Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29977870e17878ef862951bdf0fcb0d46ac5b3c96f11c32d67660a13ea127a9e
+oid sha256:2faf4cfb2bf43aeaf6a21ca78b640acccabbb79cfd33b34f15aed55d6f9686fe
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca575c814bbb1b7ab604d2ff2402fdd61a7afe4168e54b85660d4aa49bb6da4
+oid sha256:9dd07b5204bc4b5faa909ca466201c353c73de6df3960625e2b4a162bf8dc529
 size 1049049122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00f8fd62d63f3862699eae75fc4cc3e6b310a623af2673bfaaeac512f8b6de51
+oid sha256:4386eaa02b8692e6d3bc9c4d43aa5407166ed596aff67a30418b17effab12945
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:715bb691937d7376c92b227b94251df1a038c1523374abd3f7b09fe35f11f0bb
+oid sha256:56c25581b22b9943eaf9ccadb08be171f75ff9e11d6a8980dcd2749f264fe27d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67ab9d793757d47450a974b312eb70a0748a88d4ea605720b6844041cbe374ee
+oid sha256:d6ff05b76bbb9de1867c3b36adcd2a95ee92be60a11c33c7d7dcb3f388ff0afb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e1a3506275614359749a2cffb391f27ef95bfab7196e792fd2333b064eb3ff7
+oid sha256:a484452517f927e694b74b1c785b86e98e446f12527f0ea0964e405d4f2b7c90
 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": 1.3544864654541016,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01113368775572689,
+  "best_metric": 1.1867320537567139,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02226737551145378,
   "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": 20.548,
       "eval_steps_per_second": 2.569,
       "step": 25
+    },
+    {
+      "epoch": 0.011579035265955967,
+      "grad_norm": 30.952394485473633,
+      "learning_rate": 5e-05,
+      "loss": 1.5383,
+      "step": 26
+    },
+    {
+      "epoch": 0.012024382776185042,
+      "grad_norm": 32.05979919433594,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4933,
+      "step": 27
+    },
+    {
+      "epoch": 0.012469730286414118,
+      "grad_norm": 27.44908332824707,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1802,
+      "step": 28
+    },
+    {
+      "epoch": 0.012915077796643193,
+      "grad_norm": 29.982824325561523,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2624,
+      "step": 29
+    },
+    {
+      "epoch": 0.01336042530687227,
+      "grad_norm": 26.732736587524414,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1506,
+      "step": 30
+    },
+    {
+      "epoch": 0.013805772817101344,
+      "grad_norm": 29.822994232177734,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1674,
+      "step": 31
+    },
+    {
+      "epoch": 0.01425112032733042,
+      "grad_norm": 28.42780876159668,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0655,
+      "step": 32
+    },
+    {
+      "epoch": 0.014696467837559495,
+      "grad_norm": 27.28021812438965,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3545,
+      "step": 33
+    },
+    {
+      "epoch": 0.015141815347788572,
+      "grad_norm": 26.741413116455078,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0021,
+      "step": 34
+    },
+    {
+      "epoch": 0.015587162858017646,
+      "grad_norm": 38.1240119934082,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1049,
+      "step": 35
+    },
+    {
+      "epoch": 0.01603251036824672,
+      "grad_norm": 31.203073501586914,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1722,
+      "step": 36
+    },
+    {
+      "epoch": 0.016477857878475798,
+      "grad_norm": 28.79928207397461,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0829,
+      "step": 37
+    },
+    {
+      "epoch": 0.016923205388704874,
+      "grad_norm": 29.13315773010254,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2533,
+      "step": 38
+    },
+    {
+      "epoch": 0.01736855289893395,
+      "grad_norm": 31.34278678894043,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.338,
+      "step": 39
+    },
+    {
+      "epoch": 0.017813900409163023,
+      "grad_norm": 25.4918155670166,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1436,
+      "step": 40
+    },
+    {
+      "epoch": 0.0182592479193921,
+      "grad_norm": 27.85494041442871,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1686,
+      "step": 41
+    },
+    {
+      "epoch": 0.018704595429621176,
+      "grad_norm": 29.38884925842285,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0788,
+      "step": 42
+    },
+    {
+      "epoch": 0.019149942939850253,
+      "grad_norm": 29.656871795654297,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2324,
+      "step": 43
+    },
+    {
+      "epoch": 0.019595290450079326,
+      "grad_norm": 38.212669372558594,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9916,
+      "step": 44
+    },
+    {
+      "epoch": 0.020040637960308402,
+      "grad_norm": 32.79332733154297,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.0483,
+      "step": 45
+    },
+    {
+      "epoch": 0.02048598547053748,
+      "grad_norm": 32.203372955322266,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.3274,
+      "step": 46
+    },
+    {
+      "epoch": 0.020931332980766555,
+      "grad_norm": 26.626222610473633,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0576,
+      "step": 47
+    },
+    {
+      "epoch": 0.02137668049099563,
+      "grad_norm": 31.617427825927734,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1872,
+      "step": 48
+    },
+    {
+      "epoch": 0.021822028001224705,
+      "grad_norm": 30.30613136291504,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1083,
+      "step": 49
+    },
+    {
+      "epoch": 0.02226737551145378,
+      "grad_norm": 34.23044204711914,
+      "learning_rate": 0.0,
+      "loss": 1.2354,
+      "step": 50
+    },
+    {
+      "epoch": 0.02226737551145378,
+      "eval_loss": 1.1867320537567139,
+      "eval_runtime": 736.9926,
+      "eval_samples_per_second": 20.527,
+      "eval_steps_per_second": 2.566,
+      "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": 5.476375360176128e+17,
+  "total_flos": 1.0952750720352256e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null