Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789e24fc4034878a3a0a43e0ee68a370ec8ee62093936d76f232165db11b058f
+oid sha256:b5293ed72039fb0272f31d66cb705086e98cb6436b0bdb5d9923973bed34938a
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e396a561d120e45c43cf10187ce16dada87a59eb7752d452986f73c008e3bdd4
+oid sha256:dc00421c2766662ff7a0f2ee36c03b60e9c3cfc2fb84d3ffa69a67e69ce4ac3c
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd62a60f1b88ad5adc9a28cf36643190a21b9d1681bccd20d24f18baf514f2fa
+oid sha256:83bab428aee60a144e7fa438d458eef40c3326f2b73b20c2468c4cdfe2ee47ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04570383912248629,
+  "epoch": 0.09140767824497258,
   "eval_steps": 9,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -206,6 +206,205 @@
       "learning_rate": 9.330127018922194e-05,
       "loss": 0.7847,
       "step": 25
+    },
+    {
+      "epoch": 0.04753199268738574,
+      "grad_norm": 1.3463910818099976,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.7988,
+      "step": 26
+    },
+    {
+      "epoch": 0.04936014625228519,
+      "grad_norm": 1.4402669668197632,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.7279,
+      "step": 27
+    },
+    {
+      "epoch": 0.04936014625228519,
+      "eval_loss": 0.8090941309928894,
+      "eval_runtime": 65.9062,
+      "eval_samples_per_second": 6.995,
+      "eval_steps_per_second": 0.88,
+      "step": 27
+    },
+    {
+      "epoch": 0.051188299817184646,
+      "grad_norm": 1.5752246379852295,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.784,
+      "step": 28
+    },
+    {
+      "epoch": 0.05301645338208409,
+      "grad_norm": 1.5713309049606323,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.8821,
+      "step": 29
+    },
+    {
+      "epoch": 0.054844606946983544,
+      "grad_norm": 1.5881538391113281,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.7659,
+      "step": 30
+    },
+    {
+      "epoch": 0.056672760511883,
+      "grad_norm": 1.4045054912567139,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.8434,
+      "step": 31
+    },
+    {
+      "epoch": 0.05850091407678245,
+      "grad_norm": 1.3920577764511108,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.7623,
+      "step": 32
+    },
+    {
+      "epoch": 0.0603290676416819,
+      "grad_norm": 1.535837173461914,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.8262,
+      "step": 33
+    },
+    {
+      "epoch": 0.062157221206581355,
+      "grad_norm": 1.3267228603363037,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.7212,
+      "step": 34
+    },
+    {
+      "epoch": 0.06398537477148081,
+      "grad_norm": 1.2633198499679565,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.6503,
+      "step": 35
+    },
+    {
+      "epoch": 0.06581352833638025,
+      "grad_norm": 1.4025475978851318,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.7201,
+      "step": 36
+    },
+    {
+      "epoch": 0.06581352833638025,
+      "eval_loss": 0.7338544130325317,
+      "eval_runtime": 65.937,
+      "eval_samples_per_second": 6.992,
+      "eval_steps_per_second": 0.88,
+      "step": 36
+    },
+    {
+      "epoch": 0.06764168190127971,
+      "grad_norm": 1.480459213256836,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.7089,
+      "step": 37
+    },
+    {
+      "epoch": 0.06946983546617916,
+      "grad_norm": 1.4058476686477661,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.7587,
+      "step": 38
+    },
+    {
+      "epoch": 0.0712979890310786,
+      "grad_norm": 1.5269132852554321,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.7869,
+      "step": 39
+    },
+    {
+      "epoch": 0.07312614259597806,
+      "grad_norm": 1.5104089975357056,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.7055,
+      "step": 40
+    },
+    {
+      "epoch": 0.07495429616087751,
+      "grad_norm": 1.5070502758026123,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.677,
+      "step": 41
+    },
+    {
+      "epoch": 0.07678244972577697,
+      "grad_norm": 1.4173520803451538,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.6873,
+      "step": 42
+    },
+    {
+      "epoch": 0.07861060329067641,
+      "grad_norm": 1.5242536067962646,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.707,
+      "step": 43
+    },
+    {
+      "epoch": 0.08043875685557587,
+      "grad_norm": 1.484297752380371,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.6689,
+      "step": 44
+    },
+    {
+      "epoch": 0.08226691042047532,
+      "grad_norm": 1.4110380411148071,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.7221,
+      "step": 45
+    },
+    {
+      "epoch": 0.08226691042047532,
+      "eval_loss": 0.6858494281768799,
+      "eval_runtime": 65.9822,
+      "eval_samples_per_second": 6.987,
+      "eval_steps_per_second": 0.879,
+      "step": 45
+    },
+    {
+      "epoch": 0.08409506398537477,
+      "grad_norm": 1.623942494392395,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.6482,
+      "step": 46
+    },
+    {
+      "epoch": 0.08592321755027423,
+      "grad_norm": 1.4406014680862427,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.6407,
+      "step": 47
+    },
+    {
+      "epoch": 0.08775137111517367,
+      "grad_norm": 1.2649809122085571,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.5991,
+      "step": 48
+    },
+    {
+      "epoch": 0.08957952468007313,
+      "grad_norm": 1.4061084985733032,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.6766,
+      "step": 49
+    },
+    {
+      "epoch": 0.09140767824497258,
+      "grad_norm": 1.412961483001709,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.685,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.91723590385664e+16,
+  "total_flos": 3.83447180771328e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null