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:c7f6e8ce994cf1365fd768b01d4613dcc69b8d5db5c1d58faaa6189d2c3a7f54
+oid sha256:72c194210596d9909b393b9440bdc2b59bd71838ba8172691d5b934489964d9f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f83022dc507644fb4a9581467c3878dfd0196a296df606b31e35197c933e986f
+oid sha256:18a2b82be96b655b5d2a4c291ea748cf7d72193e2dbd86ba8e3d0e04394e19b6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b7ae4b206ae92b4259ffb923ef5da00009f3a53022d502c33431fc61393e52
+oid sha256:94c2d3812be27769760c128d1a37b0a3a72fc8d203008340efd54791fc22bbaf
 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": 0.5281378626823425,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0028609233630154133,
+  "best_metric": 0.5252118110656738,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0035761542037692664,
   "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": 4.545,
       "eval_steps_per_second": 2.272,
       "step": 20
+    },
+    {
+      "epoch": 0.003003969531166184,
+      "grad_norm": 0.6019684076309204,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.7293,
+      "step": 21
+    },
+    {
+      "epoch": 0.0031470156993169546,
+      "grad_norm": 0.4782317280769348,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.543,
+      "step": 22
+    },
+    {
+      "epoch": 0.003290061867467725,
+      "grad_norm": 0.45275384187698364,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.4797,
+      "step": 23
+    },
+    {
+      "epoch": 0.003433108035618496,
+      "grad_norm": 0.4921511709690094,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.5538,
+      "step": 24
+    },
+    {
+      "epoch": 0.0035761542037692664,
+      "grad_norm": 0.47665825486183167,
+      "learning_rate": 0.0,
+      "loss": 0.5019,
+      "step": 25
+    },
+    {
+      "epoch": 0.0035761542037692664,
+      "eval_loss": 0.5252118110656738,
+      "eval_runtime": 651.125,
+      "eval_samples_per_second": 4.521,
+      "eval_steps_per_second": 2.261,
+      "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": 6427235762307072.0,
+  "total_flos": 7999365373231104.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null