Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f9b8dc1d7e8176bf9d4dbd3d841c9ff09655e16f331e903d31f6437fe00eed0
+oid sha256:868ca528ad5ad659a0c77b45a26f8429103ac618b1fd4a939db91152ed54ba9b
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0532093a1b2a15ad0adca295b2159e36e57d90faeba0374084f0734e255c43de
+oid sha256:6a33475732e9a773cd7793e22108175431ef044c6d327d8a845a05a5d911be56
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0c59790f2e3ba0a4714a087914c6124ed7398fe25ca94de6ab9e0301a8e585f
+oid sha256:7f53083d6bf416fa674a4d7654c4dc44772d047f9fd45a1c2d70bd5cf789eb73
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0565171317555634,
+  "epoch": 0.08477569763334511,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 13.777,
       "eval_steps_per_second": 6.888,
       "step": 50
+    },
+    {
+      "epoch": 0.05764747439067467,
+      "grad_norm": 0.10484740883111954,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.1664,
+      "step": 51
+    },
+    {
+      "epoch": 0.05877781702578594,
+      "grad_norm": 0.09817209094762802,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.1572,
+      "step": 52
+    },
+    {
+      "epoch": 0.05990815966089721,
+      "grad_norm": 0.09848269075155258,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.1595,
+      "step": 53
+    },
+    {
+      "epoch": 0.061038502296008476,
+      "grad_norm": 0.09713145345449448,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.1644,
+      "step": 54
+    },
+    {
+      "epoch": 0.062168844931119745,
+      "grad_norm": 0.11254185438156128,
+      "learning_rate": 5e-05,
+      "loss": 0.153,
+      "step": 55
+    },
+    {
+      "epoch": 0.06329918756623101,
+      "grad_norm": 0.10281391441822052,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.1617,
+      "step": 56
+    },
+    {
+      "epoch": 0.06442953020134229,
+      "grad_norm": 0.09166331589221954,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.145,
+      "step": 57
+    },
+    {
+      "epoch": 0.06555987283645355,
+      "grad_norm": 0.09803515672683716,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.1616,
+      "step": 58
+    },
+    {
+      "epoch": 0.06669021547156481,
+      "grad_norm": 0.0987379401922226,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.1689,
+      "step": 59
+    },
+    {
+      "epoch": 0.06782055810667609,
+      "grad_norm": 0.09968309849500656,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1529,
+      "step": 60
+    },
+    {
+      "epoch": 0.06895090074178735,
+      "grad_norm": 0.09657073765993118,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.1593,
+      "step": 61
+    },
+    {
+      "epoch": 0.07008124337689862,
+      "grad_norm": 0.10319285094738007,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.1617,
+      "step": 62
+    },
+    {
+      "epoch": 0.07121158601200989,
+      "grad_norm": 0.09319040179252625,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.1388,
+      "step": 63
+    },
+    {
+      "epoch": 0.07234192864712116,
+      "grad_norm": 0.10078910738229752,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.157,
+      "step": 64
+    },
+    {
+      "epoch": 0.07347227128223242,
+      "grad_norm": 0.0971289873123169,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.157,
+      "step": 65
+    },
+    {
+      "epoch": 0.0746026139173437,
+      "grad_norm": 0.09027408063411713,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.1278,
+      "step": 66
+    },
+    {
+      "epoch": 0.07573295655245496,
+      "grad_norm": 0.09577968716621399,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.1476,
+      "step": 67
+    },
+    {
+      "epoch": 0.07686329918756624,
+      "grad_norm": 0.095377616584301,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.1401,
+      "step": 68
+    },
+    {
+      "epoch": 0.0779936418226775,
+      "grad_norm": 0.09206076711416245,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.145,
+      "step": 69
+    },
+    {
+      "epoch": 0.07912398445778877,
+      "grad_norm": 0.10833960771560669,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.144,
+      "step": 70
+    },
+    {
+      "epoch": 0.08025432709290004,
+      "grad_norm": 0.10532192140817642,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.1684,
+      "step": 71
+    },
+    {
+      "epoch": 0.0813846697280113,
+      "grad_norm": 0.09503438323736191,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.1353,
+      "step": 72
+    },
+    {
+      "epoch": 0.08251501236312257,
+      "grad_norm": 0.10530933737754822,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.1293,
+      "step": 73
+    },
+    {
+      "epoch": 0.08364535499823383,
+      "grad_norm": 0.0886959508061409,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.1283,
+      "step": 74
+    },
+    {
+      "epoch": 0.08477569763334511,
+      "grad_norm": 0.09509113430976868,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.1503,
+      "step": 75
+    },
+    {
+      "epoch": 0.08477569763334511,
+      "eval_loss": 0.14312788844108582,
+      "eval_runtime": 108.0678,
+      "eval_samples_per_second": 13.788,
+      "eval_steps_per_second": 6.894,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -400,7 +583,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.26648217239552e+17,
+  "total_flos": 1.89972325859328e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null