Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26718983bea015ad9bbde011a422f655fc8f61d8b0f42683a619d9a945f04fb8
+oid sha256:53bcb3dd4babc44bbdab31d435f4d49e92d5f5ed8c12da261dcc3e906c352463
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a68c2211cea34a2b7116f38bc1970b90f496a535851ddad8e8ee81d599fdaec
+oid sha256:9bcd209096a60687bd7e6009788c92c614d5c82102731d63dd4bcee0b96172a4
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6fa88e6d7fb6992492403e76ec5c0929a4a07662672923b98022b6a4c69f6a5
+oid sha256:462a0023e9c8d8f6d08b93741c609dc4d7e1ca89de3df4d71be6669e0223b8da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8825191855430603,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004564646810453041,
+  "best_metric": 0.8396795392036438,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.005705808513066302,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 4.563,
       "eval_steps_per_second": 2.283,
       "step": 20
+    },
+    {
+      "epoch": 0.004792879150975694,
+      "grad_norm": 2.500640869140625,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.5253,
+      "step": 21
+    },
+    {
+      "epoch": 0.0050211114914983455,
+      "grad_norm": 2.87005352973938,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.9051,
+      "step": 22
+    },
+    {
+      "epoch": 0.005249343832020997,
+      "grad_norm": 4.616143226623535,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.2478,
+      "step": 23
+    },
+    {
+      "epoch": 0.005477576172543649,
+      "grad_norm": 3.5486695766448975,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0517,
+      "step": 24
+    },
+    {
+      "epoch": 0.005705808513066302,
+      "grad_norm": 2.1593828201293945,
+      "learning_rate": 0.0,
+      "loss": 0.5063,
+      "step": 25
+    },
+    {
+      "epoch": 0.005705808513066302,
+      "eval_loss": 0.8396795392036438,
+      "eval_runtime": 403.6745,
+      "eval_samples_per_second": 4.571,
+      "eval_steps_per_second": 2.286,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6750909505732608.0,
+  "total_flos": 8415517329063936.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null