Training in progress, step 65, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39bf2ee99ccfbf5ef5faf4a767bd4a3d50688ad35b8a2d88d3c9dfbed7dfe833
+oid sha256:26c58723cd37ee178453a88b9ea77865f8d0778431c7fe59ae1127b0102d8098
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19f614dc0a8027a25cd6bbbfae053c9c8e0347059f44fbfeb0cfd37b058526a7
+oid sha256:c177b961775cabda4013f61846c7bbae0bda71c85a664cd5e942fd8442b7a681
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d6306c7ebebc1ba61010c16f5f72bbe4229c8a68ab9af106d32f4e58acec2ce
+oid sha256:6376f78de9d6501f496c4dd46738ff9438d8e16db2e3a4d56d72fb1753a98312
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:161cf4e9397a65b9a3becdc79cb01972bac91b391263bc91430c5cb64f5cd1c2
+oid sha256:ebf12ecec9415e9d3e13423155f95cbe61b82658c03045a3a80d99f9fd473672
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016,
+  "epoch": 0.026,
   "eval_steps": 1000,
-  "global_step": 40,
+  "global_step": 65,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,13 +247,163 @@
       "learning_rate": 9.722222222222223e-05,
       "loss": 1.4805,
       "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.444444444444444e-05,
+      "loss": 1.4624,
+      "step": 41
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 1.7335,
+      "step": 42
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.888888888888889e-05,
+      "loss": 1.976,
+      "step": 43
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.611111111111112e-05,
+      "loss": 1.7132,
+      "step": 44
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 1.8266,
+      "step": 45
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8.055555555555556e-05,
+      "loss": 1.4724,
+      "step": 46
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7.777777777777778e-05,
+      "loss": 1.9093,
+      "step": 47
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.6004,
+      "step": 48
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 7.222222222222222e-05,
+      "loss": 1.8015,
+      "step": 49
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.944444444444444e-05,
+      "loss": 1.5109,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.8057,
+      "step": 51
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.388888888888888e-05,
+      "loss": 1.6599,
+      "step": 52
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 6.111111111111112e-05,
+      "loss": 1.6122,
+      "step": 53
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 1.4713,
+      "step": 54
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.555555555555556e-05,
+      "loss": 1.5983,
+      "step": 55
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5.2777777777777784e-05,
+      "loss": 1.7994,
+      "step": 56
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 5e-05,
+      "loss": 1.7283,
+      "step": 57
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 1.7313,
+      "step": 58
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 1.9441,
+      "step": 59
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.6845,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 1.753,
+      "step": 61
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.611111111111111e-05,
+      "loss": 1.6686,
+      "step": 62
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.6792,
+      "step": 63
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 1.4095,
+      "step": 64
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 1.511,
+      "step": 65
     }
   ],
   "logging_steps": 1,
   "max_steps": 75,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 2434139976646656.0,
+  "total_flos": 3836019066667008.0,
   "trial_name": null,
   "trial_params": null
 }