Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:825fba47ba538b74260e47597ac812ddcf29276fccc80a67e7f7bdd3e6f0a0b4
+oid sha256:02ef03e83c1b005f1906d2712177efb26c7b9f1633249ec6d975df5448fd692c
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:617fc0f5b7ea192c3f7c38dd9508194aa9300e50a3f10f069d82a4143cdca2bb
+oid sha256:ea13652adfc41e99e61456168b61db08c733e5b085f6d4fc6031891e6885aa53
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71cddd6c4ff643d7889f00bac1c58dd1b0b622d1a22609d3502d45129df9795c
+oid sha256:32b42ea309f9feac8cf9ba672b7df24cd3ed4d728e4a0768471488cf130d35a4
 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": 1.5499287843704224,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.09950248756218906,
+  "best_metric": 1.529019832611084,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.14925373134328357,
   "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": 18.216,
       "eval_steps_per_second": 9.215,
       "step": 20
+    },
+    {
+      "epoch": 0.1044776119402985,
+      "grad_norm": 1.0285145044326782,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.4911,
+      "step": 21
+    },
+    {
+      "epoch": 0.11940298507462686,
+      "grad_norm": 0.8856176733970642,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.5143,
+      "step": 24
+    },
+    {
+      "epoch": 0.12437810945273632,
+      "eval_loss": 1.5311452150344849,
+      "eval_runtime": 4.6651,
+      "eval_samples_per_second": 18.22,
+      "eval_steps_per_second": 9.217,
+      "step": 25
+    },
+    {
+      "epoch": 0.13432835820895522,
+      "grad_norm": 0.7971075773239136,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.542,
+      "step": 27
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "grad_norm": 0.8718319535255432,
+      "learning_rate": 0.0,
+      "loss": 1.4543,
+      "step": 30
+    },
+    {
+      "epoch": 0.14925373134328357,
+      "eval_loss": 1.529019832611084,
+      "eval_runtime": 4.6718,
+      "eval_samples_per_second": 18.194,
+      "eval_steps_per_second": 9.204,
+      "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": 6534582019031040.0,
+  "total_flos": 9801873028546560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null