Training in progress, step 68, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2690da81d83e89e9ee7b7dc7113de883b592b46176c59f118aaff5ad1b1c42cc
+oid sha256:f124e3c2fc8ec891656fbfca5ea9b6718202104b53c2f90f6f237b8efab7e7d6
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:580ef17b80875f7190859d2da30842b5c7fe663cfb653f5c46ee771354997856
+oid sha256:34aed8fc1414c28cb971615850dd2195d1ae883d038da558c27b755343438bb1
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02f54eb84b382db409dccc97cebf46240cf5b6285939222273bf59b8c0558286
+oid sha256:a4c0dfbada95d07c631cece0f7fdca52ecc156135c62bc34b4e8b1a466156bc4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c86702c0a3caad6c51746e54805a7289de03dff9cc5abc148a58966cf1f4d339
+oid sha256:3f4e77fd2a3bb3f08929494d77da2f57f8781f91a45852bcf8f71a5777dd088c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07508626639061422,
+  "epoch": 0.10011502185415229,
   "eval_steps": 50,
-  "global_step": 51,
+  "global_step": 68,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -380,6 +380,125 @@
       "learning_rate": 0.00013928754755265842,
       "loss": 0.1427,
       "step": 51
+    },
+    {
+      "epoch": 0.07655854612376352,
+      "grad_norm": 0.12584620714187622,
+      "learning_rate": 0.00013860360721173193,
+      "loss": 0.0863,
+      "step": 52
+    },
+    {
+      "epoch": 0.07803082585691282,
+      "grad_norm": 0.11394777148962021,
+      "learning_rate": 0.0001379002925959068,
+      "loss": 0.0691,
+      "step": 53
+    },
+    {
+      "epoch": 0.07950310559006211,
+      "grad_norm": 0.10938312113285065,
+      "learning_rate": 0.0001371778179416281,
+      "loss": 0.0826,
+      "step": 54
+    },
+    {
+      "epoch": 0.08097538532321141,
+      "grad_norm": 0.12558647990226746,
+      "learning_rate": 0.00013643640332167438,
+      "loss": 0.0766,
+      "step": 55
+    },
+    {
+      "epoch": 0.08244766505636071,
+      "grad_norm": 0.10897130519151688,
+      "learning_rate": 0.00013567627457812106,
+      "loss": 0.062,
+      "step": 56
+    },
+    {
+      "epoch": 0.08391994478951001,
+      "grad_norm": 0.09030541032552719,
+      "learning_rate": 0.00013489766325354695,
+      "loss": 0.0393,
+      "step": 57
+    },
+    {
+      "epoch": 0.08539222452265931,
+      "grad_norm": 0.1143849790096283,
+      "learning_rate": 0.00013410080652050412,
+      "loss": 0.1219,
+      "step": 58
+    },
+    {
+      "epoch": 0.0868645042558086,
+      "grad_norm": 0.1283547431230545,
+      "learning_rate": 0.0001332859471092728,
+      "loss": 0.1195,
+      "step": 59
+    },
+    {
+      "epoch": 0.0883367839889579,
+      "grad_norm": 0.11828132718801498,
+      "learning_rate": 0.00013245333323392333,
+      "loss": 0.0925,
+      "step": 60
+    },
+    {
+      "epoch": 0.0898090637221072,
+      "grad_norm": 0.10878538340330124,
+      "learning_rate": 0.0001316032185167079,
+      "loss": 0.0542,
+      "step": 61
+    },
+    {
+      "epoch": 0.0912813434552565,
+      "grad_norm": 0.1320784091949463,
+      "learning_rate": 0.00013073586191080457,
+      "loss": 0.1005,
+      "step": 62
+    },
+    {
+      "epoch": 0.0927536231884058,
+      "grad_norm": 0.10936389863491058,
+      "learning_rate": 0.00012985152762143778,
+      "loss": 0.0526,
+      "step": 63
+    },
+    {
+      "epoch": 0.0942259029215551,
+      "grad_norm": 0.13538584113121033,
+      "learning_rate": 0.00012895048502539882,
+      "loss": 0.0956,
+      "step": 64
+    },
+    {
+      "epoch": 0.0956981826547044,
+      "grad_norm": 0.13087764382362366,
+      "learning_rate": 0.00012803300858899104,
+      "loss": 0.0795,
+      "step": 65
+    },
+    {
+      "epoch": 0.09717046238785369,
+      "grad_norm": 0.1554757058620453,
+      "learning_rate": 0.0001270993777844248,
+      "loss": 0.1455,
+      "step": 66
+    },
+    {
+      "epoch": 0.09864274212100299,
+      "grad_norm": 0.12131679803133011,
+      "learning_rate": 0.0001261498770046874,
+      "loss": 0.0625,
+      "step": 67
+    },
+    {
+      "epoch": 0.10011502185415229,
+      "grad_norm": 0.11470583826303482,
+      "learning_rate": 0.00012518479547691435,
+      "loss": 0.0903,
+      "step": 68
     }
   ],
   "logging_steps": 1,
@@ -399,7 +518,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.401115673671762e+17,
+  "total_flos": 7.176620549823529e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null