Training in progress, step 151, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47d9a4a16fdc46bbc89f10c142edbc1e5936b4695667b90c838c25efe312e0c7
+oid sha256:a0540f2e663270d7b286adf364a4c5c89fc5048e95c951a845eed6f0ff29ea84
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56feeb9665ee04e9f2375c78123f291155a50d9e9fe263a4ee579e6d3373686f
+oid sha256:a8db9b0ba2385beafa45cd08c4cfef71f07e0c891e37249f4e660078960576ad
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200e1fbf02bb39ece07cfd621f3e0b4a5ed2afd2723f8d7313b94a6fd4c9bbb8
+oid sha256:9d8fe7d9ddafff804fb27f268ff5b42d441929f36c7969d48f1e18f0898463d2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed41efdd6283cc55a7eeb8c1b2afb10664f4494afd05738afd0d2d78da3d68f7
+oid sha256:7f5e2b7252ed14bf7b200301efea19c6da8009c4b85d61545d95c12430694780
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.9624110460281372,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 2.9850746268656714,
+  "epoch": 3.0049751243781095,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 151,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,13 @@
       "eval_samples_per_second": 13.367,
       "eval_steps_per_second": 3.46,
       "step": 150
+    },
+    {
+      "epoch": 3.0049751243781095,
+      "grad_norm": 7.453361511230469,
+      "learning_rate": 0.0,
+      "loss": 2.4948,
+      "step": 151
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1119,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.262770368118784e+17,
+  "total_flos": 2.2778555039062426e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null