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:e9e5e4a0b5ff99e69d060085f7f9d994d684c7045fb89e5acf66e8fa54edbe15
+oid sha256:085011a6f8f6959af8256de8706ed692f952dc7fce026892ed83f0d28a5de8e1
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:491e9adfc1152d5c2f54f348ed3c39d0066143a4d94e204da30b8cebaef98013
+oid sha256:e60917e24fe21883264ac99804bfae9f1b4183b6eec6fe7633faa985b8f0f589
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c30a3e980ba7fef9f17510e8136c39c706a4a7933de932f5aeeeab091f6901
+oid sha256:bd59315e0a13a2872638ce651a674f4d8a806e8929ce9671bca867ab86dbab7e
 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": 0.000729735252050556,
+  "epoch": 0.001459470504101112,
   "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": 2.9962,
       "step": 25
+    },
+    {
+      "epoch": 0.0007589246621325783,
+      "grad_norm": 5.740274429321289,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 2.9059,
+      "step": 26
+    },
+    {
+      "epoch": 0.0007881140722146005,
+      "grad_norm": 4.832045555114746,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.051,
+      "step": 27
+    },
+    {
+      "epoch": 0.0007881140722146005,
+      "eval_loss": 1.29904043674469,
+      "eval_runtime": 5166.4607,
+      "eval_samples_per_second": 5.584,
+      "eval_steps_per_second": 0.698,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008173034822966228,
+      "grad_norm": 5.021420955657959,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.949,
+      "step": 28
+    },
+    {
+      "epoch": 0.0008464928923786451,
+      "grad_norm": 7.856975555419922,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.8508,
+      "step": 29
+    },
+    {
+      "epoch": 0.0008756823024606673,
+      "grad_norm": 5.426181316375732,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 2.5198,
+      "step": 30
+    },
+    {
+      "epoch": 0.0009048717125426895,
+      "grad_norm": 5.714426040649414,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.613,
+      "step": 31
+    },
+    {
+      "epoch": 0.0009340611226247117,
+      "grad_norm": 3.9779551029205322,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.9224,
+      "step": 32
+    },
+    {
+      "epoch": 0.000963250532706734,
+      "grad_norm": 5.584859371185303,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 2.6696,
+      "step": 33
+    },
+    {
+      "epoch": 0.0009924399427887563,
+      "grad_norm": 7.049388885498047,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.5729,
+      "step": 34
+    },
+    {
+      "epoch": 0.0010216293528707784,
+      "grad_norm": 9.85444450378418,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 2.7488,
+      "step": 35
+    },
+    {
+      "epoch": 0.0010508187629528008,
+      "grad_norm": 5.08799934387207,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.9356,
+      "step": 36
+    },
+    {
+      "epoch": 0.0010508187629528008,
+      "eval_loss": 1.2538187503814697,
+      "eval_runtime": 5165.2612,
+      "eval_samples_per_second": 5.585,
+      "eval_steps_per_second": 0.698,
+      "step": 36
+    },
+    {
+      "epoch": 0.001080008173034823,
+      "grad_norm": 4.305152893066406,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.1296,
+      "step": 37
+    },
+    {
+      "epoch": 0.0011091975831168453,
+      "grad_norm": 4.324735164642334,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 2.434,
+      "step": 38
+    },
+    {
+      "epoch": 0.0011383869931988675,
+      "grad_norm": 5.634093761444092,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 3.0592,
+      "step": 39
+    },
+    {
+      "epoch": 0.0011675764032808896,
+      "grad_norm": 3.8521158695220947,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.2043,
+      "step": 40
+    },
+    {
+      "epoch": 0.001196765813362912,
+      "grad_norm": 4.983729839324951,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 3.2767,
+      "step": 41
+    },
+    {
+      "epoch": 0.0012259552234449341,
+      "grad_norm": 3.823223829269409,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.1992,
+      "step": 42
+    },
+    {
+      "epoch": 0.0012551446335269565,
+      "grad_norm": 5.168725490570068,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 2.8579,
+      "step": 43
+    },
+    {
+      "epoch": 0.0012843340436089787,
+      "grad_norm": 3.6878905296325684,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.9881,
+      "step": 44
+    },
+    {
+      "epoch": 0.0013135234536910008,
+      "grad_norm": 5.2658467292785645,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.8113,
+      "step": 45
+    },
+    {
+      "epoch": 0.0013135234536910008,
+      "eval_loss": 1.2026046514511108,
+      "eval_runtime": 5163.7463,
+      "eval_samples_per_second": 5.587,
+      "eval_steps_per_second": 0.699,
+      "step": 45
+    },
+    {
+      "epoch": 0.0013427128637730232,
+      "grad_norm": 4.249842166900635,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.1704,
+      "step": 46
+    },
+    {
+      "epoch": 0.0013719022738550453,
+      "grad_norm": 4.676008701324463,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 2.5203,
+      "step": 47
+    },
+    {
+      "epoch": 0.0014010916839370677,
+      "grad_norm": 5.7045817375183105,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.4709,
+      "step": 48
+    },
+    {
+      "epoch": 0.0014302810940190899,
+      "grad_norm": 4.275635719299316,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.595,
+      "step": 49
+    },
+    {
+      "epoch": 0.001459470504101112,
+      "grad_norm": 5.484550476074219,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.4328,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.74519592124416e+16,
+  "total_flos": 7.6173476364288e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null