Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f24291ec77eb4e2b3542182381e0644ab86760511b78ae8c56e86f9cdc33304
+oid sha256:9fb9fab4ed1812721c369bb6971738cb629426f4ab194657fa52c63520ad95e9
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fffe180fc7661732e439c0f6aa08315bbede0dc997ba0be6a382f7fafa505dd
+oid sha256:5d112535ccb863c4ccd5136b78fcc86970fd9d01d32253c4077abfcbbfc416cc
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
+oid sha256:c70a576494e56c909be11c04fa488ebbe191aee3195b0dd47c32f36094b31b77
 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": 2.5085737705230713,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.014275517487508922,
+  "best_metric": 2.4624974727630615,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.017844396859386154,
   "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": 5.464,
       "eval_steps_per_second": 2.732,
       "step": 20
+    },
+    {
+      "epoch": 0.014989293361884369,
+      "grad_norm": 4.717961311340332,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 2.228,
+      "step": 21
+    },
+    {
+      "epoch": 0.015703069236259814,
+      "grad_norm": 3.9442169666290283,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.1003,
+      "step": 22
+    },
+    {
+      "epoch": 0.01641684511063526,
+      "grad_norm": 3.9127326011657715,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 2.3318,
+      "step": 23
+    },
+    {
+      "epoch": 0.017130620985010708,
+      "grad_norm": 4.625472068786621,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 2.1449,
+      "step": 24
+    },
+    {
+      "epoch": 0.017844396859386154,
+      "grad_norm": 4.23487663269043,
+      "learning_rate": 0.0,
+      "loss": 2.3897,
+      "step": 25
+    },
+    {
+      "epoch": 0.017844396859386154,
+      "eval_loss": 2.4624974727630615,
+      "eval_runtime": 108.8764,
+      "eval_samples_per_second": 5.419,
+      "eval_steps_per_second": 2.709,
+      "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": 3699128496291840.0,
+  "total_flos": 4623910620364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null