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:aa9a0384b7e8dadb9ca8646b4c4c4f3804523ee6ca3fd756ed763ace6c9e7647
+oid sha256:528fd98e795f6be9b1ea3fb24c098952b92bc3494e0bbf923fbfcbbbabcdb423
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4533734fb17aa23a9d3aa707151d1b58287388f4ec4ca9d7e8d619bf7c1fc61c
+oid sha256:4df5e982c31c1c59b7c3578e260a75233a325f98cd13b484c70ef465926190b7
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87186703aed64a28f7aa092aa66ac4cff9ccd6f164d6515ce692fb3a15c4760e
+oid sha256:f7a008e4416221a92675c1aa1d6ef4a2ecef81cd840382268d055b69f64f070b
 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": 0.9407100677490234,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.019975031210986267,
+  "best_metric": 0.9329267144203186,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0299625468164794,
   "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": 8.471,
       "eval_steps_per_second": 4.235,
       "step": 20
+    },
+    {
+      "epoch": 0.020973782771535582,
+      "grad_norm": 0.4452764391899109,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 0.9141,
+      "step": 21
+    },
+    {
+      "epoch": 0.02397003745318352,
+      "grad_norm": 0.5386295318603516,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 0.9,
+      "step": 24
+    },
+    {
+      "epoch": 0.024968789013732832,
+      "eval_loss": 0.9346191883087158,
+      "eval_runtime": 49.834,
+      "eval_samples_per_second": 8.468,
+      "eval_steps_per_second": 4.234,
+      "step": 25
+    },
+    {
+      "epoch": 0.02696629213483146,
+      "grad_norm": 0.48347967863082886,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.96,
+      "step": 27
+    },
+    {
+      "epoch": 0.0299625468164794,
+      "grad_norm": 0.4335913062095642,
+      "learning_rate": 0.0,
+      "loss": 0.9135,
+      "step": 30
+    },
+    {
+      "epoch": 0.0299625468164794,
+      "eval_loss": 0.9329267144203186,
+      "eval_runtime": 49.8408,
+      "eval_samples_per_second": 8.467,
+      "eval_steps_per_second": 4.233,
+      "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": 3292692008140800.0,
+  "total_flos": 4939038012211200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null