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:f9f835d24cb00816e8a086d177287160e396774c9b37403b34a85381d40a93f2
+oid sha256:50d5a40416c4a2260df9db3fffae8e508c6354936b995d40c3125e5093a8d5e5
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecaa21f1908f496764ff2f5df3d1649db68d112bc9c757c2eec67b6744818eca
+oid sha256:fc404682ca939e77c8e6562eb04430a369971bacb941a139f11c8d50895f4f4f
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00232e97a2ee007008a7027c0bc814ccd78a98292311c559a14218c779acf1c8
+oid sha256:07dd1512a79888eacbcce2601f625cc6db154ee830f37557fc0d8f4ba3fb4525
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6230759024620056,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004349906477010744,
+  "best_metric": 0.6011509895324707,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.008699812954021488,
   "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": 50.886,
       "eval_steps_per_second": 6.361,
       "step": 25
+    },
+    {
+      "epoch": 0.004523902736091174,
+      "grad_norm": 0.31274470686912537,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.6096,
+      "step": 26
+    },
+    {
+      "epoch": 0.004697898995171604,
+      "grad_norm": 0.32117345929145813,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.6286,
+      "step": 27
+    },
+    {
+      "epoch": 0.004871895254252034,
+      "grad_norm": 0.32933807373046875,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.5944,
+      "step": 28
+    },
+    {
+      "epoch": 0.005045891513332464,
+      "grad_norm": 0.351071298122406,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.5933,
+      "step": 29
+    },
+    {
+      "epoch": 0.0052198877724128935,
+      "grad_norm": 0.31884631514549255,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.6248,
+      "step": 30
+    },
+    {
+      "epoch": 0.0053938840314933225,
+      "grad_norm": 0.34024742245674133,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.6292,
+      "step": 31
+    },
+    {
+      "epoch": 0.0055678802905737524,
+      "grad_norm": 0.3358078896999359,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.6344,
+      "step": 32
+    },
+    {
+      "epoch": 0.005741876549654182,
+      "grad_norm": 0.31253138184547424,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.5386,
+      "step": 33
+    },
+    {
+      "epoch": 0.005915872808734612,
+      "grad_norm": 0.3540220856666565,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.6591,
+      "step": 34
+    },
+    {
+      "epoch": 0.006089869067815042,
+      "grad_norm": 0.3631910979747772,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6059,
+      "step": 35
+    },
+    {
+      "epoch": 0.006263865326895472,
+      "grad_norm": 0.355940580368042,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.6156,
+      "step": 36
+    },
+    {
+      "epoch": 0.006437861585975902,
+      "grad_norm": 0.427781879901886,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.7358,
+      "step": 37
+    },
+    {
+      "epoch": 0.006611857845056331,
+      "grad_norm": 0.3944018483161926,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.6576,
+      "step": 38
+    },
+    {
+      "epoch": 0.006785854104136761,
+      "grad_norm": 0.38060876727104187,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.5713,
+      "step": 39
+    },
+    {
+      "epoch": 0.006959850363217191,
+      "grad_norm": 0.427198201417923,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.6833,
+      "step": 40
+    },
+    {
+      "epoch": 0.007133846622297621,
+      "grad_norm": 0.4212252199649811,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.6029,
+      "step": 41
+    },
+    {
+      "epoch": 0.0073078428813780506,
+      "grad_norm": 0.45848748087882996,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.6784,
+      "step": 42
+    },
+    {
+      "epoch": 0.0074818391404584805,
+      "grad_norm": 0.4559570848941803,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.6133,
+      "step": 43
+    },
+    {
+      "epoch": 0.0076558353995389095,
+      "grad_norm": 0.4943748712539673,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.5837,
+      "step": 44
+    },
+    {
+      "epoch": 0.00782983165861934,
+      "grad_norm": 0.5308108925819397,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.6114,
+      "step": 45
+    },
+    {
+      "epoch": 0.00800382791769977,
+      "grad_norm": 0.5437849760055542,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.5849,
+      "step": 46
+    },
+    {
+      "epoch": 0.0081778241767802,
+      "grad_norm": 0.5877715349197388,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.6909,
+      "step": 47
+    },
+    {
+      "epoch": 0.008351820435860628,
+      "grad_norm": 0.5954829454421997,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.634,
+      "step": 48
+    },
+    {
+      "epoch": 0.008525816694941058,
+      "grad_norm": 0.6944670081138611,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.6864,
+      "step": 49
+    },
+    {
+      "epoch": 0.008699812954021488,
+      "grad_norm": 1.0665466785430908,
+      "learning_rate": 0.0,
+      "loss": 0.7594,
+      "step": 50
+    },
+    {
+      "epoch": 0.008699812954021488,
+      "eval_loss": 0.6011509895324707,
+      "eval_runtime": 190.2616,
+      "eval_samples_per_second": 50.877,
+      "eval_steps_per_second": 6.36,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5817093618401280.0,
+  "total_flos": 9218902751969280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null