Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5903f03fb873b594317036d1b3058285e825d81aff26ce19a33fd6fbc9377ecb
+oid sha256:e87d7e0bb792078e0dc620645249aa24d34e3404d744fcb7c43b1c3c39d1d8f0
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54fc843391a9d822484f02f10d14a910fe25c46c8aa3fecc338eca43134f63e
+oid sha256:2bb45fb6dd9754fa066bab83c4703917b43eb27c5dfa3a4f3db611d08817e1a8
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1b9d1de311812320d04acc9a090b8bc0e198690b0ab0a70bfe2a2525696e789
+oid sha256:7599fc7e35920f1e1dfe1dde7aa1dc2b189c47384e9c696e1b6cddfd02b2c333
 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": 0.0025351112913856917,
+  "epoch": 0.005070222582771383,
   "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": 2.724,
       "step": 25
+    },
+    {
+      "epoch": 0.0026365157430411194,
+      "grad_norm": 11.551734924316406,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.6014,
+      "step": 26
+    },
+    {
+      "epoch": 0.002737920194696547,
+      "grad_norm": 12.696028709411621,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.9341,
+      "step": 27
+    },
+    {
+      "epoch": 0.002737920194696547,
+      "eval_loss": 1.0254631042480469,
+      "eval_runtime": 2531.8043,
+      "eval_samples_per_second": 3.28,
+      "eval_steps_per_second": 0.41,
+      "step": 27
+    },
+    {
+      "epoch": 0.002839324646351975,
+      "grad_norm": 15.396026611328125,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.137,
+      "step": 28
+    },
+    {
+      "epoch": 0.0029407290980074025,
+      "grad_norm": 8.307568550109863,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.1559,
+      "step": 29
+    },
+    {
+      "epoch": 0.0030421335496628303,
+      "grad_norm": 7.1335039138793945,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.0939,
+      "step": 30
+    },
+    {
+      "epoch": 0.003143538001318258,
+      "grad_norm": 10.62819766998291,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 1.8892,
+      "step": 31
+    },
+    {
+      "epoch": 0.0032449424529736857,
+      "grad_norm": 11.622336387634277,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.6192,
+      "step": 32
+    },
+    {
+      "epoch": 0.0033463469046291134,
+      "grad_norm": 17.134801864624023,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.4415,
+      "step": 33
+    },
+    {
+      "epoch": 0.0034477513562845407,
+      "grad_norm": 10.51050090789795,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.087,
+      "step": 34
+    },
+    {
+      "epoch": 0.0035491558079399684,
+      "grad_norm": 13.633468627929688,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.2582,
+      "step": 35
+    },
+    {
+      "epoch": 0.003650560259595396,
+      "grad_norm": 7.963433742523193,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.8015,
+      "step": 36
+    },
+    {
+      "epoch": 0.003650560259595396,
+      "eval_loss": 0.7936967611312866,
+      "eval_runtime": 2531.3442,
+      "eval_samples_per_second": 3.281,
+      "eval_steps_per_second": 0.41,
+      "step": 36
+    },
+    {
+      "epoch": 0.003751964711250824,
+      "grad_norm": 9.670333862304688,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.2679,
+      "step": 37
+    },
+    {
+      "epoch": 0.0038533691629062516,
+      "grad_norm": 6.487051963806152,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.0628,
+      "step": 38
+    },
+    {
+      "epoch": 0.003954773614561679,
+      "grad_norm": 4.90863037109375,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.7516,
+      "step": 39
+    },
+    {
+      "epoch": 0.004056178066217107,
+      "grad_norm": 10.051084518432617,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.357,
+      "step": 40
+    },
+    {
+      "epoch": 0.004157582517872535,
+      "grad_norm": 12.850255966186523,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.7103,
+      "step": 41
+    },
+    {
+      "epoch": 0.0042589869695279624,
+      "grad_norm": 5.273253917694092,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.9891,
+      "step": 42
+    },
+    {
+      "epoch": 0.00436039142118339,
+      "grad_norm": 8.386213302612305,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.1369,
+      "step": 43
+    },
+    {
+      "epoch": 0.004461795872838818,
+      "grad_norm": 6.173641681671143,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.6839,
+      "step": 44
+    },
+    {
+      "epoch": 0.004563200324494246,
+      "grad_norm": 7.425925254821777,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.1384,
+      "step": 45
+    },
+    {
+      "epoch": 0.004563200324494246,
+      "eval_loss": 0.6476368308067322,
+      "eval_runtime": 2531.2596,
+      "eval_samples_per_second": 3.281,
+      "eval_steps_per_second": 0.41,
+      "step": 45
+    },
+    {
+      "epoch": 0.004664604776149673,
+      "grad_norm": 8.646309852600098,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.5463,
+      "step": 46
+    },
+    {
+      "epoch": 0.004766009227805101,
+      "grad_norm": 7.022440433502197,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.6431,
+      "step": 47
+    },
+    {
+      "epoch": 0.004867413679460528,
+      "grad_norm": 6.80689811706543,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.917,
+      "step": 48
+    },
+    {
+      "epoch": 0.004968818131115956,
+      "grad_norm": 7.6442179679870605,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 1.0936,
+      "step": 49
+    },
+    {
+      "epoch": 0.005070222582771383,
+      "grad_norm": 6.82839298248291,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 1.2947,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.15735600611328e+16,
+  "total_flos": 1.231471201222656e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null