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:cf5b200e6f9c6618a0658ade682279b9308799d413096a768fcef9e8fb54775e
+oid sha256:f4fbbb9f62958c897c43cd9a5c5d6d038f45ed677354628edd0108e1edcb9118
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7497b7e6d0e58635f03cda3329291c987f09a65e3545679b5761dadd425abad8
+oid sha256:7ac320922865fe9265305a2a402e32430894fc71705dc508dc59544e6c1900df
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e9b243df93fca8e540c85b8c141b058b63f5a8d46754cc3dd7c5514038fddbd
+oid sha256:65d9923ac95d4aa4a298bd8ed065c1e1d7f9c926e4f6149f930b0b873ca9c5f4
 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": 0.005327082889409759,
+  "epoch": 0.010654165778819518,
   "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": 2.3188,
       "step": 25
+    },
+    {
+      "epoch": 0.00554016620498615,
+      "grad_norm": 1.7765617370605469,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.1691,
+      "step": 26
+    },
+    {
+      "epoch": 0.00575324952056254,
+      "grad_norm": 1.7104406356811523,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.3399,
+      "step": 27
+    },
+    {
+      "epoch": 0.00575324952056254,
+      "eval_loss": 2.3587300777435303,
+      "eval_runtime": 485.0287,
+      "eval_samples_per_second": 8.148,
+      "eval_steps_per_second": 1.018,
+      "step": 27
+    },
+    {
+      "epoch": 0.00596633283613893,
+      "grad_norm": 1.2958590984344482,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.336,
+      "step": 28
+    },
+    {
+      "epoch": 0.006179416151715321,
+      "grad_norm": 1.8951802253723145,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.5203,
+      "step": 29
+    },
+    {
+      "epoch": 0.006392499467291711,
+      "grad_norm": 1.4188854694366455,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.5081,
+      "step": 30
+    },
+    {
+      "epoch": 0.0066055827828681015,
+      "grad_norm": 1.756216287612915,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.2355,
+      "step": 31
+    },
+    {
+      "epoch": 0.006818666098444491,
+      "grad_norm": 1.6971544027328491,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 2.2753,
+      "step": 32
+    },
+    {
+      "epoch": 0.007031749414020882,
+      "grad_norm": 1.730682611465454,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.2489,
+      "step": 33
+    },
+    {
+      "epoch": 0.007244832729597273,
+      "grad_norm": 1.500222086906433,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.5747,
+      "step": 34
+    },
+    {
+      "epoch": 0.007457916045173663,
+      "grad_norm": 1.689780592918396,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 2.4923,
+      "step": 35
+    },
+    {
+      "epoch": 0.0076709993607500535,
+      "grad_norm": 1.5094739198684692,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 2.3113,
+      "step": 36
+    },
+    {
+      "epoch": 0.0076709993607500535,
+      "eval_loss": 2.3216378688812256,
+      "eval_runtime": 485.2683,
+      "eval_samples_per_second": 8.144,
+      "eval_steps_per_second": 1.018,
+      "step": 36
+    },
+    {
+      "epoch": 0.007884082676326443,
+      "grad_norm": 1.8050920963287354,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.1219,
+      "step": 37
+    },
+    {
+      "epoch": 0.008097165991902834,
+      "grad_norm": 1.7702151536941528,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.3288,
+      "step": 38
+    },
+    {
+      "epoch": 0.008310249307479225,
+      "grad_norm": 1.9148733615875244,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 2.2052,
+      "step": 39
+    },
+    {
+      "epoch": 0.008523332623055616,
+      "grad_norm": 1.9198733568191528,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.0524,
+      "step": 40
+    },
+    {
+      "epoch": 0.008736415938632005,
+      "grad_norm": 1.6441048383712769,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 2.3595,
+      "step": 41
+    },
+    {
+      "epoch": 0.008949499254208395,
+      "grad_norm": 1.6988778114318848,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.2509,
+      "step": 42
+    },
+    {
+      "epoch": 0.009162582569784786,
+      "grad_norm": 1.6815834045410156,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.285,
+      "step": 43
+    },
+    {
+      "epoch": 0.009375665885361177,
+      "grad_norm": 1.5567946434020996,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 2.2638,
+      "step": 44
+    },
+    {
+      "epoch": 0.009588749200937566,
+      "grad_norm": 1.5238242149353027,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.455,
+      "step": 45
+    },
+    {
+      "epoch": 0.009588749200937566,
+      "eval_loss": 2.2901864051818848,
+      "eval_runtime": 484.6308,
+      "eval_samples_per_second": 8.155,
+      "eval_steps_per_second": 1.019,
+      "step": 45
+    },
+    {
+      "epoch": 0.009801832516513957,
+      "grad_norm": 1.698690414428711,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.5036,
+      "step": 46
+    },
+    {
+      "epoch": 0.010014915832090347,
+      "grad_norm": 1.5626423358917236,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.3447,
+      "step": 47
+    },
+    {
+      "epoch": 0.010227999147666738,
+      "grad_norm": 1.6634929180145264,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.2132,
+      "step": 48
+    },
+    {
+      "epoch": 0.010441082463243129,
+      "grad_norm": 1.5750799179077148,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.4226,
+      "step": 49
+    },
+    {
+      "epoch": 0.010654165778819518,
+      "grad_norm": 1.4968082904815674,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.3799,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.85471820890112e+16,
+  "total_flos": 3.70943641780224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null