Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7283322875ebde2e780fc92240332f4478132d8f624cbf3d574a4babecbea28a
+oid sha256:1b2e8646d23770a53e06b60bdd6e13600b45d6b0d1b27e64c10daba920a94438
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebc9f2167e244f1988eeae9f027f0c4aa9eaff98f29013ec5d01f8a35d73e47b
+oid sha256:c3b056c887b0791808a8e81bf59001d985142abdd482d46034fd5921ba6eaf98
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d0fa38e22d21582135676388d187556a32884b386e232991735dbba6c0730ab
+oid sha256:b5f049c612d8105d513198029fc94d9f0a9ff603c13814ba380f8517ad0deaeb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5553081035614014,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.015479876160990712,
+  "best_metric": 1.547580361366272,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02321981424148607,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 15.133,
       "eval_steps_per_second": 7.581,
       "step": 20
+    },
+    {
+      "epoch": 0.016253869969040248,
+      "grad_norm": 0.8542360067367554,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.7232,
+      "step": 21
+    },
+    {
+      "epoch": 0.018575851393188854,
+      "grad_norm": 0.7060607075691223,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.4711,
+      "step": 24
+    },
+    {
+      "epoch": 0.01934984520123839,
+      "eval_loss": 1.5487457513809204,
+      "eval_runtime": 35.9901,
+      "eval_samples_per_second": 15.143,
+      "eval_steps_per_second": 7.585,
+      "step": 25
+    },
+    {
+      "epoch": 0.02089783281733746,
+      "grad_norm": 0.7153496742248535,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.6556,
+      "step": 27
+    },
+    {
+      "epoch": 0.02321981424148607,
+      "grad_norm": 0.8175066113471985,
+      "learning_rate": 0.0,
+      "loss": 1.2415,
+      "step": 30
+    },
+    {
+      "epoch": 0.02321981424148607,
+      "eval_loss": 1.547580361366272,
+      "eval_runtime": 36.0882,
+      "eval_samples_per_second": 15.102,
+      "eval_steps_per_second": 7.565,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9366326954950656.0,
+  "total_flos": 1.3724914745868288e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null