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:f61e1526c035352db38b6528641d8ed9c655d44ae9e59834186a50225d85ef4e
+oid sha256:ea6a42ee5dcc4beae850b8d3b7cde163027e774103aef0f69362ccbef312630a
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b6e061807bd4326ec5b16288d8d241f294cf0cdf9f4437fa866c4cd85972c93
+oid sha256:b93c11740271aa8d278dd34106e30fcadfab5cbb3fece496b20cf6bac38cf7b3
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd1ebf454031a941c8766869644643e5857c05165f3942927e75947630136d9
+oid sha256:a518ffcf1704ed6bb871672d16e0ae98e928d067ab51aa37e7629c34ebaaa55a
 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": 1.865534782409668,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0061495887462525945,
+  "best_metric": 1.819774866104126,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.009224383119378891,
   "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": 10.261,
       "eval_steps_per_second": 5.13,
       "step": 20
+    },
+    {
+      "epoch": 0.0064570681835652245,
+      "grad_norm": 1.018054485321045,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.8903,
+      "step": 21
+    },
+    {
+      "epoch": 0.0073795064955031135,
+      "grad_norm": 0.8236993551254272,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.8529,
+      "step": 24
+    },
+    {
+      "epoch": 0.0076869859328157425,
+      "eval_loss": 1.8260083198547363,
+      "eval_runtime": 133.4963,
+      "eval_samples_per_second": 10.262,
+      "eval_steps_per_second": 5.131,
+      "step": 25
+    },
+    {
+      "epoch": 0.008301944807441002,
+      "grad_norm": 0.8157389163970947,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.8317,
+      "step": 27
+    },
+    {
+      "epoch": 0.009224383119378891,
+      "grad_norm": 1.0121748447418213,
+      "learning_rate": 0.0,
+      "loss": 1.7414,
+      "step": 30
+    },
+    {
+      "epoch": 0.009224383119378891,
+      "eval_loss": 1.819774866104126,
+      "eval_runtime": 133.5545,
+      "eval_samples_per_second": 10.258,
+      "eval_steps_per_second": 5.129,
+      "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": 2791603735363584.0,
+  "total_flos": 4170173481222144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null