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:fcec0f72b749a5368fac9d4c2c20405a88cb5aa3385bddfcd6bded962ffd5622
+oid sha256:66b1f51030bb007cb8c00cb787e59a0fcb3c57367f52fa71ff12f385654f08f5
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b7c90593bcd3e0c99bc28cf591efc92997498e3ce496fd06d77f78a43637c11
+oid sha256:6db25879075003f326cc6d3b89c659737a69de1b88d39d171ff9237e3d44d3fd
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c334162029911df951f21e152e5ddf37f5d979575a6d060ad1d369247ccd5d4
+oid sha256:c08c9f2db3519491f65c896dc5570f0688363fea4110372251c117212111fc45
 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": 0.07374631268436578,
+  "epoch": 0.14749262536873156,
   "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": 2.8964,
       "step": 25
+    },
+    {
+      "epoch": 0.07669616519174041,
+      "grad_norm": 1.7615406513214111,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 1.5812,
+      "step": 26
+    },
+    {
+      "epoch": 0.07964601769911504,
+      "grad_norm": 2.4763855934143066,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 2.2404,
+      "step": 27
+    },
+    {
+      "epoch": 0.07964601769911504,
+      "eval_loss": 1.0080937147140503,
+      "eval_runtime": 44.3909,
+      "eval_samples_per_second": 6.443,
+      "eval_steps_per_second": 0.811,
+      "step": 27
+    },
+    {
+      "epoch": 0.08259587020648967,
+      "grad_norm": 2.52359676361084,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.7129,
+      "step": 28
+    },
+    {
+      "epoch": 0.0855457227138643,
+      "grad_norm": 2.9214510917663574,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 2.0964,
+      "step": 29
+    },
+    {
+      "epoch": 0.08849557522123894,
+      "grad_norm": 2.418994188308716,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.9937,
+      "step": 30
+    },
+    {
+      "epoch": 0.09144542772861357,
+      "grad_norm": 2.003028154373169,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 2.5031,
+      "step": 31
+    },
+    {
+      "epoch": 0.0943952802359882,
+      "grad_norm": 3.0602455139160156,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 1.8419,
+      "step": 32
+    },
+    {
+      "epoch": 0.09734513274336283,
+      "grad_norm": 3.8223624229431152,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.7186,
+      "step": 33
+    },
+    {
+      "epoch": 0.10029498525073746,
+      "grad_norm": 2.1360504627227783,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.8072,
+      "step": 34
+    },
+    {
+      "epoch": 0.10324483775811209,
+      "grad_norm": 2.5613925457000732,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 1.4713,
+      "step": 35
+    },
+    {
+      "epoch": 0.10619469026548672,
+      "grad_norm": 4.114505767822266,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 1.8798,
+      "step": 36
+    },
+    {
+      "epoch": 0.10619469026548672,
+      "eval_loss": 0.9803729057312012,
+      "eval_runtime": 44.3399,
+      "eval_samples_per_second": 6.45,
+      "eval_steps_per_second": 0.812,
+      "step": 36
+    },
+    {
+      "epoch": 0.10914454277286136,
+      "grad_norm": 2.2606899738311768,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.1288,
+      "step": 37
+    },
+    {
+      "epoch": 0.11209439528023599,
+      "grad_norm": 2.3474953174591064,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.8458,
+      "step": 38
+    },
+    {
+      "epoch": 0.11504424778761062,
+      "grad_norm": 2.764202833175659,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 3.0195,
+      "step": 39
+    },
+    {
+      "epoch": 0.11799410029498525,
+      "grad_norm": 2.4660158157348633,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.827,
+      "step": 40
+    },
+    {
+      "epoch": 0.12094395280235988,
+      "grad_norm": 2.5078041553497314,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 1.3851,
+      "step": 41
+    },
+    {
+      "epoch": 0.12389380530973451,
+      "grad_norm": 2.1289970874786377,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.4684,
+      "step": 42
+    },
+    {
+      "epoch": 0.12684365781710916,
+      "grad_norm": 3.008479595184326,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.7663,
+      "step": 43
+    },
+    {
+      "epoch": 0.12979351032448377,
+      "grad_norm": 2.681143045425415,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 1.6546,
+      "step": 44
+    },
+    {
+      "epoch": 0.13274336283185842,
+      "grad_norm": 3.201345443725586,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.0512,
+      "step": 45
+    },
+    {
+      "epoch": 0.13274336283185842,
+      "eval_loss": 0.9570127129554749,
+      "eval_runtime": 44.365,
+      "eval_samples_per_second": 6.447,
+      "eval_steps_per_second": 0.811,
+      "step": 45
+    },
+    {
+      "epoch": 0.13569321533923304,
+      "grad_norm": 1.8258627653121948,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.5324,
+      "step": 46
+    },
+    {
+      "epoch": 0.13864306784660768,
+      "grad_norm": 1.8189584016799927,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 1.7706,
+      "step": 47
+    },
+    {
+      "epoch": 0.1415929203539823,
+      "grad_norm": 2.40757155418396,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 2.6126,
+      "step": 48
+    },
+    {
+      "epoch": 0.14454277286135694,
+      "grad_norm": 2.335020065307617,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 2.326,
+      "step": 49
+    },
+    {
+      "epoch": 0.14749262536873156,
+      "grad_norm": 1.997075080871582,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 2.5148,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.173894848512e+16,
+  "total_flos": 6.347789697024e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null