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:be7dc769ec13501d38b1ac710479956337430ee3cff518c386207cfa9903028d
+oid sha256:48f7bdf167759cae2f9b6f9fae05ea36727393d4272640e5019aa52225e4ca1d
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f06c7c8e6c3d134b7fd4808b60c7a9e8d0300121377d3d894fc74d6de4887ce0
+oid sha256:e2cb205489d162abcc1da8febf612044a8f89414d1df3c78d4167551ff72324e
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:911058565dc868849673710656c32933e9a5c0c739dc26b6d67dce13bb3e41c3
+oid sha256:9cad2658200f2482b7574bdc57c18294b67c90589354a1df1f50b18ca492e76c
 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": 0.016809547823163556,
+  "epoch": 0.025214321734745335,
   "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": 0.9211,
       "step": 50
+    },
+    {
+      "epoch": 0.01714573877962683,
+      "grad_norm": 0.15525253117084503,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 1.0932,
+      "step": 51
+    },
+    {
+      "epoch": 0.0174819297360901,
+      "grad_norm": 0.16235189139842987,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.8784,
+      "step": 52
+    },
+    {
+      "epoch": 0.01781812069255337,
+      "grad_norm": 0.15708541870117188,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.8008,
+      "step": 53
+    },
+    {
+      "epoch": 0.018154311649016642,
+      "grad_norm": 0.14517341554164886,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.8614,
+      "step": 54
+    },
+    {
+      "epoch": 0.018154311649016642,
+      "eval_loss": 0.3940263092517853,
+      "eval_runtime": 520.2854,
+      "eval_samples_per_second": 4.815,
+      "eval_steps_per_second": 0.604,
+      "step": 54
+    },
+    {
+      "epoch": 0.01849050260547991,
+      "grad_norm": 0.14681681990623474,
+      "learning_rate": 5e-05,
+      "loss": 0.7681,
+      "step": 55
+    },
+    {
+      "epoch": 0.018826693561943185,
+      "grad_norm": 0.16690337657928467,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.8776,
+      "step": 56
+    },
+    {
+      "epoch": 0.019162884518406455,
+      "grad_norm": 0.1465039998292923,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.8363,
+      "step": 57
+    },
+    {
+      "epoch": 0.019499075474869725,
+      "grad_norm": 0.14444556832313538,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.7682,
+      "step": 58
+    },
+    {
+      "epoch": 0.019835266431332998,
+      "grad_norm": 0.15662549436092377,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.8127,
+      "step": 59
+    },
+    {
+      "epoch": 0.020171457387796268,
+      "grad_norm": 0.20951992273330688,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.8957,
+      "step": 60
+    },
+    {
+      "epoch": 0.02050764834425954,
+      "grad_norm": 0.14374086260795593,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.5995,
+      "step": 61
+    },
+    {
+      "epoch": 0.02084383930072281,
+      "grad_norm": 0.16216455399990082,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.8144,
+      "step": 62
+    },
+    {
+      "epoch": 0.02118003025718608,
+      "grad_norm": 0.19871731102466583,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.9087,
+      "step": 63
+    },
+    {
+      "epoch": 0.02118003025718608,
+      "eval_loss": 0.38950610160827637,
+      "eval_runtime": 520.3691,
+      "eval_samples_per_second": 4.814,
+      "eval_steps_per_second": 0.603,
+      "step": 63
+    },
+    {
+      "epoch": 0.021516221213649354,
+      "grad_norm": 0.17969125509262085,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8345,
+      "step": 64
+    },
+    {
+      "epoch": 0.021852412170112624,
+      "grad_norm": 0.1704406887292862,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 1.0127,
+      "step": 65
+    },
+    {
+      "epoch": 0.022188603126575897,
+      "grad_norm": 0.1846325546503067,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.6452,
+      "step": 66
+    },
+    {
+      "epoch": 0.022524794083039167,
+      "grad_norm": 0.17157776653766632,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.8627,
+      "step": 67
+    },
+    {
+      "epoch": 0.022860985039502436,
+      "grad_norm": 0.16123242676258087,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.0274,
+      "step": 68
+    },
+    {
+      "epoch": 0.02319717599596571,
+      "grad_norm": 0.1710616648197174,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.85,
+      "step": 69
+    },
+    {
+      "epoch": 0.02353336695242898,
+      "grad_norm": 0.1854245364665985,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6882,
+      "step": 70
+    },
+    {
+      "epoch": 0.02386955790889225,
+      "grad_norm": 0.17862558364868164,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 1.0612,
+      "step": 71
+    },
+    {
+      "epoch": 0.024205748865355523,
+      "grad_norm": 0.15848234295845032,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.6429,
+      "step": 72
+    },
+    {
+      "epoch": 0.024205748865355523,
+      "eval_loss": 0.3867124319076538,
+      "eval_runtime": 520.5242,
+      "eval_samples_per_second": 4.812,
+      "eval_steps_per_second": 0.603,
+      "step": 72
+    },
+    {
+      "epoch": 0.024541939821818792,
+      "grad_norm": 0.24715834856033325,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.0981,
+      "step": 73
+    },
+    {
+      "epoch": 0.024878130778282066,
+      "grad_norm": 0.17577554285526276,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.8896,
+      "step": 74
+    },
+    {
+      "epoch": 0.025214321734745335,
+      "grad_norm": 0.1859356015920639,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.6978,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.3478299623424e+16,
+  "total_flos": 9.5217449435136e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null