Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e308a8c8dbbc25bf9329c28eb08de0dbbbeb892b0c5784844c57e32a79ce18b
+oid sha256:d0c596ffa37a5c0aae869697ed0c4258ed8be0ab2aa57cd53064475561c0445d
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2c65690b68f0b98badb69a3a84535250f5fd7301d7b515f61a130736ec5a150
+oid sha256:acb4e376cdb679f61fb8fba5960ea95731949456001255ff4d38c371f6a59a21
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f46aacd801ffed4bc2f191287788d54cf08d172c311342ac62a58e7e003b935c
+oid sha256:0c2d0b82ad8463d5a5ab97a8782881dcea7fd2c50422e4018cc66aa8f04c4ef6
 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": 1.5170910358428955,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.030959752321981424,
+  "best_metric": 1.5044535398483276,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.04643962848297214,
   "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": 5.694,
       "eval_steps_per_second": 1.431,
       "step": 20
+    },
+    {
+      "epoch": 0.032507739938080496,
+      "grad_norm": 1.0437849760055542,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 7.9916,
+      "step": 21
+    },
+    {
+      "epoch": 0.03715170278637771,
+      "grad_norm": 1.031005620956421,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 8.3096,
+      "step": 24
+    },
+    {
+      "epoch": 0.03869969040247678,
+      "eval_loss": 1.5103068351745605,
+      "eval_runtime": 96.2893,
+      "eval_samples_per_second": 5.66,
+      "eval_steps_per_second": 1.423,
+      "step": 25
+    },
+    {
+      "epoch": 0.04179566563467492,
+      "grad_norm": 1.2108943462371826,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 7.874,
+      "step": 27
+    },
+    {
+      "epoch": 0.04643962848297214,
+      "grad_norm": 1.2310171127319336,
+      "learning_rate": 0.0,
+      "loss": 8.7045,
+      "step": 30
+    },
+    {
+      "epoch": 0.04643962848297214,
+      "eval_loss": 1.5044535398483276,
+      "eval_runtime": 96.2779,
+      "eval_samples_per_second": 5.661,
+      "eval_steps_per_second": 1.423,
+      "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": 1.8460376203001856e+16,
+  "total_flos": 2.4995022646542336e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null