Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f5df66734fdf1be049389ba78ee349594674e53068c13f713b19452b30f17c
+oid sha256:801066273382ad9bd75d81e1271ce2fcc67f368b0e7873ec6765f45d48d45687
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3266e925484b5e0ee9c8f453b44a8c3fc483759456233a64e9f75f688e98e3c8
+oid sha256:98d066ca19d6221b5c2563031e392a0fb4aaa990613a0ef497498eb2e5fd16bb
 size 800394282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65072f5a23f04b35af2bb991261d0d17278046f0d94d2e2e7b409e8dd8b3d1a6
+oid sha256:e65076d159784cf12fd935950cc80a50cd767edca11b9643742f5d1d58eb9d2d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019506485906563932,
+  "epoch": 0.039012971813127864,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 3.34,
       "eval_steps_per_second": 1.67,
       "step": 25
+    },
+    {
+      "epoch": 0.02028674534282649,
+      "grad_norm": 0.7108809351921082,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.8741,
+      "step": 26
+    },
+    {
+      "epoch": 0.021067004779089047,
+      "grad_norm": 0.7109420299530029,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.9355,
+      "step": 27
+    },
+    {
+      "epoch": 0.021847264215351603,
+      "grad_norm": 0.6290819048881531,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.8823,
+      "step": 28
+    },
+    {
+      "epoch": 0.022627523651614162,
+      "grad_norm": 0.6449434161186218,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.8747,
+      "step": 29
+    },
+    {
+      "epoch": 0.023407783087876718,
+      "grad_norm": 0.7190560102462769,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.9264,
+      "step": 30
+    },
+    {
+      "epoch": 0.024188042524139277,
+      "grad_norm": 0.6574559807777405,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.8356,
+      "step": 31
+    },
+    {
+      "epoch": 0.024968301960401833,
+      "grad_norm": 0.6734890937805176,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.9268,
+      "step": 32
+    },
+    {
+      "epoch": 0.025748561396664392,
+      "grad_norm": 0.7330193519592285,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.8603,
+      "step": 33
+    },
+    {
+      "epoch": 0.026528820832926948,
+      "grad_norm": 0.7113292813301086,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.8205,
+      "step": 34
+    },
+    {
+      "epoch": 0.027309080269189507,
+      "grad_norm": 0.6743346452713013,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.8219,
+      "step": 35
+    },
+    {
+      "epoch": 0.028089339705452063,
+      "grad_norm": 0.6742866039276123,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.8635,
+      "step": 36
+    },
+    {
+      "epoch": 0.02886959914171462,
+      "grad_norm": 0.7305226922035217,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.818,
+      "step": 37
+    },
+    {
+      "epoch": 0.029649858577977178,
+      "grad_norm": 0.6999145150184631,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.8282,
+      "step": 38
+    },
+    {
+      "epoch": 0.030430118014239733,
+      "grad_norm": 0.6912006139755249,
+      "learning_rate": 5e-05,
+      "loss": 0.7905,
+      "step": 39
+    },
+    {
+      "epoch": 0.031210377450502293,
+      "grad_norm": 0.7328338623046875,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.8069,
+      "step": 40
+    },
+    {
+      "epoch": 0.03199063688676485,
+      "grad_norm": 0.7178049087524414,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.7919,
+      "step": 41
+    },
+    {
+      "epoch": 0.032770896323027404,
+      "grad_norm": 0.7273955941200256,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8151,
+      "step": 42
+    },
+    {
+      "epoch": 0.03355115575928996,
+      "grad_norm": 0.7298927307128906,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.8524,
+      "step": 43
+    },
+    {
+      "epoch": 0.03433141519555252,
+      "grad_norm": 0.740074872970581,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.8144,
+      "step": 44
+    },
+    {
+      "epoch": 0.03511167463181508,
+      "grad_norm": 0.7409592866897583,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8217,
+      "step": 45
+    },
+    {
+      "epoch": 0.035891934068077634,
+      "grad_norm": 0.757175087928772,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.7642,
+      "step": 46
+    },
+    {
+      "epoch": 0.03667219350434019,
+      "grad_norm": 0.8015655875205994,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.7827,
+      "step": 47
+    },
+    {
+      "epoch": 0.03745245294060275,
+      "grad_norm": 0.7460522651672363,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7761,
+      "step": 48
+    },
+    {
+      "epoch": 0.038232712376865305,
+      "grad_norm": 0.8603819608688354,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.7828,
+      "step": 49
+    },
+    {
+      "epoch": 0.039012971813127864,
+      "grad_norm": 1.0592442750930786,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.8512,
+      "step": 50
+    },
+    {
+      "epoch": 0.039012971813127864,
+      "eval_loss": 0.7553926706314087,
+      "eval_runtime": 323.1681,
+      "eval_samples_per_second": 3.342,
+      "eval_steps_per_second": 1.671,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.878345006854963e+16,
+  "total_flos": 7.737394764919603e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null