Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eae2154f5360c666df1dc6138333e70036eb70e2b4712a781f0509a51435355
+oid sha256:37edc3da03bd08d050862933525bc66ac11526bc53c0d526a938ba07528783b9
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307338e35d131d082406e11613b90110dfa3b85929b90b7aca0717db22772502
+oid sha256:82e1a7145b0ff40eca8131df4e2beb654df087022f49569dfd867e59442cf5f6
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12c483438e53dfd1447a9c59abc6dd3da8911d31b39e66ba4f91fdf4cbf0812e
+oid sha256:05b73ad84c340848449630b8ba5d44d00cf190b57032c98da82f66eb1d42ce81
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bae09aad61e2b257222ef247073b7c56272c6c5d678c385495db7f1dd1a5d65d
+oid sha256:2244dee00848383b7446fb496ff07994eb70b25c6cfcae9b041bd3589b1f8868
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:160cd1750fced26c9346073f1fc56df678f78dd9faf391345dfe6bc15e540964
+oid sha256:0cd325ef68b6303e733973d9df1a9cd182276c25365e738ae5e64862a22b1cab
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66bc19b1748e4361c99a1854e6f9e70fe0d81b9bd5981391bc8f91a5d9128807
+oid sha256:603213eb82ee62d82b12949831145a628807fab1164802727d08fea3f18cb2bc
 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": 0.2265699952840805,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012324377618930245,
+  "best_metric": 0.186006560921669,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02464875523786049,
   "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": 15.93,
       "eval_steps_per_second": 4.142,
       "step": 25
+    },
+    {
+      "epoch": 0.012817352723687454,
+      "grad_norm": 10.468292236328125,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 20.6504,
+      "step": 26
+    },
+    {
+      "epoch": 0.013310327828444664,
+      "grad_norm": 11.983538627624512,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 14.0288,
+      "step": 27
+    },
+    {
+      "epoch": 0.013803302933201873,
+      "grad_norm": 11.06685733795166,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 8.5962,
+      "step": 28
+    },
+    {
+      "epoch": 0.014296278037959083,
+      "grad_norm": 8.283320426940918,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 7.9514,
+      "step": 29
+    },
+    {
+      "epoch": 0.014789253142716292,
+      "grad_norm": 6.831525802612305,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.8261,
+      "step": 30
+    },
+    {
+      "epoch": 0.015282228247473502,
+      "grad_norm": 6.675940036773682,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 5.9154,
+      "step": 31
+    },
+    {
+      "epoch": 0.01577520335223071,
+      "grad_norm": 5.194748878479004,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 5.2149,
+      "step": 32
+    },
+    {
+      "epoch": 0.01626817845698792,
+      "grad_norm": 4.787224292755127,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.336,
+      "step": 33
+    },
+    {
+      "epoch": 0.01676115356174513,
+      "grad_norm": 4.844122886657715,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.0652,
+      "step": 34
+    },
+    {
+      "epoch": 0.01725412866650234,
+      "grad_norm": 4.37100887298584,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.0931,
+      "step": 35
+    },
+    {
+      "epoch": 0.017747103771259553,
+      "grad_norm": 6.856547832489014,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 5.6895,
+      "step": 36
+    },
+    {
+      "epoch": 0.018240078876016762,
+      "grad_norm": 7.979983806610107,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.8833,
+      "step": 37
+    },
+    {
+      "epoch": 0.018733053980773972,
+      "grad_norm": 8.421024322509766,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 15.118,
+      "step": 38
+    },
+    {
+      "epoch": 0.01922602908553118,
+      "grad_norm": 9.07979965209961,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 14.3319,
+      "step": 39
+    },
+    {
+      "epoch": 0.01971900419028839,
+      "grad_norm": 6.959233283996582,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 8.4428,
+      "step": 40
+    },
+    {
+      "epoch": 0.0202119792950456,
+      "grad_norm": 11.418706893920898,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 7.1254,
+      "step": 41
+    },
+    {
+      "epoch": 0.02070495439980281,
+      "grad_norm": 6.823760509490967,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.6503,
+      "step": 42
+    },
+    {
+      "epoch": 0.02119792950456002,
+      "grad_norm": 5.575032711029053,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.2792,
+      "step": 43
+    },
+    {
+      "epoch": 0.02169090460931723,
+      "grad_norm": 5.068197250366211,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.4281,
+      "step": 44
+    },
+    {
+      "epoch": 0.02218387971407444,
+      "grad_norm": 5.049072742462158,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.1483,
+      "step": 45
+    },
+    {
+      "epoch": 0.022676854818831648,
+      "grad_norm": 4.566128253936768,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.1247,
+      "step": 46
+    },
+    {
+      "epoch": 0.023169829923588858,
+      "grad_norm": 4.03365421295166,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.581,
+      "step": 47
+    },
+    {
+      "epoch": 0.023662805028346067,
+      "grad_norm": 5.189533233642578,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.5164,
+      "step": 48
+    },
+    {
+      "epoch": 0.024155780133103277,
+      "grad_norm": 6.00453519821167,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.8618,
+      "step": 49
+    },
+    {
+      "epoch": 0.02464875523786049,
+      "grad_norm": 8.213972091674805,
+      "learning_rate": 1e-05,
+      "loss": 3.8589,
+      "step": 50
+    },
+    {
+      "epoch": 0.02464875523786049,
+      "eval_loss": 0.186006560921669,
+      "eval_runtime": 3.1298,
+      "eval_samples_per_second": 15.976,
+      "eval_steps_per_second": 4.154,
+      "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": 1.4868141154762752e+17,
+  "total_flos": 2.972701001200435e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null