Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:941c4f07da1ea170ccc363b09fc82de8797e9cc5a8ad2dfd342b9a682f9fede9
+oid sha256:61341ea83f2470873ca4ebb1145004e32106ce1b65f0b3a2303a70672914737b
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c709439d065ac1da67d95461ee6538d45172539c97fe03b6d682368e1dc97b77
+oid sha256:331db0bfeef9f40fe1ea15edaf1408b1e2d0eb20179e1919030d0be6e675dc77
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae341615e23f78ea0d9ec53f366f85dd01668aeaa6fa0024d702041da2ad7e77
+oid sha256:aaa1e2cd7802d7de0ca43660a1a852bdc77512f1304e615ca21d92d061acc315
 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": 2.063730001449585,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07640878701050621,
+  "best_metric": 2.0486373901367188,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.11461318051575932,
   "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": 2.528,
       "eval_steps_per_second": 0.641,
       "step": 20
+    },
+    {
+      "epoch": 0.08022922636103152,
+      "grad_norm": 0.13450752198696136,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.0838,
+      "step": 21
+    },
+    {
+      "epoch": 0.09169054441260745,
+      "grad_norm": 0.13830527663230896,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.08,
+      "step": 24
+    },
+    {
+      "epoch": 0.09551098376313276,
+      "eval_loss": 2.0513598918914795,
+      "eval_runtime": 87.4326,
+      "eval_samples_per_second": 2.528,
+      "eval_steps_per_second": 0.64,
+      "step": 25
+    },
+    {
+      "epoch": 0.10315186246418338,
+      "grad_norm": 0.14177772402763367,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.1142,
+      "step": 27
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "grad_norm": 0.15173637866973877,
+      "learning_rate": 0.0,
+      "loss": 2.0229,
+      "step": 30
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "eval_loss": 2.0486373901367188,
+      "eval_runtime": 87.4288,
+      "eval_samples_per_second": 2.528,
+      "eval_steps_per_second": 0.641,
+      "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": 5.0782317576192e+16,
+  "total_flos": 7.6173476364288e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null