Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09505c25550333885133c94c3605c650daa21e690743c88e0015fccae6c91bd2
+oid sha256:8ab39b3a629250289c7d14fc70ba8b115d1cb62c3d10dba2fbbef7ccc8b5ba9c
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4d2e7c38161a2e1c7f2660cd991626140cb8a128622dacf42fb61706c0fe7a9
+oid sha256:022d12665e01147730ea4ef77e779f6624af12adc851eacb66ee302656f7d339
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efbaca5a41d6eb7ddf5ffcdaadbefc90141ba0339ef8e68e464b674133adc821
+oid sha256:9ff4d56c5742d3d05eab3025f7ff1647ceed8a0f737889b02abf846daa5f25ed
 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": 10.379438400268555,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0005646009330030418,
+  "best_metric": 10.379171371459961,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0008469013995045627,
   "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": 199.47,
       "eval_steps_per_second": 99.742,
       "step": 20
+    },
+    {
+      "epoch": 0.0005928309796531939,
+      "grad_norm": 0.04127081111073494,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.3795,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006775211196036502,
+      "grad_norm": 0.03377717733383179,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.38,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007057511662538022,
+      "eval_loss": 10.379210472106934,
+      "eval_runtime": 74.469,
+      "eval_samples_per_second": 200.285,
+      "eval_steps_per_second": 100.149,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007622112595541064,
+      "grad_norm": 0.03797104209661484,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 10.3793,
+      "step": 27
+    },
+    {
+      "epoch": 0.0008469013995045627,
+      "grad_norm": 0.035392846912145615,
+      "learning_rate": 0.0,
+      "loss": 10.3804,
+      "step": 30
+    },
+    {
+      "epoch": 0.0008469013995045627,
+      "eval_loss": 10.379171371459961,
+      "eval_runtime": 74.1932,
+      "eval_samples_per_second": 201.029,
+      "eval_steps_per_second": 100.521,
+      "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": 529562271744.0,
+  "total_flos": 791074504704.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null