef015a8c237e1c34da6d3dd21e759b0aef08a2
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dfeec10c4488a928944026c2d75408c2e1b33654f1376bb77c53629f1618bc1
+oid sha256:8417b3f9d5b1359970536bb12f52bc99c995b94763d8ae32f24181d5adae6553
 size 40570324

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4d4d519233b1d715f1e302ab6f44d45be958cf79d89096c5f483d5bae7b8096
+oid sha256:d7d8f7f8e1a76d94091cc701a4a00cc6fd2a3c1a746e29e297276a305cc6801f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1c7360581e177bcd8f1baa11a13d34ab7c59b5ff1e9e1739e68f1c3241102b6
+oid sha256:1584b1b2cf9ecd956165af14d13e1fadf07b1f7d91e0a62867f52fe0a3a9ac7c
 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": 0.00010736842105263158,
       "loss": 1.6563,
       "step": 50
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 1.5786,
+      "step": 51
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 1.5629,
+      "step": 52
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 0.00010105263157894738,
+      "loss": 1.0232,
+      "step": 53
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.894736842105263e-05,
+      "loss": 1.5671,
+      "step": 54
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.68421052631579e-05,
+      "loss": 1.6186,
+      "step": 55
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 1.6145,
+      "step": 56
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.263157894736843e-05,
+      "loss": 1.5494,
+      "step": 57
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 9.052631578947369e-05,
+      "loss": 1.7099,
+      "step": 58
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.842105263157894e-05,
+      "loss": 1.586,
+      "step": 59
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.631578947368421e-05,
+      "loss": 1.2571,
+      "step": 60
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 1.4626,
+      "step": 61
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 1.4228,
+      "step": 62
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 8e-05,
+      "loss": 1.4772,
+      "step": 63
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.789473684210526e-05,
+      "loss": 1.6396,
+      "step": 64
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.578947368421054e-05,
+      "loss": 1.6148,
+      "step": 65
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 1.4147,
+      "step": 66
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 7.157894736842105e-05,
+      "loss": 1.9057,
+      "step": 67
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.947368421052632e-05,
+      "loss": 1.2152,
+      "step": 68
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.736842105263159e-05,
+      "loss": 1.611,
+      "step": 69
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.526315789473685e-05,
+      "loss": 1.3557,
+      "step": 70
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 1.6397,
+      "step": 71
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 1.631,
+      "step": 72
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.894736842105263e-05,
+      "loss": 1.6067,
+      "step": 73
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.68421052631579e-05,
+      "loss": 1.7248,
+      "step": 74
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5.4736842105263165e-05,
+      "loss": 1.5881,
+      "step": 75
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 2741329648189440.0,
+  "total_flos": 4183967298846720.0,
   "trial_name": null,
   "trial_params": null
 }