Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2366ce080617dce353b20eedfcf4555d6b0654c17873d89492c41aedc6c31182
+oid sha256:2edb08fa94ef8c5b291e82605a3368cb3be0907524c48dc07390bab31335f73c
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0584a7abf68d4422d3ab5521845446b6e811f7ddcc2d427cad60c5cce5b2730
+oid sha256:5396837c7ba58603303ccd4ab4c0fee83fcfae7c4ccb5ff52937488de9536f2f
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2050bb97e91833e69533b5233c1b5cc861d26fa35f8ee79758756c1768e10e52
+oid sha256:340c1d087dc617eaaaf0949ab96a0275c260c5c8b33bf7b90ad7e3a02b7b8ee2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfbc15885001cdb94156289411aa0b2685bf6076188764edffc86a9c7ebff5f2
+oid sha256:f21f3ce3e2193aa6f5ad3f7d81b399f3c87af6404db934f7458693a5f8f89559
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e48406bf43eef96e781db0f543fb412e377b71f14f4a6385ffaa7edbc50db0e0
+oid sha256:c432922a8507a3ec3fd642425f21702c68e7643268f6c90328020bb9c3c5ea56
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd27d6def98cf39ce346a854182141e64ef667926c05eb8de6763ba69d11fcd
+oid sha256:1c774ef863c8731d84b9f50aa392e1c5ed44d3459914110a75c3f376d276bb0e
 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": 0.44637736678123474,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02430281305061061,
+  "best_metric": 0.2565852403640747,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04860562610122122,
   "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": 14.766,
       "eval_steps_per_second": 3.839,
       "step": 25
+    },
+    {
+      "epoch": 0.025274925572635033,
+      "grad_norm": 2.274613380432129,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4278,
+      "step": 26
+    },
+    {
+      "epoch": 0.026247038094659458,
+      "grad_norm": 2.005136489868164,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3865,
+      "step": 27
+    },
+    {
+      "epoch": 0.027219150616683882,
+      "grad_norm": 1.3703882694244385,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.3564,
+      "step": 28
+    },
+    {
+      "epoch": 0.028191263138708306,
+      "grad_norm": 2.662112236022949,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4548,
+      "step": 29
+    },
+    {
+      "epoch": 0.02916337566073273,
+      "grad_norm": 1.5636816024780273,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.3732,
+      "step": 30
+    },
+    {
+      "epoch": 0.030135488182757155,
+      "grad_norm": 0.8259252309799194,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.3298,
+      "step": 31
+    },
+    {
+      "epoch": 0.03110760070478158,
+      "grad_norm": 1.1385399103164673,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.36,
+      "step": 32
+    },
+    {
+      "epoch": 0.032079713226806,
+      "grad_norm": 1.2352774143218994,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.3025,
+      "step": 33
+    },
+    {
+      "epoch": 0.03305182574883043,
+      "grad_norm": 1.3201019763946533,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.3255,
+      "step": 34
+    },
+    {
+      "epoch": 0.03402393827085485,
+      "grad_norm": 2.216609239578247,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3294,
+      "step": 35
+    },
+    {
+      "epoch": 0.03499605079287928,
+      "grad_norm": 1.7982845306396484,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.2809,
+      "step": 36
+    },
+    {
+      "epoch": 0.0359681633149037,
+      "grad_norm": 2.063532829284668,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3373,
+      "step": 37
+    },
+    {
+      "epoch": 0.036940275836928126,
+      "grad_norm": 2.5849380493164062,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.4325,
+      "step": 38
+    },
+    {
+      "epoch": 0.037912388358952546,
+      "grad_norm": 1.5866343975067139,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3466,
+      "step": 39
+    },
+    {
+      "epoch": 0.038884500880976974,
+      "grad_norm": 1.0172760486602783,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.2981,
+      "step": 40
+    },
+    {
+      "epoch": 0.039856613403001395,
+      "grad_norm": 1.2064744234085083,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.2807,
+      "step": 41
+    },
+    {
+      "epoch": 0.04082872592502582,
+      "grad_norm": 1.1969460248947144,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3194,
+      "step": 42
+    },
+    {
+      "epoch": 0.041800838447050244,
+      "grad_norm": 1.2646105289459229,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.2595,
+      "step": 43
+    },
+    {
+      "epoch": 0.04277295096907467,
+      "grad_norm": 1.483519434928894,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.241,
+      "step": 44
+    },
+    {
+      "epoch": 0.04374506349109909,
+      "grad_norm": 1.630673885345459,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.2726,
+      "step": 45
+    },
+    {
+      "epoch": 0.04471717601312352,
+      "grad_norm": 1.378562331199646,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.2539,
+      "step": 46
+    },
+    {
+      "epoch": 0.04568928853514794,
+      "grad_norm": 1.6784262657165527,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2285,
+      "step": 47
+    },
+    {
+      "epoch": 0.04666140105717237,
+      "grad_norm": 1.9682538509368896,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.2745,
+      "step": 48
+    },
+    {
+      "epoch": 0.04763351357919679,
+      "grad_norm": 2.4254722595214844,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.32,
+      "step": 49
+    },
+    {
+      "epoch": 0.04860562610122122,
+      "grad_norm": 2.277864456176758,
+      "learning_rate": 1e-05,
+      "loss": 0.3111,
+      "step": 50
+    },
+    {
+      "epoch": 0.04860562610122122,
+      "eval_loss": 0.2565852403640747,
+      "eval_runtime": 3.4031,
+      "eval_samples_per_second": 14.693,
+      "eval_steps_per_second": 3.82,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null