Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57ce59ea9f9f2d08d079939678b119647278e7102d7d2ccaba645d31d5025ea5
+oid sha256:d7f0a4561a482ec0c80f18f1258516c2fcd0682b4a3223a8b595dac37c1b02df
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ae957cab8b6592b95bef8baae7ad1e392b861436bf36e0bcc19b825f3ded3c
+oid sha256:336339fd0b3d94b37525a10f2fcbd5b4a30cc88e584c62b2a0484160c601bfe2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4e3a6bc13c78d0b7f7a4c3643c313c460487768781ba0a74ec4bb0e88ffcc0
+oid sha256:d797c380856a6852d2af134518fd713385e8ff3ac396d3bc2fac979dc0323627
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abd3b8dee739e144693a38b45d34a8e12145739e065de714acf2ea3f06107891
+oid sha256:8d00bfb7fb18b67e4ff31e1cbe35c52bc9bb931dfd60dd8086904fbdc6888cbd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784bb47ffa3469f420dafc952075139ddac81ddfea99ab83634b2c86140fcd5f
+oid sha256:c8bf010ef4219699e18196b83284b352aec4571e3822606e6dbae5ad295a1148
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b98bccd169aefcf51ab2bf40cd9af8ffa1f82a75896b2f5271c3403518f299
+oid sha256:35ce3c14c5feae901fc7641ce67b710befe5a1d0d501844da7b5dfe9d62ddbf0
 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": 1.3769758939743042,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005629996622002027,
+  "best_metric": 1.260650873184204,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.011259993244004054,
   "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": 16.601,
       "eval_steps_per_second": 4.316,
       "step": 25
+    },
+    {
+      "epoch": 0.0058551964868821076,
+      "grad_norm": 1.5193920135498047,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.4401,
+      "step": 26
+    },
+    {
+      "epoch": 0.006080396351762189,
+      "grad_norm": 1.2190526723861694,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.3128,
+      "step": 27
+    },
+    {
+      "epoch": 0.00630559621664227,
+      "grad_norm": 1.185204029083252,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.346,
+      "step": 28
+    },
+    {
+      "epoch": 0.006530796081522351,
+      "grad_norm": 0.9483022689819336,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3156,
+      "step": 29
+    },
+    {
+      "epoch": 0.006755995946402432,
+      "grad_norm": 1.055773377418518,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.2951,
+      "step": 30
+    },
+    {
+      "epoch": 0.006981195811282513,
+      "grad_norm": 0.8046019673347473,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.1903,
+      "step": 31
+    },
+    {
+      "epoch": 0.007206395676162595,
+      "grad_norm": 0.9744685888290405,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.272,
+      "step": 32
+    },
+    {
+      "epoch": 0.007431595541042675,
+      "grad_norm": 0.9115360975265503,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3022,
+      "step": 33
+    },
+    {
+      "epoch": 0.0076567954059227564,
+      "grad_norm": 1.0355730056762695,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.3344,
+      "step": 34
+    },
+    {
+      "epoch": 0.007881995270802838,
+      "grad_norm": 1.0381739139556885,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.3516,
+      "step": 35
+    },
+    {
+      "epoch": 0.008107195135682919,
+      "grad_norm": 1.140064001083374,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.4159,
+      "step": 36
+    },
+    {
+      "epoch": 0.008332395000563,
+      "grad_norm": 1.489823579788208,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.489,
+      "step": 37
+    },
+    {
+      "epoch": 0.00855759486544308,
+      "grad_norm": 0.9764193296432495,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.2021,
+      "step": 38
+    },
+    {
+      "epoch": 0.008782794730323161,
+      "grad_norm": 1.035754919052124,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.2263,
+      "step": 39
+    },
+    {
+      "epoch": 0.009007994595203243,
+      "grad_norm": 1.046346664428711,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.292,
+      "step": 40
+    },
+    {
+      "epoch": 0.009233194460083324,
+      "grad_norm": 0.8970901966094971,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3079,
+      "step": 41
+    },
+    {
+      "epoch": 0.009458394324963405,
+      "grad_norm": 0.7692161798477173,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3526,
+      "step": 42
+    },
+    {
+      "epoch": 0.009683594189843487,
+      "grad_norm": 0.7230208516120911,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.3218,
+      "step": 43
+    },
+    {
+      "epoch": 0.009908794054723568,
+      "grad_norm": 0.7119923233985901,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2683,
+      "step": 44
+    },
+    {
+      "epoch": 0.010133993919603648,
+      "grad_norm": 0.7796542644500732,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.3427,
+      "step": 45
+    },
+    {
+      "epoch": 0.010359193784483729,
+      "grad_norm": 0.7200309038162231,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2604,
+      "step": 46
+    },
+    {
+      "epoch": 0.01058439364936381,
+      "grad_norm": 0.9918878674507141,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.3989,
+      "step": 47
+    },
+    {
+      "epoch": 0.010809593514243892,
+      "grad_norm": 1.0034048557281494,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.4172,
+      "step": 48
+    },
+    {
+      "epoch": 0.011034793379123973,
+      "grad_norm": 1.2579437494277954,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4476,
+      "step": 49
+    },
+    {
+      "epoch": 0.011259993244004054,
+      "grad_norm": 1.7536529302597046,
+      "learning_rate": 1e-05,
+      "loss": 1.4892,
+      "step": 50
+    },
+    {
+      "epoch": 0.011259993244004054,
+      "eval_loss": 1.260650873184204,
+      "eval_runtime": 3.0632,
+      "eval_samples_per_second": 16.323,
+      "eval_steps_per_second": 4.244,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null