Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02bb7dd2abcede5ab7500d0508bd9aa0da01849724408e45dc13559d34c20ae0
+oid sha256:6449d869a889422bd45e490658479cac07bbac74e192cf35619200772b822312
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abfc628f08061df746ffa349d656be449c3b4d4b69b2b877abae9d790e337d3f
+oid sha256:641b226c4bdb10a1f194faca483fbfad08534eb22188c410e2912fbb38e11c16
 size 800394282

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405f85fd04f376f3f96ec6f0c189e085eed28eb6503fcdc8320a8aa6c97ff96a
+oid sha256:40e7b25842a40c68c62230743f873fcd5131561f7e91ed4137fa3f9f0aeff4fc
 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": 0.022878059940517045,
+  "epoch": 0.04575611988103409,
   "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": 7.777,
       "eval_steps_per_second": 3.893,
       "step": 25
+    },
+    {
+      "epoch": 0.023793182338137726,
+      "grad_norm": 1.1200025081634521,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.0118,
+      "step": 26
+    },
+    {
+      "epoch": 0.024708304735758406,
+      "grad_norm": 0.16598665714263916,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0009,
+      "step": 27
+    },
+    {
+      "epoch": 0.02562342713337909,
+      "grad_norm": 0.7957071661949158,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.0073,
+      "step": 28
+    },
+    {
+      "epoch": 0.02653854953099977,
+      "grad_norm": 3.8172872066497803,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.1607,
+      "step": 29
+    },
+    {
+      "epoch": 0.027453671928620454,
+      "grad_norm": 1.0546435117721558,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0068,
+      "step": 30
+    },
+    {
+      "epoch": 0.028368794326241134,
+      "grad_norm": 4.415338039398193,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0483,
+      "step": 31
+    },
+    {
+      "epoch": 0.029283916723861818,
+      "grad_norm": 0.23499952256679535,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.001,
+      "step": 32
+    },
+    {
+      "epoch": 0.030199039121482498,
+      "grad_norm": 0.0032876424957066774,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.03111416151910318,
+      "grad_norm": 0.0020302478224039078,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.03202928391672386,
+      "grad_norm": 0.0020431417506188154,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.032944406314344546,
+      "grad_norm": 0.34559494256973267,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0002,
+      "step": 36
+    },
+    {
+      "epoch": 0.03385952871196522,
+      "grad_norm": 0.14722956717014313,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0004,
+      "step": 37
+    },
+    {
+      "epoch": 0.034774651109585906,
+      "grad_norm": 0.0014910429017618299,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.03568977350720659,
+      "grad_norm": 0.0005584294558502734,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.036604895904827274,
+      "grad_norm": 0.0006086250650696456,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.03752001830244795,
+      "grad_norm": 0.0006442245212383568,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.038435140700068635,
+      "grad_norm": 0.0002517640241421759,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.03935026309768932,
+      "grad_norm": 0.00027328028227202594,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.040265385495309995,
+      "grad_norm": 0.0007536720368079841,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.04118050789293068,
+      "grad_norm": 0.0002211566607002169,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.04209563029055136,
+      "grad_norm": 0.012777777388691902,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0001,
+      "step": 46
+    },
+    {
+      "epoch": 0.043010752688172046,
+      "grad_norm": 0.0013763984898105264,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.04392587508579272,
+      "grad_norm": 0.20022982358932495,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0012,
+      "step": 48
+    },
+    {
+      "epoch": 0.04484099748341341,
+      "grad_norm": 0.0004175468347966671,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.04575611988103409,
+      "grad_norm": 9.72150664892979e-05,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.04575611988103409,
+      "eval_loss": 0.28562989830970764,
+      "eval_runtime": 118.4097,
+      "eval_samples_per_second": 7.778,
+      "eval_steps_per_second": 3.893,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.85904975806464e+16,
+  "total_flos": 7.71809951612928e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null