Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a316a602ffe058f14451b1db7142b2a19d5828f2c0844203b31a8f747716b165
+oid sha256:2a56c8dc710d9f29e16868b51bd961a7de1a36f29310a1637e2e82ed3fc47b85
 size 18064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2fbb1c81ab2509a4dc949c5fb9cc762278a199fe5a04aca2c5ece9b290b8153
+oid sha256:3d11ddfef92c94b87f0213162a6e3bdbc1fa097b9bc1c417dc5d323d7570ffed
 size 43578

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b144f7cb70aafc2e7b54f7a16659cc872d3061fb4e845c6cb04f1164d9a6048d
+oid sha256:553dcd59c778ca530dcc80ab66bd21953efec38b342a78fa029e7bb7063620bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a6da4479e4d6e904a1d1657795824ceae911abb9c58383db394b5c0579911a
+oid sha256:6a466a28b4a8a9c102025ce436fa94b7198b461eca0d4d66f86eed6792700b45
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.5,
   "best_model_checkpoint": "miner_id_24/checkpoint-500",
-  "epoch": 0.014698821154543405,
+  "epoch": 0.019598428206057873,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -249,6 +249,84 @@
       "eval_samples_per_second": 176.878,
       "eval_steps_per_second": 88.439,
       "step": 1500
+    },
+    {
+      "epoch": 0.015188781859694852,
+      "grad_norm": 0.0018345484277233481,
+      "learning_rate": 0.00015800569095711982,
+      "loss": 46.0,
+      "step": 1550
+    },
+    {
+      "epoch": 0.0156787425648463,
+      "grad_norm": 0.00938267633318901,
+      "learning_rate": 0.00015539200638661104,
+      "loss": 46.0,
+      "step": 1600
+    },
+    {
+      "epoch": 0.016168703269997746,
+      "grad_norm": 0.013782349415123463,
+      "learning_rate": 0.00015272254676105025,
+      "loss": 46.0,
+      "step": 1650
+    },
+    {
+      "epoch": 0.016658663975149195,
+      "grad_norm": 0.005259850528091192,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 46.0,
+      "step": 1700
+    },
+    {
+      "epoch": 0.01714862468030064,
+      "grad_norm": 0.007433369290083647,
+      "learning_rate": 0.0001472271074772683,
+      "loss": 46.0,
+      "step": 1750
+    },
+    {
+      "epoch": 0.017638585385452085,
+      "grad_norm": 0.003847072832286358,
+      "learning_rate": 0.00014440666126057744,
+      "loss": 46.0,
+      "step": 1800
+    },
+    {
+      "epoch": 0.018128546090603534,
+      "grad_norm": 0.0026508287992328405,
+      "learning_rate": 0.00014154150130018866,
+      "loss": 46.0,
+      "step": 1850
+    },
+    {
+      "epoch": 0.01861850679575498,
+      "grad_norm": 0.005416387226432562,
+      "learning_rate": 0.00013863451256931287,
+      "loss": 46.0,
+      "step": 1900
+    },
+    {
+      "epoch": 0.019108467500906428,
+      "grad_norm": 0.0011210152879357338,
+      "learning_rate": 0.00013568862215918717,
+      "loss": 46.0,
+      "step": 1950
+    },
+    {
+      "epoch": 0.019598428206057873,
+      "grad_norm": 0.004934302996844053,
+      "learning_rate": 0.00013270679633174218,
+      "loss": 46.0,
+      "step": 2000
+    },
+    {
+      "epoch": 0.019598428206057873,
+      "eval_loss": 11.5,
+      "eval_runtime": 239.7758,
+      "eval_samples_per_second": 179.201,
+      "eval_steps_per_second": 89.6,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -263,7 +341,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 2
+        "early_stopping_patience_counter": 3
       }
     },
     "TrainerControl": {
@@ -272,12 +350,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 30067558219776.0,
+  "total_flos": 40091744157696.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null