Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fd98b116783dd2e2128b57f7754943e7c8c78af1a8c7737870d2430b059f158
+oid sha256:13e22c73d675bdc0112c87221c09c287b4790114f6f39f17e3f03b0ef058c0c7
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b03fc9ef7d2e5ec63f54ba8c56e82313d28b728558511fdc3ef093966f003d
+oid sha256:5b8ef8d854dfafe14bbba9b7b235da74939c6d0d3f23e74f81faa28e266d317a
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05c6c8fe118793e2efe5d50edd9a3cde907f8de2cd1ffd9277dcf906663b389d
+oid sha256:00404fd772de3bf824af71faa569d3b85ebefc2b36c4ae8d88a38282f1a6f2fa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.598429799079895,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.11732499022291748,
+  "best_metric": 0.579126238822937,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.15643332029722332,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,135 @@
       "eval_samples_per_second": 12.595,
       "eval_steps_per_second": 3.149,
       "step": 450
+    },
+    {
+      "epoch": 0.1199322122278712,
+      "grad_norm": 7.045400619506836,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 1.9138,
+      "step": 460
+    },
+    {
+      "epoch": 0.12253943423282493,
+      "grad_norm": 8.932710647583008,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 2.1108,
+      "step": 470
+    },
+    {
+      "epoch": 0.12514665623777865,
+      "grad_norm": 14.591238975524902,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 2.394,
+      "step": 480
+    },
+    {
+      "epoch": 0.12775387824273238,
+      "grad_norm": 11.373315811157227,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 2.4359,
+      "step": 490
+    },
+    {
+      "epoch": 0.1303611002476861,
+      "grad_norm": 18.106515884399414,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 2.9492,
+      "step": 500
+    },
+    {
+      "epoch": 0.1303611002476861,
+      "eval_loss": 0.5898227095603943,
+      "eval_runtime": 514.4469,
+      "eval_samples_per_second": 12.557,
+      "eval_steps_per_second": 3.139,
+      "step": 500
+    },
+    {
+      "epoch": 0.13296832225263983,
+      "grad_norm": 9.076396942138672,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 2.0251,
+      "step": 510
+    },
+    {
+      "epoch": 0.13557554425759352,
+      "grad_norm": 11.412988662719727,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 2.2448,
+      "step": 520
+    },
+    {
+      "epoch": 0.13818276626254725,
+      "grad_norm": 10.8418550491333,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 2.3559,
+      "step": 530
+    },
+    {
+      "epoch": 0.14078998826750097,
+      "grad_norm": 9.6925687789917,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 2.4988,
+      "step": 540
+    },
+    {
+      "epoch": 0.1433972102724547,
+      "grad_norm": 18.714468002319336,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 2.8972,
+      "step": 550
+    },
+    {
+      "epoch": 0.1433972102724547,
+      "eval_loss": 0.5796568989753723,
+      "eval_runtime": 514.4013,
+      "eval_samples_per_second": 12.558,
+      "eval_steps_per_second": 3.14,
+      "step": 550
+    },
+    {
+      "epoch": 0.14600443227740842,
+      "grad_norm": 8.010424613952637,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 1.7564,
+      "step": 560
+    },
+    {
+      "epoch": 0.14861165428236214,
+      "grad_norm": 8.445106506347656,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 2.0401,
+      "step": 570
+    },
+    {
+      "epoch": 0.15121887628731587,
+      "grad_norm": 10.118414878845215,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 2.3152,
+      "step": 580
+    },
+    {
+      "epoch": 0.1538260982922696,
+      "grad_norm": 11.436360359191895,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 2.4145,
+      "step": 590
+    },
+    {
+      "epoch": 0.15643332029722332,
+      "grad_norm": 14.37455940246582,
+      "learning_rate": 0.0,
+      "loss": 2.9678,
+      "step": 600
+    },
+    {
+      "epoch": 0.15643332029722332,
+      "eval_loss": 0.579126238822937,
+      "eval_runtime": 512.7083,
+      "eval_samples_per_second": 12.6,
+      "eval_steps_per_second": 3.15,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -425,12 +554,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.736589326437581e+17,
+  "total_flos": 8.982119101916774e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null