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:f9f03266cca956dc5bd9e613d937d440a449c1626b7647818f5faf5a4de3ee81
+oid sha256:e96336799a9029ba656845bc357f3b24c3d8feb84dedc9d77148392a1c56cd2e
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307a7f989d5d7467fd297a9c192384b48623779490b40e90c255137a010da60b
+oid sha256:068f863d220442ed02af8b000db343ee844bf20ed5b622aa1f42649687775c70
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef3d0db0e6bea405a95d244a39a1875a8fe35574fb46f4c6d06a9d7908f278a
+oid sha256:ca19f5541917bb5f8305450dd3598f032bfb3457ad61b8c552b1bbe0b110d65f
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fac5bb42ffa69767eb666a3bee9bc4ee101c460bd2fda7f7adc7501b07fa5ca5
+oid sha256:520b637fb478811bded0c174b6e2f377e13bce36d9cf7b35cf36dc4d01117e13
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce88335b0a8e52b60bb77c9ea632ef862762cbbdddceea46fc3b4f2d63f7325b
+oid sha256:8e2021b2208cc858b1866f44f62dfb915c64de72597e8ccfb921be58f7e39e15
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e858609935e6bdb84cf7a682baaa42002a85386578c57b09776cf6ceaa780c2
+oid sha256:9d1e1b84d5cf477292cd0d30c1db194f9b12b442c4e64ac131185925a4b23b35
 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": 0.6559107899665833,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0335795836131632,
+  "best_metric": 0.6203262209892273,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0671591672263264,
   "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": 84.235,
       "eval_steps_per_second": 21.901,
       "step": 25
+    },
+    {
+      "epoch": 0.03492276695768973,
+      "grad_norm": 0.6402541399002075,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1511,
+      "step": 26
+    },
+    {
+      "epoch": 0.03626595030221625,
+      "grad_norm": 0.5437145233154297,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5757,
+      "step": 27
+    },
+    {
+      "epoch": 0.03760913364674278,
+      "grad_norm": 0.4473167061805725,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5216,
+      "step": 28
+    },
+    {
+      "epoch": 0.03895231699126931,
+      "grad_norm": 0.45289281010627747,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5476,
+      "step": 29
+    },
+    {
+      "epoch": 0.040295500335795834,
+      "grad_norm": 0.4508344233036041,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6536,
+      "step": 30
+    },
+    {
+      "epoch": 0.041638683680322364,
+      "grad_norm": 0.4123438000679016,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.625,
+      "step": 31
+    },
+    {
+      "epoch": 0.042981867024848894,
+      "grad_norm": 0.4256981313228607,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.6231,
+      "step": 32
+    },
+    {
+      "epoch": 0.04432505036937542,
+      "grad_norm": 0.43175458908081055,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.6893,
+      "step": 33
+    },
+    {
+      "epoch": 0.04566823371390195,
+      "grad_norm": 0.4677419066429138,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.6701,
+      "step": 34
+    },
+    {
+      "epoch": 0.04701141705842848,
+      "grad_norm": 0.6207624673843384,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.6548,
+      "step": 35
+    },
+    {
+      "epoch": 0.048354600402955,
+      "grad_norm": 0.6289758086204529,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.641,
+      "step": 36
+    },
+    {
+      "epoch": 0.04969778374748153,
+      "grad_norm": 0.810161828994751,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.7249,
+      "step": 37
+    },
+    {
+      "epoch": 0.05104096709200806,
+      "grad_norm": 0.5295881032943726,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.143,
+      "step": 38
+    },
+    {
+      "epoch": 0.052384150436534584,
+      "grad_norm": 0.37527188658714294,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.5272,
+      "step": 39
+    },
+    {
+      "epoch": 0.053727333781061114,
+      "grad_norm": 0.38970667123794556,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4768,
+      "step": 40
+    },
+    {
+      "epoch": 0.055070517125587644,
+      "grad_norm": 0.42394906282424927,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5588,
+      "step": 41
+    },
+    {
+      "epoch": 0.056413700470114174,
+      "grad_norm": 0.40651217103004456,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.5674,
+      "step": 42
+    },
+    {
+      "epoch": 0.0577568838146407,
+      "grad_norm": 0.4719997048377991,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6885,
+      "step": 43
+    },
+    {
+      "epoch": 0.05910006715916723,
+      "grad_norm": 0.45096564292907715,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6588,
+      "step": 44
+    },
+    {
+      "epoch": 0.06044325050369376,
+      "grad_norm": 0.48418763279914856,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6306,
+      "step": 45
+    },
+    {
+      "epoch": 0.06178643384822028,
+      "grad_norm": 0.44281038641929626,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6718,
+      "step": 46
+    },
+    {
+      "epoch": 0.0631296171927468,
+      "grad_norm": 0.46086570620536804,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6546,
+      "step": 47
+    },
+    {
+      "epoch": 0.06447280053727333,
+      "grad_norm": 0.4880565106868744,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.6342,
+      "step": 48
+    },
+    {
+      "epoch": 0.06581598388179986,
+      "grad_norm": 0.6008680462837219,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.619,
+      "step": 49
+    },
+    {
+      "epoch": 0.0671591672263264,
+      "grad_norm": 0.8862148523330688,
+      "learning_rate": 1e-05,
+      "loss": 0.6159,
+      "step": 50
+    },
+    {
+      "epoch": 0.0671591672263264,
+      "eval_loss": 0.6203262209892273,
+      "eval_runtime": 0.6215,
+      "eval_samples_per_second": 80.447,
+      "eval_steps_per_second": 20.916,
+      "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": 1.5558666870587392e+16,
+  "total_flos": 3.1071193041731584e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null