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:b2c1974f1a5aefff4205ef8321a1aa3490ff07b1c4ef9611d384c6cd700eb7cf
+oid sha256:0ab45aa988e6a9c84b8ca98631ddfe1a5c121434eeabc697ffd322ae9776fd50
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f23e11350d7f99aebf86b741b44d2944d1fc40f0bd210d7cbd24de5b02d5a4f
+oid sha256:cdd5f7749d0760109dde2f21e167c77485ede84e2f8b88e76abfb9ab4f2bc29d
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efaca16a676d4ae6ebaf66057866b601409d301d4063bf0b2bd4c7eb4965b1c7
+oid sha256:a1402da9553ca434c2f6710d2d40e3b5eae193c866f0bef2eaccca39058993a1
 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": 0.004218697266284171,
+  "epoch": 0.008437394532568343,
   "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": 0.715,
       "step": 25
+    },
+    {
+      "epoch": 0.004387445156935539,
+      "grad_norm": 0.2743527591228485,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.8243,
+      "step": 26
+    },
+    {
+      "epoch": 0.004556193047586905,
+      "grad_norm": 0.2194703072309494,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.8237,
+      "step": 27
+    },
+    {
+      "epoch": 0.004556193047586905,
+      "eval_loss": 0.7984665632247925,
+      "eval_runtime": 673.0127,
+      "eval_samples_per_second": 7.414,
+      "eval_steps_per_second": 0.927,
+      "step": 27
+    },
+    {
+      "epoch": 0.004724940938238272,
+      "grad_norm": 0.2173057645559311,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.6946,
+      "step": 28
+    },
+    {
+      "epoch": 0.0048936888288896386,
+      "grad_norm": 0.26414012908935547,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.9683,
+      "step": 29
+    },
+    {
+      "epoch": 0.005062436719541006,
+      "grad_norm": 0.19070331752300262,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.7274,
+      "step": 30
+    },
+    {
+      "epoch": 0.005231184610192373,
+      "grad_norm": 0.22258605062961578,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.6563,
+      "step": 31
+    },
+    {
+      "epoch": 0.005399932500843739,
+      "grad_norm": 0.16770727932453156,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.7469,
+      "step": 32
+    },
+    {
+      "epoch": 0.005568680391495107,
+      "grad_norm": 0.2346215546131134,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.7293,
+      "step": 33
+    },
+    {
+      "epoch": 0.005737428282146473,
+      "grad_norm": 0.20247291028499603,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.722,
+      "step": 34
+    },
+    {
+      "epoch": 0.00590617617279784,
+      "grad_norm": 0.2722700834274292,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.8538,
+      "step": 35
+    },
+    {
+      "epoch": 0.006074924063449207,
+      "grad_norm": 0.23295146226882935,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.7712,
+      "step": 36
+    },
+    {
+      "epoch": 0.006074924063449207,
+      "eval_loss": 0.7734177708625793,
+      "eval_runtime": 672.6791,
+      "eval_samples_per_second": 7.418,
+      "eval_steps_per_second": 0.928,
+      "step": 36
+    },
+    {
+      "epoch": 0.006243671954100574,
+      "grad_norm": 0.22734515368938446,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.6952,
+      "step": 37
+    },
+    {
+      "epoch": 0.00641241984475194,
+      "grad_norm": 0.23274950683116913,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.6745,
+      "step": 38
+    },
+    {
+      "epoch": 0.0065811677354033074,
+      "grad_norm": 0.2169954478740692,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.8216,
+      "step": 39
+    },
+    {
+      "epoch": 0.006749915626054675,
+      "grad_norm": 0.24286970496177673,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.7567,
+      "step": 40
+    },
+    {
+      "epoch": 0.006918663516706041,
+      "grad_norm": 0.21593761444091797,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.7137,
+      "step": 41
+    },
+    {
+      "epoch": 0.007087411407357408,
+      "grad_norm": 0.23738643527030945,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.7267,
+      "step": 42
+    },
+    {
+      "epoch": 0.007256159298008775,
+      "grad_norm": 0.23834103345870972,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.8647,
+      "step": 43
+    },
+    {
+      "epoch": 0.007424907188660142,
+      "grad_norm": 0.19728927314281464,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.6978,
+      "step": 44
+    },
+    {
+      "epoch": 0.007593655079311508,
+      "grad_norm": 0.25146934390068054,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.8439,
+      "step": 45
+    },
+    {
+      "epoch": 0.007593655079311508,
+      "eval_loss": 0.7586240172386169,
+      "eval_runtime": 672.7804,
+      "eval_samples_per_second": 7.417,
+      "eval_steps_per_second": 0.927,
+      "step": 45
+    },
+    {
+      "epoch": 0.0077624029699628755,
+      "grad_norm": 0.2514830529689789,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.7707,
+      "step": 46
+    },
+    {
+      "epoch": 0.007931150860614243,
+      "grad_norm": 0.21285653114318848,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.6869,
+      "step": 47
+    },
+    {
+      "epoch": 0.00809989875126561,
+      "grad_norm": 0.2110971063375473,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.8896,
+      "step": 48
+    },
+    {
+      "epoch": 0.008268646641916975,
+      "grad_norm": 0.22739623486995697,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.7584,
+      "step": 49
+    },
+    {
+      "epoch": 0.008437394532568343,
+      "grad_norm": 0.27134278416633606,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.8999,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.049391762341888e+16,
+  "total_flos": 4.197947642216448e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null