Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:269e02dc931865a4d7c1981eca33d2486373d043dd99da5f05186ac7501a7648
+oid sha256:4a504e7087c42efa0abf4ec92b7f2fffe60bc836a276d2d8040eb1e14d8fe701
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b219215a0cdf22b74e690dedd537471ed5ec27d5a848a0c00dd9462c08dea9c
+oid sha256:8c3a1c360125505fbecae7ce8c3717ae80f5d8f194f13bc58ae229409e120928
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58973b63eb41c8b34c51f7eb73abffa4ae0d2af806c0e342de338e3f48596cb0
+oid sha256:3f3d5d54b849ab203f6cdfb3dbb15af8bac4b9cdd7cf70876a104c601b1d220d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02173fc97b82f2e000f1d5084934ed87f720106f5dddb2874a3633a6c2964dab
+oid sha256:ef61bc9a6dc6a8e5bc76abe40655ca3cc8891ccb7b6be31278a254ac81104357
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 50.0,
+  "epoch": 75.0,
   "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": 0.0001136842105263158,
       "loss": 0.004,
       "step": 50
+    },
+    {
+      "epoch": 51.0,
+      "learning_rate": 0.00011157894736842105,
+      "loss": 0.0042,
+      "step": 51
+    },
+    {
+      "epoch": 52.0,
+      "learning_rate": 0.00010947368421052633,
+      "loss": 0.0039,
+      "step": 52
+    },
+    {
+      "epoch": 53.0,
+      "learning_rate": 0.00010736842105263158,
+      "loss": 0.0046,
+      "step": 53
+    },
+    {
+      "epoch": 54.0,
+      "learning_rate": 0.00010526315789473685,
+      "loss": 0.0041,
+      "step": 54
+    },
+    {
+      "epoch": 55.0,
+      "learning_rate": 0.00010315789473684211,
+      "loss": 0.0042,
+      "step": 55
+    },
+    {
+      "epoch": 56.0,
+      "learning_rate": 0.00010105263157894738,
+      "loss": 0.0042,
+      "step": 56
+    },
+    {
+      "epoch": 57.0,
+      "learning_rate": 9.894736842105263e-05,
+      "loss": 0.0037,
+      "step": 57
+    },
+    {
+      "epoch": 58.0,
+      "learning_rate": 9.68421052631579e-05,
+      "loss": 0.0038,
+      "step": 58
+    },
+    {
+      "epoch": 59.0,
+      "learning_rate": 9.473684210526316e-05,
+      "loss": 0.0042,
+      "step": 59
+    },
+    {
+      "epoch": 60.0,
+      "learning_rate": 9.263157894736843e-05,
+      "loss": 0.0042,
+      "step": 60
+    },
+    {
+      "epoch": 61.0,
+      "learning_rate": 9.052631578947369e-05,
+      "loss": 0.0042,
+      "step": 61
+    },
+    {
+      "epoch": 62.0,
+      "learning_rate": 8.842105263157894e-05,
+      "loss": 0.0038,
+      "step": 62
+    },
+    {
+      "epoch": 63.0,
+      "learning_rate": 8.631578947368421e-05,
+      "loss": 0.0041,
+      "step": 63
+    },
+    {
+      "epoch": 64.0,
+      "learning_rate": 8.421052631578948e-05,
+      "loss": 0.0036,
+      "step": 64
+    },
+    {
+      "epoch": 65.0,
+      "learning_rate": 8.210526315789474e-05,
+      "loss": 0.0042,
+      "step": 65
+    },
+    {
+      "epoch": 66.0,
+      "learning_rate": 8e-05,
+      "loss": 0.004,
+      "step": 66
+    },
+    {
+      "epoch": 67.0,
+      "learning_rate": 7.789473684210526e-05,
+      "loss": 0.0036,
+      "step": 67
+    },
+    {
+      "epoch": 68.0,
+      "learning_rate": 7.578947368421054e-05,
+      "loss": 0.0043,
+      "step": 68
+    },
+    {
+      "epoch": 69.0,
+      "learning_rate": 7.368421052631579e-05,
+      "loss": 0.0037,
+      "step": 69
+    },
+    {
+      "epoch": 70.0,
+      "learning_rate": 7.157894736842105e-05,
+      "loss": 0.0038,
+      "step": 70
+    },
+    {
+      "epoch": 71.0,
+      "learning_rate": 6.947368421052632e-05,
+      "loss": 0.0043,
+      "step": 71
+    },
+    {
+      "epoch": 72.0,
+      "learning_rate": 6.736842105263159e-05,
+      "loss": 0.004,
+      "step": 72
+    },
+    {
+      "epoch": 73.0,
+      "learning_rate": 6.526315789473685e-05,
+      "loss": 0.0043,
+      "step": 73
+    },
+    {
+      "epoch": 74.0,
+      "learning_rate": 6.31578947368421e-05,
+      "loss": 0.0041,
+      "step": 74
+    },
+    {
+      "epoch": 75.0,
+      "learning_rate": 6.105263157894737e-05,
+      "loss": 0.0034,
+      "step": 75
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 100,
   "save_steps": 25,
-  "total_flos": 534872371200000.0,
+  "total_flos": 802308556800000.0,
   "trial_name": null,
   "trial_params": null
 }