Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f91a032091b4d44d60bb0e09eb86f9d305f9365256cbdf069a77d1b7cfcaa95
+oid sha256:2c1792e16999d20aab7c7f3147de13f2f2744a71aa4369a0ff55883d494181e4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d592ae1b646b7d407d98d03dc5e76455a2198a6440aa75c55be4c11c27328d76
+oid sha256:8c1c49f99d095521a72089fd929683f6a057d9cc2a6a525e29dafa17d1a3263a
 size 42546196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d04fa6ba62e6d2693994357040d1f8b0df1a2292ac61d59108919d588e97608
+oid sha256:3a1c514f7fd02541ee711c621db702524520ab84a034f9ac00217461e361da06
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:829afd908950b55f19acd29cd95ce4b7eeb6e3a96dff858cc79db502814ed864
+oid sha256:0fce62aa16b9baa5f49dced04db0ff1567e194dc4daa50ed8d0d1098cd28a3b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08980054825597883,
+  "epoch": 0.09452689290103035,
   "eval_steps": 1000,
-  "global_step": 475,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2857,13 +2857,163 @@
       "learning_rate": 1.129032258064516e-05,
       "loss": 1.5357,
       "step": 475
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.0887096774193549e-05,
+      "loss": 1.7497,
+      "step": 476
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.0483870967741936e-05,
+      "loss": 1.4821,
+      "step": 477
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.0080645161290323e-05,
+      "loss": 1.5097,
+      "step": 478
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.67741935483871e-06,
+      "loss": 1.5417,
+      "step": 479
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.274193548387097e-06,
+      "loss": 1.715,
+      "step": 480
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.870967741935484e-06,
+      "loss": 1.5074,
+      "step": 481
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.46774193548387e-06,
+      "loss": 1.9941,
+      "step": 482
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 8.064516129032258e-06,
+      "loss": 1.4365,
+      "step": 483
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.661290322580646e-06,
+      "loss": 1.6494,
+      "step": 484
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.258064516129033e-06,
+      "loss": 1.3565,
+      "step": 485
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.854838709677419e-06,
+      "loss": 1.7097,
+      "step": 486
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.451612903225806e-06,
+      "loss": 1.5873,
+      "step": 487
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 6.048387096774194e-06,
+      "loss": 1.3527,
+      "step": 488
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.64516129032258e-06,
+      "loss": 1.5721,
+      "step": 489
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 5.241935483870968e-06,
+      "loss": 1.6132,
+      "step": 490
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 1.8699,
+      "step": 491
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.435483870967742e-06,
+      "loss": 1.5994,
+      "step": 492
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.032258064516129e-06,
+      "loss": 1.5774,
+      "step": 493
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.6290322580645166e-06,
+      "loss": 1.7266,
+      "step": 494
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.225806451612903e-06,
+      "loss": 1.4401,
+      "step": 495
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.82258064516129e-06,
+      "loss": 1.6521,
+      "step": 496
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.4193548387096776e-06,
+      "loss": 1.5495,
+      "step": 497
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 2.0161290322580646e-06,
+      "loss": 1.7499,
+      "step": 498
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.6129032258064516e-06,
+      "loss": 1.393,
+      "step": 499
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.2096774193548388e-06,
+      "loss": 1.5208,
+      "step": 500
     }
   ],
   "logging_steps": 1,
   "max_steps": 501,
   "num_train_epochs": 1,
   "save_steps": 25,
-  "total_flos": 2.920625653658419e+16,
+  "total_flos": 3.0694656581369856e+16,
   "trial_name": null,
   "trial_params": null
 }