Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a6429f76c5712a339224f9bff5e24eefb6c32a5376e9f5ffc44a4527181937
+oid sha256:54695b0ef988984532d206ca03ec72e21bc98bef9e61fa86e88e8e7663a1cdd7
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24e2018f0042549f021947aade5b5c09dcac429d363450e2b5c826ee21bde453
+oid sha256:db06f6872a73482033ff66e6edcf642da7032c4531b85a3e767046a0fbea1d40
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ba55cf8fc9c596bbf0ccf5a62d093b0efdc097e069de0f3b26e1e163b85441
+oid sha256:1411f2253e4e305d691ef6f97907d86e42545036b1050b5f6187605655a22a6e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e207ea4c000b041ccf9040c77162b355dc2bf3b39dcce9d50d49743a27e5bcd0
+oid sha256:fc5598ab16ac6c752ff894733b1bcfd832314a9cf84bfd629d1867e5d5b6e380
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f9ef0b9f3d2c316e2b75466457490f5eb8e255cf5a5b77d2e3d2956f306caf2
+oid sha256:07f8fbf18c7823b14b2b4eb51f47155aa0c70f6f9c21639d56f5e388c84682b0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29da797529ec459579ecaaf1e576cd3a54c67c83fef9dcad7acacf71f41d9c8
+oid sha256:e02be7df605b308ce2f09f5d1531c7cbe1623b6a9f6caf653640166ce809e550
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.053691275167785234,
+  "epoch": 0.10738255033557047,
   "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": 24.838,
       "eval_steps_per_second": 6.458,
       "step": 25
+    },
+    {
+      "epoch": 0.05583892617449664,
+      "grad_norm": 0.0,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.05798657718120805,
+      "grad_norm": 0.0,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.06013422818791946,
+      "grad_norm": 0.0,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.06228187919463087,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.06442953020134229,
+      "grad_norm": 0.0,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.06657718120805368,
+      "grad_norm": 0.0,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.0687248322147651,
+      "grad_norm": 17.758140563964844,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.9235,
+      "step": 32
+    },
+    {
+      "epoch": 0.0708724832214765,
+      "grad_norm": 18.05216407775879,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.9561,
+      "step": 33
+    },
+    {
+      "epoch": 0.07302013422818791,
+      "grad_norm": 12.09702205657959,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.6542,
+      "step": 34
+    },
+    {
+      "epoch": 0.07516778523489932,
+      "grad_norm": 8.332193374633789,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.2896,
+      "step": 35
+    },
+    {
+      "epoch": 0.07731543624161073,
+      "grad_norm": 7.144294261932373,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.7258,
+      "step": 36
+    },
+    {
+      "epoch": 0.07946308724832214,
+      "grad_norm": 6.225759029388428,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.7284,
+      "step": 37
+    },
+    {
+      "epoch": 0.08161073825503355,
+      "grad_norm": 5.70999002456665,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.4476,
+      "step": 38
+    },
+    {
+      "epoch": 0.08375838926174496,
+      "grad_norm": 0.0,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.08590604026845637,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.08805369127516778,
+      "grad_norm": 13.675680160522461,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.8872,
+      "step": 41
+    },
+    {
+      "epoch": 0.09020134228187919,
+      "grad_norm": 0.0,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.0923489932885906,
+      "grad_norm": 0.0,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.09449664429530201,
+      "grad_norm": 19.001270294189453,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0711,
+      "step": 44
+    },
+    {
+      "epoch": 0.09664429530201342,
+      "grad_norm": 5.015544414520264,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.7845,
+      "step": 45
+    },
+    {
+      "epoch": 0.09879194630872483,
+      "grad_norm": 14.717562675476074,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.2785,
+      "step": 46
+    },
+    {
+      "epoch": 0.10093959731543624,
+      "grad_norm": 11.277101516723633,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.848,
+      "step": 47
+    },
+    {
+      "epoch": 0.10308724832214765,
+      "grad_norm": 6.0920562744140625,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8882,
+      "step": 48
+    },
+    {
+      "epoch": 0.10523489932885906,
+      "grad_norm": 5.014962673187256,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.2657,
+      "step": 49
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 3.8420026302337646,
+      "learning_rate": 1e-05,
+      "loss": 1.5918,
+      "step": 50
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "eval_loss": NaN,
+      "eval_runtime": 1.9967,
+      "eval_samples_per_second": 25.041,
+      "eval_steps_per_second": 6.511,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null