Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3673c2ae47f37ef258277f82ab41a0e4a90356a1541d14199d58dfc7bf667f7b
+oid sha256:6432f06093e112165e27bfca42faf1a66f88a613db54acc427ebd4d78e6f1364
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc410672882d33123606a04465cdb4f01f0419e4fb2dccf90a55de0f7514167a
+oid sha256:aeb238706915ddac055b15a743da9bfce76239167e3e0972aae347454beb1289
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0c7f09bd73266dd99569e538df619114201cc00b773cd167ed6de626e73d7a9
+oid sha256:3afaf3f3564c16c04d795830fb092a2ac6c3faca33ed33013ede0152903d175f
 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": 0.04764173415912339,
+  "epoch": 0.07146260123868509,
   "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": 1.9995,
       "step": 50
+    },
+    {
+      "epoch": 0.04859456884230586,
+      "grad_norm": 1.1231671571731567,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.2521,
+      "step": 51
+    },
+    {
+      "epoch": 0.04954740352548833,
+      "grad_norm": 1.1129883527755737,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.0542,
+      "step": 52
+    },
+    {
+      "epoch": 0.0505002382086708,
+      "grad_norm": 1.109358310699463,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 2.04,
+      "step": 53
+    },
+    {
+      "epoch": 0.05145307289185326,
+      "grad_norm": 1.1299806833267212,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.4423,
+      "step": 54
+    },
+    {
+      "epoch": 0.05145307289185326,
+      "eval_loss": 2.2711129188537598,
+      "eval_runtime": 196.6182,
+      "eval_samples_per_second": 4.496,
+      "eval_steps_per_second": 0.565,
+      "step": 54
+    },
+    {
+      "epoch": 0.05240590757503573,
+      "grad_norm": 1.216711401939392,
+      "learning_rate": 5e-05,
+      "loss": 2.1914,
+      "step": 55
+    },
+    {
+      "epoch": 0.0533587422582182,
+      "grad_norm": 1.4715956449508667,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.6387,
+      "step": 56
+    },
+    {
+      "epoch": 0.054311576941400666,
+      "grad_norm": 1.202911615371704,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.2061,
+      "step": 57
+    },
+    {
+      "epoch": 0.055264411624583135,
+      "grad_norm": 11.649187088012695,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.0835,
+      "step": 58
+    },
+    {
+      "epoch": 0.0562172463077656,
+      "grad_norm": 1.2017055749893188,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 2.2761,
+      "step": 59
+    },
+    {
+      "epoch": 0.05717008099094807,
+      "grad_norm": 1.1830456256866455,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.4208,
+      "step": 60
+    },
+    {
+      "epoch": 0.05812291567413054,
+      "grad_norm": 1.0666215419769287,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 2.2889,
+      "step": 61
+    },
+    {
+      "epoch": 0.05907575035731301,
+      "grad_norm": 0.9857567548751831,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.2491,
+      "step": 62
+    },
+    {
+      "epoch": 0.06002858504049548,
+      "grad_norm": 0.9194086194038391,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.028,
+      "step": 63
+    },
+    {
+      "epoch": 0.06002858504049548,
+      "eval_loss": 2.2625362873077393,
+      "eval_runtime": 196.687,
+      "eval_samples_per_second": 4.494,
+      "eval_steps_per_second": 0.564,
+      "step": 63
+    },
+    {
+      "epoch": 0.06098141972367794,
+      "grad_norm": 5.810688495635986,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.3557,
+      "step": 64
+    },
+    {
+      "epoch": 0.06193425440686041,
+      "grad_norm": 1.6563860177993774,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 2.1718,
+      "step": 65
+    },
+    {
+      "epoch": 0.06288708909004288,
+      "grad_norm": 4.58107852935791,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.2625,
+      "step": 66
+    },
+    {
+      "epoch": 0.06383992377322535,
+      "grad_norm": 1.1236543655395508,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 2.1118,
+      "step": 67
+    },
+    {
+      "epoch": 0.06479275845640782,
+      "grad_norm": 1.2911332845687866,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.2574,
+      "step": 68
+    },
+    {
+      "epoch": 0.06574559313959027,
+      "grad_norm": 1.0672364234924316,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.1681,
+      "step": 69
+    },
+    {
+      "epoch": 0.06669842782277274,
+      "grad_norm": 1.161694049835205,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.3036,
+      "step": 70
+    },
+    {
+      "epoch": 0.06765126250595521,
+      "grad_norm": 1.2077661752700806,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 2.204,
+      "step": 71
+    },
+    {
+      "epoch": 0.06860409718913768,
+      "grad_norm": 1.1666839122772217,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.2889,
+      "step": 72
+    },
+    {
+      "epoch": 0.06860409718913768,
+      "eval_loss": 2.254430055618286,
+      "eval_runtime": 196.7106,
+      "eval_samples_per_second": 4.494,
+      "eval_steps_per_second": 0.564,
+      "step": 72
+    },
+    {
+      "epoch": 0.06955693187232015,
+      "grad_norm": 0.7700322866439819,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.0121,
+      "step": 73
+    },
+    {
+      "epoch": 0.07050976655550262,
+      "grad_norm": 0.9282349944114685,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.1442,
+      "step": 74
+    },
+    {
+      "epoch": 0.07146260123868509,
+      "grad_norm": 0.8676728010177612,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.102,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.41887283560448e+16,
+  "total_flos": 1.112830925340672e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null