Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7a291a32b0075fb1bb6c5429a91a03dec63e325633673cc2d710261b86ec61
+oid sha256:346e6cf8810a70a39be4291afc346b53c918c3cf7d506748ade2a7e326054d9d
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a0132f9b53e54fba8d410967a46b9ca65d322e1fcc1d2fc30e59fc2fb12b179
+oid sha256:99fb1965a8bd54c8d5fd4d7a2dd0af957c38ef401e7225b649137b0348bd3715
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fb53a88c7f354580801381bf9f9cb68ea799947ddde7ac68dff170181f21647
+oid sha256:a125448ed2516369b44b30100b1f18cd9f7f375067d6e1c9d8cd2ace51dbb90c
 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": 0.1394700139470014,
+  "epoch": 0.20920502092050208,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 0.3296,
       "step": 50
+    },
+    {
+      "epoch": 0.14225941422594143,
+      "grad_norm": 0.7000058889389038,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.2693,
+      "step": 51
+    },
+    {
+      "epoch": 0.14504881450488144,
+      "grad_norm": 0.6057772636413574,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.2903,
+      "step": 52
+    },
+    {
+      "epoch": 0.14783821478382148,
+      "grad_norm": 0.5921920537948608,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.239,
+      "step": 53
+    },
+    {
+      "epoch": 0.1506276150627615,
+      "grad_norm": 0.750872015953064,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2087,
+      "step": 54
+    },
+    {
+      "epoch": 0.1506276150627615,
+      "eval_loss": 0.27080443501472473,
+      "eval_runtime": 52.711,
+      "eval_samples_per_second": 5.729,
+      "eval_steps_per_second": 0.721,
+      "step": 54
+    },
+    {
+      "epoch": 0.15341701534170155,
+      "grad_norm": 0.8061081767082214,
+      "learning_rate": 5e-05,
+      "loss": 0.267,
+      "step": 55
+    },
+    {
+      "epoch": 0.15620641562064155,
+      "grad_norm": 0.6060543656349182,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.222,
+      "step": 56
+    },
+    {
+      "epoch": 0.1589958158995816,
+      "grad_norm": 0.6406531929969788,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.2602,
+      "step": 57
+    },
+    {
+      "epoch": 0.16178521617852162,
+      "grad_norm": 1.3150423765182495,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.3005,
+      "step": 58
+    },
+    {
+      "epoch": 0.16457461645746166,
+      "grad_norm": 0.6370297074317932,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.2092,
+      "step": 59
+    },
+    {
+      "epoch": 0.16736401673640167,
+      "grad_norm": 0.6858253479003906,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1646,
+      "step": 60
+    },
+    {
+      "epoch": 0.1701534170153417,
+      "grad_norm": 0.8348706960678101,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.2604,
+      "step": 61
+    },
+    {
+      "epoch": 0.17294281729428174,
+      "grad_norm": 0.7750731706619263,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.2594,
+      "step": 62
+    },
+    {
+      "epoch": 0.17573221757322174,
+      "grad_norm": 0.5308626294136047,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.2119,
+      "step": 63
+    },
+    {
+      "epoch": 0.17573221757322174,
+      "eval_loss": 0.25027772784233093,
+      "eval_runtime": 52.7494,
+      "eval_samples_per_second": 5.725,
+      "eval_steps_per_second": 0.72,
+      "step": 63
+    },
+    {
+      "epoch": 0.17852161785216178,
+      "grad_norm": 0.635723888874054,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2522,
+      "step": 64
+    },
+    {
+      "epoch": 0.18131101813110181,
+      "grad_norm": 0.6576067805290222,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.2243,
+      "step": 65
+    },
+    {
+      "epoch": 0.18410041841004185,
+      "grad_norm": 0.6761228442192078,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.2236,
+      "step": 66
+    },
+    {
+      "epoch": 0.18688981868898186,
+      "grad_norm": 0.6696838736534119,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.2044,
+      "step": 67
+    },
+    {
+      "epoch": 0.1896792189679219,
+      "grad_norm": 0.6317145824432373,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.1486,
+      "step": 68
+    },
+    {
+      "epoch": 0.19246861924686193,
+      "grad_norm": 0.9569390416145325,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.6536,
+      "step": 69
+    },
+    {
+      "epoch": 0.19525801952580196,
+      "grad_norm": 0.7576932907104492,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2566,
+      "step": 70
+    },
+    {
+      "epoch": 0.19804741980474197,
+      "grad_norm": 1.474607229232788,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.3012,
+      "step": 71
+    },
+    {
+      "epoch": 0.200836820083682,
+      "grad_norm": 0.6508307456970215,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.2188,
+      "step": 72
+    },
+    {
+      "epoch": 0.200836820083682,
+      "eval_loss": 0.2393614649772644,
+      "eval_runtime": 52.7336,
+      "eval_samples_per_second": 5.727,
+      "eval_steps_per_second": 0.721,
+      "step": 72
+    },
+    {
+      "epoch": 0.20362622036262204,
+      "grad_norm": 0.6299262642860413,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.1672,
+      "step": 73
+    },
+    {
+      "epoch": 0.20641562064156208,
+      "grad_norm": 0.5372329354286194,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.1438,
+      "step": 74
+    },
+    {
+      "epoch": 0.20920502092050208,
+      "grad_norm": 0.844080924987793,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.213,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.411270135742464e+16,
+  "total_flos": 9.775600008953856e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null