Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e67a7e65ea622d81520677dbc23bd2e467ae70ec78c8d37bd86ca1440303b55
+oid sha256:e5104d2ff845d76df05fd20874245a42bcf5cf57c54c6f4c9db77504f470c840
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e94f01074dd04fa664ae9a0cddc80ccea7a605293cbc7b4a636c18b7c6483a3
+oid sha256:aaa3b89eb829a76e62157bcb3dd26adcf55f7d48f96c5412488f2bc2dd4315eb
 size 501028338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f6d708ab0b9719cb7283087c16cb31213a902632f59739f4a613a13d5deced
+oid sha256:0991582830d7e41ad37db0df8d8635eacf70147ad63f5c31e3baf68e5782df77
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.201594352722168,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0005730043333452709,
+  "best_metric": 1.17819082736969,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0008595065000179064,
   "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": 5.15,
       "eval_steps_per_second": 2.575,
       "step": 20
+    },
+    {
+      "epoch": 0.0006016545500125345,
+      "grad_norm": 0.6407626867294312,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 1.1543,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006876052000143251,
+      "grad_norm": 0.579468846321106,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 1.1352,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007162554166815887,
+      "eval_loss": 1.1811610460281372,
+      "eval_runtime": 2854.1127,
+      "eval_samples_per_second": 5.149,
+      "eval_steps_per_second": 2.575,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007735558500161158,
+      "grad_norm": 0.5746999382972717,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.1843,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008595065000179064,
+      "grad_norm": 0.655366837978363,
+      "learning_rate": 0.0,
+      "loss": 1.1799,
+      "step": 30
+    },
+    {
+      "epoch": 0.0008595065000179064,
+      "eval_loss": 1.17819082736969,
+      "eval_runtime": 2854.4994,
+      "eval_samples_per_second": 5.149,
+      "eval_steps_per_second": 2.575,
+      "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": 1.2695579394048e+16,
+  "total_flos": 1.9043369091072e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null