Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad26dfe3635e98ecebec7c3fc2fc9c78af4f2a1c2a730ddff7f3e0f34b7544aa
+oid sha256:e6130a92e72377b0fa368407fbe5af74e617d7866099b0bd43fc36227d053021
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:356595f70d56e9bba3501c44a53c991dd7e145886153da5c191b8ce5f4079ed5
+oid sha256:8c43978505433084a91f0d8b32ac27ee9b0839a21962c8fd6e0ee06a6fc4f04e
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e308ed925c617da46a4ea3336123b6650481a462e9f3c8b139347f263e68e262
+oid sha256:5ddbc6ef9ee9c53b95887edb13f85a4a261b7dc302ce9113dc1139c25fb70c73
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39918f03969339950f01b35b86c4ebcc997e20fe5cc5982a4934d4618e39105
+oid sha256:df4d803f5c11f09708eaffc40171d0800d5b2de68ac6ea9a400270bbfe0f771f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5f35a3528346f7fd76143e5334dcfc6c86a4c47cc736983ae6073dff945271
+oid sha256:622a7380e9ba19a0ee59ae1825ab45e47bce64b5a9b5814c6d6eeff8c47f42bb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7683ee62bd57fc23f1a0026beed100e43bf40d1f79229a261b46986c0c6f5e
+oid sha256:92795ac8cd299b4e592764b1f0d9456b03edff7f01e8522ccd6781a9363eae9e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.622530996799469,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4925373134328357,
+  "best_metric": 0.46879878640174866,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.9850746268656714,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 51.839,
       "eval_steps_per_second": 13.478,
       "step": 25
+    },
+    {
+      "epoch": 1.5522388059701493,
+      "grad_norm": 1.2284759283065796,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.6242,
+      "step": 26
+    },
+    {
+      "epoch": 1.6119402985074627,
+      "grad_norm": 1.1227284669876099,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5985,
+      "step": 27
+    },
+    {
+      "epoch": 1.671641791044776,
+      "grad_norm": 1.330870509147644,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.563,
+      "step": 28
+    },
+    {
+      "epoch": 1.7313432835820897,
+      "grad_norm": 1.2725169658660889,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.6058,
+      "step": 29
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "grad_norm": 0.9444494247436523,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.5344,
+      "step": 30
+    },
+    {
+      "epoch": 1.8507462686567164,
+      "grad_norm": 1.003670573234558,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5498,
+      "step": 31
+    },
+    {
+      "epoch": 1.9104477611940298,
+      "grad_norm": 0.9227081537246704,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.4844,
+      "step": 32
+    },
+    {
+      "epoch": 1.9701492537313432,
+      "grad_norm": 0.98988276720047,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.5589,
+      "step": 33
+    },
+    {
+      "epoch": 2.029850746268657,
+      "grad_norm": 1.2500901222229004,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.5848,
+      "step": 34
+    },
+    {
+      "epoch": 2.08955223880597,
+      "grad_norm": 1.1457059383392334,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5207,
+      "step": 35
+    },
+    {
+      "epoch": 2.1492537313432836,
+      "grad_norm": 1.111443281173706,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4604,
+      "step": 36
+    },
+    {
+      "epoch": 2.208955223880597,
+      "grad_norm": 1.067543625831604,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.4344,
+      "step": 37
+    },
+    {
+      "epoch": 2.2686567164179103,
+      "grad_norm": 0.8861973881721497,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4895,
+      "step": 38
+    },
+    {
+      "epoch": 2.328358208955224,
+      "grad_norm": 0.9545814394950867,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4499,
+      "step": 39
+    },
+    {
+      "epoch": 2.388059701492537,
+      "grad_norm": 1.0408685207366943,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4442,
+      "step": 40
+    },
+    {
+      "epoch": 2.4477611940298507,
+      "grad_norm": 1.24673593044281,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.469,
+      "step": 41
+    },
+    {
+      "epoch": 2.5074626865671643,
+      "grad_norm": 0.9520359635353088,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4764,
+      "step": 42
+    },
+    {
+      "epoch": 2.5671641791044775,
+      "grad_norm": 0.8973754644393921,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4698,
+      "step": 43
+    },
+    {
+      "epoch": 2.626865671641791,
+      "grad_norm": 0.9955081343650818,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4454,
+      "step": 44
+    },
+    {
+      "epoch": 2.6865671641791042,
+      "grad_norm": 1.2142070531845093,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4314,
+      "step": 45
+    },
+    {
+      "epoch": 2.746268656716418,
+      "grad_norm": 1.1162165403366089,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4658,
+      "step": 46
+    },
+    {
+      "epoch": 2.8059701492537314,
+      "grad_norm": 1.1647312641143799,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4592,
+      "step": 47
+    },
+    {
+      "epoch": 2.8656716417910446,
+      "grad_norm": 0.9554238319396973,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4353,
+      "step": 48
+    },
+    {
+      "epoch": 2.925373134328358,
+      "grad_norm": 0.9301491379737854,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.445,
+      "step": 49
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "grad_norm": 0.990142285823822,
+      "learning_rate": 1e-05,
+      "loss": 0.5118,
+      "step": 50
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "eval_loss": 0.46879878640174866,
+      "eval_runtime": 0.9571,
+      "eval_samples_per_second": 52.242,
+      "eval_steps_per_second": 13.583,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null