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:d179173b8b86c0280169091fa294be67889254a7ee7217c16fa770b42dcbb4fa
+oid sha256:cce19a5ea5aa06a5a36dc08e1963e182b012817857e3c3f2bf82419e9f7255e3
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c314b0ed63621905bcd96bfba5d03e2fcd37bf51a89d00e800664d267771db8e
+oid sha256:6fcc3e1b6862f805e7dce7971e982c82b4ceaa93dd8f169c8d743de947e3037b
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a2c2ba0f305db719678c78486795724b46909ee00886fad69e61ec505fddb09
+oid sha256:09a0ddb5acac6866ad72a7cfcfc172558946662257fe4858ac75678d83cd7a15
 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": 1.1754357814788818,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0007406241610116926,
+  "best_metric": 1.1388864517211914,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.001110936241517539,
   "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": 51.894,
       "eval_steps_per_second": 25.949,
       "step": 20
+    },
+    {
+      "epoch": 0.0007776553690622772,
+      "grad_norm": 1.2544924020767212,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.1061,
+      "step": 21
+    },
+    {
+      "epoch": 0.0008887489932140312,
+      "grad_norm": 1.6223948001861572,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.1773,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009257802012646157,
+      "eval_loss": 1.1445308923721313,
+      "eval_runtime": 222.9199,
+      "eval_samples_per_second": 51.009,
+      "eval_steps_per_second": 25.507,
+      "step": 25
+    },
+    {
+      "epoch": 0.000999842617365785,
+      "grad_norm": 1.3915208578109741,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.092,
+      "step": 27
+    },
+    {
+      "epoch": 0.001110936241517539,
+      "grad_norm": 1.7029190063476562,
+      "learning_rate": 0.0,
+      "loss": 1.1993,
+      "step": 30
+    },
+    {
+      "epoch": 0.001110936241517539,
+      "eval_loss": 1.1388864517211914,
+      "eval_runtime": 219.2161,
+      "eval_samples_per_second": 51.871,
+      "eval_steps_per_second": 25.938,
+      "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": 360477150412800.0,
+  "total_flos": 540715725619200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null