Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b9180abc17870a1700f2493217f8744356715c29da9e8a24daf6068af0a1e90
+oid sha256:ab6048cb1922a1c165cbefd18b072938d64b2f4365155a9ad6abf1a6981c15b7
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff6d44a366000fe286f019853207239d43f70700f826717db750199ddb453ac
+oid sha256:7b24a6fdb16e332f103cedff95803e187b6f1185e7501f2a813e5bf72cd5f7e3
 size 1101572914

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26007346bef8935a3741e27a431c5b1a9980c9a246c0c780054691d43c65fb7f
+oid sha256:c027d64df6193cca76ebc0fc7d8e25ec3d62280ff3a65f8886a30c80c9dbd95b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:657fe98d49f74cdb7443c034d48f3c07123c5b4a0f5dceebfa1c69fbcf7a65bf
+oid sha256:75bfd75d2d1d7413dbd511a504e350f57fbf687c8ff3ae1083d352d94ac85304
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df20e8cd6b46fddba695bcf8f53085fd19793048d8efedaf0f06a02a6c30cd9c
+oid sha256:be23fdae86798c70d8d555adc5d83a5a5e4078454050b894b6e6f4beb6d08106
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c9e1e53e2b3dc2f0cab8e7c643f5cb48b5a6d1caaf4a41b04f8d1f975ae01ae
+oid sha256:4208087f77135bcd37f8d8b3040f8067df04bcf77574d7e202b2b5d64bc5d375
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7922729849815369,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3147128245476003,
+  "best_metric": 0.4945218563079834,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6294256490952006,
   "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": 18.669,
       "eval_steps_per_second": 2.334,
       "step": 25
+    },
+    {
+      "epoch": 0.32730133752950435,
+      "grad_norm": 1.1050761938095093,
+      "learning_rate": 5e-05,
+      "loss": 0.9919,
+      "step": 26
+    },
+    {
+      "epoch": 0.33988985051140835,
+      "grad_norm": 1.3330028057098389,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9198,
+      "step": 27
+    },
+    {
+      "epoch": 0.35247836349331235,
+      "grad_norm": 1.1018527746200562,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8412,
+      "step": 28
+    },
+    {
+      "epoch": 0.36506687647521635,
+      "grad_norm": 0.9233662486076355,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8082,
+      "step": 29
+    },
+    {
+      "epoch": 0.3776553894571204,
+      "grad_norm": 0.9848074316978455,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7682,
+      "step": 30
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.8084222674369812,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6514,
+      "step": 31
+    },
+    {
+      "epoch": 0.4028324154209284,
+      "grad_norm": 1.097373127937317,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7189,
+      "step": 32
+    },
+    {
+      "epoch": 0.4154209284028324,
+      "grad_norm": 1.6498360633850098,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6969,
+      "step": 33
+    },
+    {
+      "epoch": 0.42800944138473646,
+      "grad_norm": 1.8005599975585938,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6476,
+      "step": 34
+    },
+    {
+      "epoch": 0.44059795436664045,
+      "grad_norm": 1.278456687927246,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5076,
+      "step": 35
+    },
+    {
+      "epoch": 0.45318646734854445,
+      "grad_norm": 1.1756541728973389,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.5192,
+      "step": 36
+    },
+    {
+      "epoch": 0.46577498033044845,
+      "grad_norm": 1.3729151487350464,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5166,
+      "step": 37
+    },
+    {
+      "epoch": 0.4783634933123525,
+      "grad_norm": 1.0366138219833374,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6122,
+      "step": 38
+    },
+    {
+      "epoch": 0.4909520062942565,
+      "grad_norm": 0.9966530203819275,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7652,
+      "step": 39
+    },
+    {
+      "epoch": 0.5035405192761605,
+      "grad_norm": 0.8695334196090698,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.629,
+      "step": 40
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 1.0313053131103516,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6526,
+      "step": 41
+    },
+    {
+      "epoch": 0.5287175452399685,
+      "grad_norm": 0.9505526423454285,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6085,
+      "step": 42
+    },
+    {
+      "epoch": 0.5413060582218725,
+      "grad_norm": 1.02927565574646,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5774,
+      "step": 43
+    },
+    {
+      "epoch": 0.5538945712037766,
+      "grad_norm": 0.9868349432945251,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4886,
+      "step": 44
+    },
+    {
+      "epoch": 0.5664830841856806,
+      "grad_norm": 1.0703577995300293,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5164,
+      "step": 45
+    },
+    {
+      "epoch": 0.5790715971675846,
+      "grad_norm": 0.9647153615951538,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4849,
+      "step": 46
+    },
+    {
+      "epoch": 0.5916601101494886,
+      "grad_norm": 1.2369579076766968,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.425,
+      "step": 47
+    },
+    {
+      "epoch": 0.6042486231313926,
+      "grad_norm": 1.017994999885559,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3793,
+      "step": 48
+    },
+    {
+      "epoch": 0.6168371361132966,
+      "grad_norm": 1.1479705572128296,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3435,
+      "step": 49
+    },
+    {
+      "epoch": 0.6294256490952006,
+      "grad_norm": 1.798177719116211,
+      "learning_rate": 0.0,
+      "loss": 0.4222,
+      "step": 50
+    },
+    {
+      "epoch": 0.6294256490952006,
+      "eval_loss": 0.4945218563079834,
+      "eval_runtime": 28.7393,
+      "eval_samples_per_second": 18.65,
+      "eval_steps_per_second": 2.331,
+      "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": 5.555785010511872e+17,
+  "total_flos": 1.1111570021023744e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null