Training in progress, step 61, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9adec3c4d4ce7c1a955666abbde366adcc406302669a947745d14914760d8325
+oid sha256:4ffbe3469f4c42c7cb866fdeb5184e8d9fb4c35780e3bc41d45d553b1570e41d
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a4abfc37dfb521100817cffdd7d23ed37eadaaea8e94bafc799d8d68a769f6f
+oid sha256:256227b4d757a5f6fad8a9b1c59bfed03c29ad2f52eab91882ba36184467d338
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9dece06a2a475795a147ee35c2a3453b2663869fb01988081543a009bb20250
+oid sha256:6d042cd41bcb8fc3e6cfb7aa84301cda4f043602a3a459c5d4b976a7332c110c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d45c96467833182ded638377a74d35c27bfc6d409c3a75a7ed9d96313f2209
+oid sha256:72c76386f38653d23653debdd7194fca0374345c66eb3b8c72b9036822ebc2d3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.21439266204834,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.8264462809917356,
+  "epoch": 1.0082644628099173,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 61,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,83 @@
       "eval_samples_per_second": 5.79,
       "eval_steps_per_second": 2.895,
       "step": 50
+    },
+    {
+      "epoch": 0.8429752066115702,
+      "grad_norm": 8.537187576293945,
+      "learning_rate": 7.157141191620548e-06,
+      "loss": 2.4486,
+      "step": 51
+    },
+    {
+      "epoch": 0.859504132231405,
+      "grad_norm": 7.167176723480225,
+      "learning_rate": 5.824397777698859e-06,
+      "loss": 2.2525,
+      "step": 52
+    },
+    {
+      "epoch": 0.8760330578512396,
+      "grad_norm": 7.074034690856934,
+      "learning_rate": 4.621229016452156e-06,
+      "loss": 2.1293,
+      "step": 53
+    },
+    {
+      "epoch": 0.8925619834710744,
+      "grad_norm": 5.562939643859863,
+      "learning_rate": 3.551164009160429e-06,
+      "loss": 1.3322,
+      "step": 54
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 7.1741414070129395,
+      "learning_rate": 2.6173414408598827e-06,
+      "loss": 1.8027,
+      "step": 55
+    },
+    {
+      "epoch": 0.9256198347107438,
+      "grad_norm": 7.7900896072387695,
+      "learning_rate": 1.8225003740388547e-06,
+      "loss": 1.8203,
+      "step": 56
+    },
+    {
+      "epoch": 0.9421487603305785,
+      "grad_norm": 7.23261022567749,
+      "learning_rate": 1.1689722144956671e-06,
+      "loss": 1.6585,
+      "step": 57
+    },
+    {
+      "epoch": 0.9586776859504132,
+      "grad_norm": 8.060309410095215,
+      "learning_rate": 6.58673872923693e-07,
+      "loss": 2.3596,
+      "step": 58
+    },
+    {
+      "epoch": 0.9752066115702479,
+      "grad_norm": 9.658180236816406,
+      "learning_rate": 2.9310214228202013e-07,
+      "loss": 2.2916,
+      "step": 59
+    },
+    {
+      "epoch": 0.9917355371900827,
+      "grad_norm": 11.173391342163086,
+      "learning_rate": 7.332930744380906e-08,
+      "loss": 2.2498,
+      "step": 60
+    },
+    {
+      "epoch": 1.0082644628099173,
+      "grad_norm": 10.068079948425293,
+      "learning_rate": 0.0,
+      "loss": 3.287,
+      "step": 61
     }
   ],
   "logging_steps": 1,
@@ -404,12 +481,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.83447180771328e+16,
+  "total_flos": 4.678055605410202e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null