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:c7744c374f681e13530b6386308493128eec8f78a92f50b2a1055c54323ac9e2
+oid sha256:e53c4f154a40cd37ea266c1eb4d1bb93ef2914ee4b2f1b010658cbac1c69004c
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b154c0f02fa060d8ee83237b60ad8ed974654d902d2a06462b0cf3db0160814
+oid sha256:0e04f772bad80b24cb8aa0203aa9b17a50050c059db2d6d9caa52b2bf5eb17e0
 size 180543866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:368358f58452bb4695adc76aefabfd8b6fc3bbff6cdd245c1d5a07066625b09e
+oid sha256:de4e50a6bbcf5bd9016d3fc9208330d6cf9fe6bdff9489249b7d4bfb6b1689f2
 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": 0.0022715398768825387,
+  "epoch": 0.0045430797537650775,
   "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": 30.274,
       "eval_steps_per_second": 15.137,
       "step": 25
+    },
+    {
+      "epoch": 0.00236240147195784,
+      "grad_norm": 0.2939962148666382,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.0027,
+      "step": 26
+    },
+    {
+      "epoch": 0.002453263067033142,
+      "grad_norm": 0.6323854923248291,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0051,
+      "step": 27
+    },
+    {
+      "epoch": 0.002544124662108443,
+      "grad_norm": 0.011483444832265377,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.0002,
+      "step": 28
+    },
+    {
+      "epoch": 0.002634986257183745,
+      "grad_norm": 0.028377123177051544,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.0002,
+      "step": 29
+    },
+    {
+      "epoch": 0.0027258478522590463,
+      "grad_norm": 0.0203834380954504,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0003,
+      "step": 30
+    },
+    {
+      "epoch": 0.002816709447334348,
+      "grad_norm": 9.312389373779297,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.4706,
+      "step": 31
+    },
+    {
+      "epoch": 0.0029075710424096494,
+      "grad_norm": 68.22864532470703,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 3.3187,
+      "step": 32
+    },
+    {
+      "epoch": 0.002998432637484951,
+      "grad_norm": 48.021480560302734,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 2.134,
+      "step": 33
+    },
+    {
+      "epoch": 0.0030892942325602525,
+      "grad_norm": 18.471052169799805,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 1.2329,
+      "step": 34
+    },
+    {
+      "epoch": 0.0031801558276355543,
+      "grad_norm": 16.42901039123535,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.4616,
+      "step": 35
+    },
+    {
+      "epoch": 0.0032710174227108557,
+      "grad_norm": 13.609719276428223,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.3694,
+      "step": 36
+    },
+    {
+      "epoch": 0.0033618790177861574,
+      "grad_norm": 2.441948652267456,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.043,
+      "step": 37
+    },
+    {
+      "epoch": 0.0034527406128614588,
+      "grad_norm": 0.41872337460517883,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0039,
+      "step": 38
+    },
+    {
+      "epoch": 0.00354360220793676,
+      "grad_norm": 0.22431544959545135,
+      "learning_rate": 5e-05,
+      "loss": 0.0019,
+      "step": 39
+    },
+    {
+      "epoch": 0.003634463803012062,
+      "grad_norm": 0.3925679624080658,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0035,
+      "step": 40
+    },
+    {
+      "epoch": 0.0037253253980873632,
+      "grad_norm": 0.04403270035982132,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0006,
+      "step": 41
+    },
+    {
+      "epoch": 0.003816186993162665,
+      "grad_norm": 0.034630876034498215,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0005,
+      "step": 42
+    },
+    {
+      "epoch": 0.003907048588237967,
+      "grad_norm": 0.46163317561149597,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0027,
+      "step": 43
+    },
+    {
+      "epoch": 0.003997910183313268,
+      "grad_norm": 0.06355968862771988,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0006,
+      "step": 44
+    },
+    {
+      "epoch": 0.0040887717783885695,
+      "grad_norm": 0.05269589275121689,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0005,
+      "step": 45
+    },
+    {
+      "epoch": 0.004179633373463871,
+      "grad_norm": 0.01986519619822502,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0002,
+      "step": 46
+    },
+    {
+      "epoch": 0.004270494968539173,
+      "grad_norm": 0.019215445965528488,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0002,
+      "step": 47
+    },
+    {
+      "epoch": 0.004361356563614474,
+      "grad_norm": 0.006207428406924009,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0001,
+      "step": 48
+    },
+    {
+      "epoch": 0.004452218158689776,
+      "grad_norm": 0.012795104645192623,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.0002,
+      "step": 49
+    },
+    {
+      "epoch": 0.0045430797537650775,
+      "grad_norm": 0.004560490138828754,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0001,
+      "step": 50
+    },
+    {
+      "epoch": 0.0045430797537650775,
+      "eval_loss": 2.606266498565674,
+      "eval_runtime": 305.9895,
+      "eval_samples_per_second": 30.289,
+      "eval_steps_per_second": 15.144,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4894017925939200.0,
+  "total_flos": 9788035851878400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null