Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ffa6825cd70cb72e63574f7409c22ed0ead2562ca31d16ec70d23be266ed33e
+oid sha256:6ad32a635c8dae304e62fa860d23ebe995d1c4da1db959caa523089cf3a0078f
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa4f2956b3a05aaa80054a31aa9ec4c6e67028f19680649aa1b54b4105a3953
+oid sha256:ba80fbbcca41072c6841f342597f900ee79ee5f905458665221fe39faf74dbd8
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0254cf785e654c94a145e8bbdbf28f81ca917d3434a419a3e41617ce8a883488
+oid sha256:53bc105f641f221bb360e468ad5aa940b7c04d0a3ca0638ebb32d944f58db229
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8518651f873961c61b0300738b2eebb0db47d92dc0f10c186c58d3dad7272cc
+oid sha256:59a3d72580db31dd72e5e3a10c3d238dc07a5d18a770ca613409094a3da67a7b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18a4eb7ae3c879a40d9800828946120c1cd9495d80fc29d21ad036b44f674ba8
+oid sha256:23eb659617e78eabc9bc625ad8009fbbbcc0978dfbbc57609d87409407fa65bc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0ca2b5dafca3842a04584419ba6bc451b3c0a136035a18c86056bbd6e4c884
+oid sha256:350d14782066e8c11dae14dc1ccd725bf9d8875a3241e1e0ad350c86b250a484
 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": 1.4864065647125244,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009694854455997479,
+  "best_metric": 1.4502235651016235,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.019389708911994957,
   "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": 11.197,
       "eval_steps_per_second": 2.911,
       "step": 25
+    },
+    {
+      "epoch": 0.01008264863423738,
+      "grad_norm": 0.20189368724822998,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.4917,
+      "step": 26
+    },
+    {
+      "epoch": 0.010470442812477278,
+      "grad_norm": 0.10461372137069702,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.3872,
+      "step": 27
+    },
+    {
+      "epoch": 0.010858236990717177,
+      "grad_norm": 0.11615948379039764,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.3038,
+      "step": 28
+    },
+    {
+      "epoch": 0.011246031168957076,
+      "grad_norm": 0.14780248701572418,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3648,
+      "step": 29
+    },
+    {
+      "epoch": 0.011633825347196975,
+      "grad_norm": 0.18061505258083344,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.3164,
+      "step": 30
+    },
+    {
+      "epoch": 0.012021619525436874,
+      "grad_norm": 0.21259558200836182,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.4564,
+      "step": 31
+    },
+    {
+      "epoch": 0.012409413703676774,
+      "grad_norm": 0.36559170484542847,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.4106,
+      "step": 32
+    },
+    {
+      "epoch": 0.012797207881916673,
+      "grad_norm": 0.3270193636417389,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.4455,
+      "step": 33
+    },
+    {
+      "epoch": 0.013185002060156572,
+      "grad_norm": 0.3807890713214874,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.5706,
+      "step": 34
+    },
+    {
+      "epoch": 0.01357279623839647,
+      "grad_norm": 0.3821859359741211,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.4421,
+      "step": 35
+    },
+    {
+      "epoch": 0.01396059041663637,
+      "grad_norm": 0.4539583921432495,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.6156,
+      "step": 36
+    },
+    {
+      "epoch": 0.01434838459487627,
+      "grad_norm": 0.6784036755561829,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.4239,
+      "step": 37
+    },
+    {
+      "epoch": 0.014736178773116169,
+      "grad_norm": 0.3025074899196625,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.8353,
+      "step": 38
+    },
+    {
+      "epoch": 0.015123972951356068,
+      "grad_norm": 0.09835308790206909,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.1303,
+      "step": 39
+    },
+    {
+      "epoch": 0.015511767129595967,
+      "grad_norm": 0.10119763016700745,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.3868,
+      "step": 40
+    },
+    {
+      "epoch": 0.015899561307835867,
+      "grad_norm": 0.12270040065050125,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.2727,
+      "step": 41
+    },
+    {
+      "epoch": 0.016287355486075766,
+      "grad_norm": 0.15896034240722656,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.3355,
+      "step": 42
+    },
+    {
+      "epoch": 0.016675149664315665,
+      "grad_norm": 0.1862407773733139,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.2865,
+      "step": 43
+    },
+    {
+      "epoch": 0.017062943842555564,
+      "grad_norm": 0.22276803851127625,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.429,
+      "step": 44
+    },
+    {
+      "epoch": 0.017450738020795463,
+      "grad_norm": 0.286060631275177,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.4389,
+      "step": 45
+    },
+    {
+      "epoch": 0.017838532199035362,
+      "grad_norm": 0.34563249349594116,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.3784,
+      "step": 46
+    },
+    {
+      "epoch": 0.01822632637727526,
+      "grad_norm": 0.3671421408653259,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4262,
+      "step": 47
+    },
+    {
+      "epoch": 0.01861412055551516,
+      "grad_norm": 0.4121815860271454,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.4286,
+      "step": 48
+    },
+    {
+      "epoch": 0.01900191473375506,
+      "grad_norm": 0.5306976437568665,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4831,
+      "step": 49
+    },
+    {
+      "epoch": 0.019389708911994957,
+      "grad_norm": 1.086495280265808,
+      "learning_rate": 1e-05,
+      "loss": 1.5546,
+      "step": 50
+    },
+    {
+      "epoch": 0.019389708911994957,
+      "eval_loss": 1.4502235651016235,
+      "eval_runtime": 4.4794,
+      "eval_samples_per_second": 11.162,
+      "eval_steps_per_second": 2.902,
+      "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": 1.3602515653859738e+17,
+  "total_flos": 2.732115036565668e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null