Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8001888663b3a762e1e077d6e0c04c2566f9678d2ca50bbb83da88f6474a70
+oid sha256:4cab650935c0482531612b6d928e48d9dae71f5b0cc6d335d35ecfe4d2e682fd
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7da845cda640c4b07e2beed04ca032a0d6a980bb12ef105bc1ce7ad5126445eb
+oid sha256:a23578b9d30499d14bd7284f3c7cc52614b791a0d9621c824b873601faa2d12f
 size 3108666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3035ebf7301b6dda2eedd90adafea5c079c473a1e2b75bde30bcba2baea1fc16
+oid sha256:d2dacbc91d0d50e41b049f70a84d5b45ce05c0358d13151fa9f001452bc37899
 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": 0.01938548027527382,
+  "epoch": 0.03877096055054764,
   "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": 62.467,
       "eval_steps_per_second": 31.233,
       "step": 25
+    },
+    {
+      "epoch": 0.020160899486284772,
+      "grad_norm": 15.573179244995117,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 6.3441,
+      "step": 26
+    },
+    {
+      "epoch": 0.020936318697295727,
+      "grad_norm": 15.074617385864258,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 6.2842,
+      "step": 27
+    },
+    {
+      "epoch": 0.021711737908306678,
+      "grad_norm": 15.864977836608887,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 5.7357,
+      "step": 28
+    },
+    {
+      "epoch": 0.02248715711931763,
+      "grad_norm": 19.382728576660156,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 6.0517,
+      "step": 29
+    },
+    {
+      "epoch": 0.023262576330328584,
+      "grad_norm": 18.489917755126953,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 5.7561,
+      "step": 30
+    },
+    {
+      "epoch": 0.024037995541339535,
+      "grad_norm": 11.977217674255371,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 5.3761,
+      "step": 31
+    },
+    {
+      "epoch": 0.02481341475235049,
+      "grad_norm": 12.359403610229492,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 5.6858,
+      "step": 32
+    },
+    {
+      "epoch": 0.02558883396336144,
+      "grad_norm": 17.48925018310547,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 5.4112,
+      "step": 33
+    },
+    {
+      "epoch": 0.026364253174372396,
+      "grad_norm": 12.810553550720215,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 5.1038,
+      "step": 34
+    },
+    {
+      "epoch": 0.027139672385383347,
+      "grad_norm": 11.41131591796875,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 5.1019,
+      "step": 35
+    },
+    {
+      "epoch": 0.0279150915963943,
+      "grad_norm": 11.404109001159668,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 5.0096,
+      "step": 36
+    },
+    {
+      "epoch": 0.028690510807405253,
+      "grad_norm": 10.934562683105469,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 4.8367,
+      "step": 37
+    },
+    {
+      "epoch": 0.029465930018416207,
+      "grad_norm": 11.160900115966797,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 5.009,
+      "step": 38
+    },
+    {
+      "epoch": 0.03024134922942716,
+      "grad_norm": 9.400223731994629,
+      "learning_rate": 5e-05,
+      "loss": 5.121,
+      "step": 39
+    },
+    {
+      "epoch": 0.031016768440438113,
+      "grad_norm": 9.578547477722168,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 4.9154,
+      "step": 40
+    },
+    {
+      "epoch": 0.03179218765144907,
+      "grad_norm": 8.08479118347168,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 4.4877,
+      "step": 41
+    },
+    {
+      "epoch": 0.03256760686246002,
+      "grad_norm": 9.323592185974121,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 4.7919,
+      "step": 42
+    },
+    {
+      "epoch": 0.03334302607347097,
+      "grad_norm": 12.592964172363281,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 4.9646,
+      "step": 43
+    },
+    {
+      "epoch": 0.03411844528448192,
+      "grad_norm": 8.313202857971191,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 4.5304,
+      "step": 44
+    },
+    {
+      "epoch": 0.03489386449549287,
+      "grad_norm": 9.623037338256836,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 4.5277,
+      "step": 45
+    },
+    {
+      "epoch": 0.03566928370650383,
+      "grad_norm": 6.551573753356934,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 4.7194,
+      "step": 46
+    },
+    {
+      "epoch": 0.03644470291751478,
+      "grad_norm": 9.742829322814941,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 4.4445,
+      "step": 47
+    },
+    {
+      "epoch": 0.03722012212852573,
+      "grad_norm": 6.696950435638428,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.3009,
+      "step": 48
+    },
+    {
+      "epoch": 0.037995541339536684,
+      "grad_norm": 6.955257415771484,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 4.2683,
+      "step": 49
+    },
+    {
+      "epoch": 0.03877096055054764,
+      "grad_norm": 11.268085479736328,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 4.3482,
+      "step": 50
+    },
+    {
+      "epoch": 0.03877096055054764,
+      "eval_loss": 4.515497207641602,
+      "eval_runtime": 17.341,
+      "eval_samples_per_second": 62.626,
+      "eval_steps_per_second": 31.313,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 14500862361600.0,
+  "total_flos": 29001724723200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null