Training in progress, step 41, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6639ce3de26a74598f696dee56d6532dd7c143f858704ff8c978247fa325d9f
+oid sha256:b1074d29df1d24c91a0185fcd97e79aa6b466996c6cf0e8bc07c3ba5519ff002
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b555367cc6c5d9a580f282070df6e71bdbbc8c56cd3d54a63eaf28a3b198cdd2
+oid sha256:574b891eda49e80a0fbdb29537fcd1cef2a83462ac8f35dada8f322f69a66431
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88112ef40ae20b02c82a3d5ef9d95b73bfd284c4e600776afe0316fc0fb3906c
+oid sha256:92586edd1f33bc00c39afaedea250dc0a79621f53effe15c2b33d0c76ca808d3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6b77c0cbcc35c1c43ee60e2766b6027d2e111edae589e45f75af1b1040b32d
+oid sha256:84fc982e8229d2121603832a24f4c07bbdbf63985ed1d38e11762164a04dad3b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8691588785046729,
+  "epoch": 3.0654205607476634,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 41,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,118 @@
       "eval_samples_per_second": 4.938,
       "eval_steps_per_second": 2.576,
       "step": 25
+    },
+    {
+      "epoch": 1.9439252336448598,
+      "grad_norm": 9.355457305908203,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 11.0052,
+      "step": 26
+    },
+    {
+      "epoch": 2.0186915887850465,
+      "grad_norm": 13.675053596496582,
+      "learning_rate": 2.8565371929847284e-05,
+      "loss": 11.0252,
+      "step": 27
+    },
+    {
+      "epoch": 2.0934579439252334,
+      "grad_norm": 14.849433898925781,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.9197,
+      "step": 28
+    },
+    {
+      "epoch": 2.1682242990654204,
+      "grad_norm": 12.167821884155273,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 10.4549,
+      "step": 29
+    },
+    {
+      "epoch": 2.2429906542056073,
+      "grad_norm": 14.887701988220215,
+      "learning_rate": 1.837773122023114e-05,
+      "loss": 11.138,
+      "step": 30
+    },
+    {
+      "epoch": 2.317757009345794,
+      "grad_norm": 13.879959106445312,
+      "learning_rate": 1.536378232452003e-05,
+      "loss": 11.0227,
+      "step": 31
+    },
+    {
+      "epoch": 2.392523364485981,
+      "grad_norm": 10.067033767700195,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 10.97,
+      "step": 32
+    },
+    {
+      "epoch": 2.467289719626168,
+      "grad_norm": 13.370949745178223,
+      "learning_rate": 1.0027861829824952e-05,
+      "loss": 10.5925,
+      "step": 33
+    },
+    {
+      "epoch": 2.542056074766355,
+      "grad_norm": 9.568769454956055,
+      "learning_rate": 7.740495722810271e-06,
+      "loss": 11.3019,
+      "step": 34
+    },
+    {
+      "epoch": 2.616822429906542,
+      "grad_norm": 13.338472366333008,
+      "learning_rate": 5.727198717339511e-06,
+      "loss": 11.2045,
+      "step": 35
+    },
+    {
+      "epoch": 2.691588785046729,
+      "grad_norm": 17.480472564697266,
+      "learning_rate": 4.001027817058789e-06,
+      "loss": 10.5578,
+      "step": 36
+    },
+    {
+      "epoch": 2.7663551401869158,
+      "grad_norm": 9.267881393432617,
+      "learning_rate": 2.573177902642726e-06,
+      "loss": 10.4758,
+      "step": 37
+    },
+    {
+      "epoch": 2.8411214953271027,
+      "grad_norm": 14.049615859985352,
+      "learning_rate": 1.4529091286973995e-06,
+      "loss": 11.4235,
+      "step": 38
+    },
+    {
+      "epoch": 2.9158878504672896,
+      "grad_norm": 17.158531188964844,
+      "learning_rate": 6.474868681043578e-07,
+      "loss": 11.0862,
+      "step": 39
+    },
+    {
+      "epoch": 2.9906542056074765,
+      "grad_norm": 11.268014907836914,
+      "learning_rate": 1.6213459328950352e-07,
+      "loss": 10.8354,
+      "step": 40
+    },
+    {
+      "epoch": 3.0654205607476634,
+      "grad_norm": 6.079852104187012,
+      "learning_rate": 0.0,
+      "loss": 10.5835,
+      "step": 41
     }
   ],
   "logging_steps": 1,
@@ -212,12 +324,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.565663618577203e+16,
+  "total_flos": 1.0756512736817971e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null