Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2198bd63ce22d1bee78e8b0726ff33789702d55e4a389ae45f51316d96ebddea
+oid sha256:c0986325ea1c5c460beff3285a6a2f3f125e10fb81836250c30092528d4f2d8d
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4809d25ac465e972fadbc4353708a55f83d40fbb243ad60366c1f6daddaf0f92
+oid sha256:d231a443b9d73e92002bf421b8cc6956e752e44ef2d552566d729685f547be12
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce1e30bd9509e9199681f68992f14fdd35bbbf918bf8e849708b029e2ad2b814
+oid sha256:69215dc437ba0774e513b22ff2c6f064769602ae7e1bcb0abf9e1b7e3fd5723a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:942b5ff7287677b91638274d1028c992391a13b65b1ab49c65397e9ce5d61e2d
+oid sha256:959248c2df8dbba7280aed94da8330aed5a1ed9fcdba240219a85a8e445c3ea4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd94b61c50ba41b47a28112d98e53d2e942d97c2d31a1612b5855aa533f3ded3
+oid sha256:2a590c297830fb9cd7e05e7e0842d94dd06c1e1f55e4b4a1a99a2a92c3bc4090
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddee1acee9201c14e42213c2f7e7aff3e4c7fc51891f488dbe6e2b7af919920a
+oid sha256:abe5e18cf77062e5e0000f33839ac51a079d47907ec992ae20606f1620bcea2b
 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": 0.40978458523750305,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.022559995488000903,
+  "epoch": 0.045119990976001806,
   "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": 24.73,
       "eval_steps_per_second": 6.43,
       "step": 25
+    },
+    {
+      "epoch": 0.02346239530752094,
+      "grad_norm": 1.0264705419540405,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4211,
+      "step": 26
+    },
+    {
+      "epoch": 0.024364795127040973,
+      "grad_norm": 1.0953011512756348,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.4428,
+      "step": 27
+    },
+    {
+      "epoch": 0.02526719494656101,
+      "grad_norm": 1.0392162799835205,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4432,
+      "step": 28
+    },
+    {
+      "epoch": 0.026169594766081047,
+      "grad_norm": 1.050638198852539,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4315,
+      "step": 29
+    },
+    {
+      "epoch": 0.027071994585601084,
+      "grad_norm": 1.119185447692871,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4856,
+      "step": 30
+    },
+    {
+      "epoch": 0.02797439440512112,
+      "grad_norm": 1.1340469121932983,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4083,
+      "step": 31
+    },
+    {
+      "epoch": 0.028876794224641154,
+      "grad_norm": 1.2006741762161255,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.4851,
+      "step": 32
+    },
+    {
+      "epoch": 0.02977919404416119,
+      "grad_norm": 1.2338976860046387,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4353,
+      "step": 33
+    },
+    {
+      "epoch": 0.030681593863681227,
+      "grad_norm": 1.0770245790481567,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4629,
+      "step": 34
+    },
+    {
+      "epoch": 0.031583993683201264,
+      "grad_norm": 1.1007499694824219,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4546,
+      "step": 35
+    },
+    {
+      "epoch": 0.0324863935027213,
+      "grad_norm": 1.0557769536972046,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3652,
+      "step": 36
+    },
+    {
+      "epoch": 0.03338879332224134,
+      "grad_norm": 1.2306406497955322,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.421,
+      "step": 37
+    },
+    {
+      "epoch": 0.03429119314176137,
+      "grad_norm": 1.1832939386367798,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3665,
+      "step": 38
+    },
+    {
+      "epoch": 0.035193592961281404,
+      "grad_norm": 1.4779810905456543,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4152,
+      "step": 39
+    },
+    {
+      "epoch": 0.036095992780801445,
+      "grad_norm": 1.2904037237167358,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4003,
+      "step": 40
+    },
+    {
+      "epoch": 0.03699839260032148,
+      "grad_norm": 1.4843233823776245,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4327,
+      "step": 41
+    },
+    {
+      "epoch": 0.03790079241984152,
+      "grad_norm": 1.0545917749404907,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4702,
+      "step": 42
+    },
+    {
+      "epoch": 0.03880319223936155,
+      "grad_norm": 1.0966724157333374,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4913,
+      "step": 43
+    },
+    {
+      "epoch": 0.039705592058881585,
+      "grad_norm": 0.8971771597862244,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3396,
+      "step": 44
+    },
+    {
+      "epoch": 0.040607991878401625,
+      "grad_norm": 1.0624101161956787,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.4207,
+      "step": 45
+    },
+    {
+      "epoch": 0.04151039169792166,
+      "grad_norm": 1.1375459432601929,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3894,
+      "step": 46
+    },
+    {
+      "epoch": 0.0424127915174417,
+      "grad_norm": 1.0266802310943604,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3847,
+      "step": 47
+    },
+    {
+      "epoch": 0.04331519133696173,
+      "grad_norm": 1.5598934888839722,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4377,
+      "step": 48
+    },
+    {
+      "epoch": 0.044217591156481766,
+      "grad_norm": 1.8163098096847534,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3741,
+      "step": 49
+    },
+    {
+      "epoch": 0.045119990976001806,
+      "grad_norm": 1.3753440380096436,
+      "learning_rate": 1e-05,
+      "loss": 0.4274,
+      "step": 50
+    },
+    {
+      "epoch": 0.045119990976001806,
+      "eval_loss": 0.429287314414978,
+      "eval_runtime": 2.0683,
+      "eval_samples_per_second": 24.175,
+      "eval_steps_per_second": 6.285,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null