Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e91a23d75cde761f8e83ffc9be8939f470bc1765ce4439d251739d1d8482f61
+oid sha256:12b4d79ae937d123a263577dae87e6401371fe74d3188def3fb0343b46f3519a
 size 216151256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ecf375fc53fdeaf9604af192bce4dff1007b8a240b8769f0694e978cd1dad3c
+oid sha256:1ea2790d347072dde0686c590eb5cb4c21b24486ad4823825ab97265b127958e
 size 432640054

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61a9610fee0be2146ffa242be1991271935b97a4c536cdff7a1c268535db8f9a
+oid sha256:6f113ae3bdce3b38074d66477cea113c7ea8d0168d2ea7f08affeba60137612b
 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": 2.664445400238037,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.006502479070145493,
+  "best_metric": 2.6063930988311768,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.00975371860521824,
   "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": 11.307,
       "eval_steps_per_second": 2.828,
       "step": 20
+    },
+    {
+      "epoch": 0.006827603023652768,
+      "grad_norm": 1.208409309387207,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 2.3119,
+      "step": 21
+    },
+    {
+      "epoch": 0.007802974884174592,
+      "grad_norm": 1.367969274520874,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.3106,
+      "step": 24
+    },
+    {
+      "epoch": 0.008128098837681867,
+      "eval_loss": 2.616642951965332,
+      "eval_runtime": 228.6629,
+      "eval_samples_per_second": 11.331,
+      "eval_steps_per_second": 2.834,
+      "step": 25
+    },
+    {
+      "epoch": 0.008778346744696415,
+      "grad_norm": 1.717703104019165,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.3972,
+      "step": 27
+    },
+    {
+      "epoch": 0.00975371860521824,
+      "grad_norm": 1.9316027164459229,
+      "learning_rate": 0.0,
+      "loss": 2.2749,
+      "step": 30
+    },
+    {
+      "epoch": 0.00975371860521824,
+      "eval_loss": 2.6063930988311768,
+      "eval_runtime": 228.8831,
+      "eval_samples_per_second": 11.32,
+      "eval_steps_per_second": 2.831,
+      "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": 1.647225084051456e+16,
+  "total_flos": 2.470837626077184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null