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:f4099622828b2a6650a7e9e87a80d64dac11d2530b822c8ba3ba10881914b7a8
+oid sha256:8b3dc969975efef6dd9c1516bd553d6ee9ae418b3c21b4aa24aa6881d8df6d22
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f9bb23c95efe2621ea5d3c22fb369ee6a0b7380df05e8d079da1926fbd7a0e
+oid sha256:c4419a4f2a06b37625c1970faafceee39be13eadd709d803160a7138314eccdf
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec321806b1d45557a32bf6b51a82e1fbe0f11344d9834ca94ecdc32cb694ca75
+oid sha256:274bad6912abd00f7939e88b2927c448da73420ebf4efa2b0a54eb2c00324194
 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": 0.0034338300940869445,
+  "epoch": 0.006867660188173889,
   "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": 0.9594,
       "step": 25
+    },
+    {
+      "epoch": 0.003571183297850422,
+      "grad_norm": 1.5292807817459106,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.7581,
+      "step": 26
+    },
+    {
+      "epoch": 0.0037085365016139003,
+      "grad_norm": 2.0904600620269775,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 1.0291,
+      "step": 27
+    },
+    {
+      "epoch": 0.0037085365016139003,
+      "eval_loss": 1.0520473718643188,
+      "eval_runtime": 1387.7815,
+      "eval_samples_per_second": 4.418,
+      "eval_steps_per_second": 0.553,
+      "step": 27
+    },
+    {
+      "epoch": 0.003845889705377378,
+      "grad_norm": 2.166792631149292,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.0476,
+      "step": 28
+    },
+    {
+      "epoch": 0.003983242909140856,
+      "grad_norm": 4.157371997833252,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 1.1389,
+      "step": 29
+    },
+    {
+      "epoch": 0.004120596112904333,
+      "grad_norm": 2.744110345840454,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 1.005,
+      "step": 30
+    },
+    {
+      "epoch": 0.004257949316667811,
+      "grad_norm": 2.2463557720184326,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.7509,
+      "step": 31
+    },
+    {
+      "epoch": 0.0043953025204312894,
+      "grad_norm": 2.687026023864746,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.8431,
+      "step": 32
+    },
+    {
+      "epoch": 0.004532655724194767,
+      "grad_norm": 2.2226080894470215,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.9746,
+      "step": 33
+    },
+    {
+      "epoch": 0.004670008927958245,
+      "grad_norm": 1.9216952323913574,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.6121,
+      "step": 34
+    },
+    {
+      "epoch": 0.004807362131721722,
+      "grad_norm": 2.6237952709198,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.6943,
+      "step": 35
+    },
+    {
+      "epoch": 0.0049447153354852,
+      "grad_norm": 1.6128216981887817,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.5205,
+      "step": 36
+    },
+    {
+      "epoch": 0.0049447153354852,
+      "eval_loss": 0.6823018193244934,
+      "eval_runtime": 1386.5683,
+      "eval_samples_per_second": 4.422,
+      "eval_steps_per_second": 0.553,
+      "step": 36
+    },
+    {
+      "epoch": 0.005082068539248678,
+      "grad_norm": 2.30482816696167,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.4894,
+      "step": 37
+    },
+    {
+      "epoch": 0.005219421743012155,
+      "grad_norm": 4.286962985992432,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.6738,
+      "step": 38
+    },
+    {
+      "epoch": 0.0053567749467756335,
+      "grad_norm": 3.888533353805542,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.4983,
+      "step": 39
+    },
+    {
+      "epoch": 0.005494128150539112,
+      "grad_norm": 2.3330461978912354,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.4765,
+      "step": 40
+    },
+    {
+      "epoch": 0.005631481354302589,
+      "grad_norm": 4.286584377288818,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.7936,
+      "step": 41
+    },
+    {
+      "epoch": 0.005768834558066067,
+      "grad_norm": 3.957209587097168,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.7258,
+      "step": 42
+    },
+    {
+      "epoch": 0.005906187761829545,
+      "grad_norm": 5.282871723175049,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.5848,
+      "step": 43
+    },
+    {
+      "epoch": 0.006043540965593022,
+      "grad_norm": 2.5516767501831055,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.397,
+      "step": 44
+    },
+    {
+      "epoch": 0.0061808941693565,
+      "grad_norm": 2.4859097003936768,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.4567,
+      "step": 45
+    },
+    {
+      "epoch": 0.0061808941693565,
+      "eval_loss": 0.404715359210968,
+      "eval_runtime": 1387.0837,
+      "eval_samples_per_second": 4.42,
+      "eval_steps_per_second": 0.553,
+      "step": 45
+    },
+    {
+      "epoch": 0.006318247373119978,
+      "grad_norm": 2.7337472438812256,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.4548,
+      "step": 46
+    },
+    {
+      "epoch": 0.006455600576883456,
+      "grad_norm": 2.889204740524292,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.6571,
+      "step": 47
+    },
+    {
+      "epoch": 0.006592953780646934,
+      "grad_norm": 2.7503957748413086,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.3354,
+      "step": 48
+    },
+    {
+      "epoch": 0.006730306984410411,
+      "grad_norm": 2.1261167526245117,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.3084,
+      "step": 49
+    },
+    {
+      "epoch": 0.006867660188173889,
+      "grad_norm": 2.0925722122192383,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.3023,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -225,7 +424,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.415857563500544e+16,
+  "total_flos": 2.617690146471936e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null