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:b633684d7579a77afb791dfbc139d29cee20918a87d13ca8662bc790acb0e77c
+oid sha256:b31b1c699a5be0798de10025623a2257c4e3260daff022371a809dc7ca7119ff
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cc53f044518d7d217d67007c67cfd833ee6ed6e29502aca9c9d5e678791e3a2
+oid sha256:523859b346936df7630c31d71b887650a03feb14243bcac649921e6e21db673b
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75eda932a4623a5dd8cf25c973b0b0302ff8a9661199f74bde6560ed19fad39f
+oid sha256:a58906bfc344f5588d893728646e3e25d8c990a5a9fba359c5b1a7d901b3fe48
 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": 2.6764070987701416,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.03532008830022075,
+  "best_metric": 2.654357671737671,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.052980132450331126,
   "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": 114.297,
       "eval_steps_per_second": 57.387,
       "step": 20
+    },
+    {
+      "epoch": 0.03708609271523179,
+      "grad_norm": 5.1042585372924805,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 11.472,
+      "step": 21
+    },
+    {
+      "epoch": 0.0423841059602649,
+      "grad_norm": 4.660117149353027,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.8366,
+      "step": 24
+    },
+    {
+      "epoch": 0.04415011037527594,
+      "eval_loss": 2.6581664085388184,
+      "eval_runtime": 2.0873,
+      "eval_samples_per_second": 114.502,
+      "eval_steps_per_second": 57.491,
+      "step": 25
+    },
+    {
+      "epoch": 0.04768211920529802,
+      "grad_norm": 5.66838264465332,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.8062,
+      "step": 27
+    },
+    {
+      "epoch": 0.052980132450331126,
+      "grad_norm": 4.661335468292236,
+      "learning_rate": 0.0,
+      "loss": 10.8666,
+      "step": 30
+    },
+    {
+      "epoch": 0.052980132450331126,
+      "eval_loss": 2.654357671737671,
+      "eval_runtime": 2.0842,
+      "eval_samples_per_second": 114.674,
+      "eval_steps_per_second": 57.577,
+      "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": 86222642872320.0,
+  "total_flos": 132567313416192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null