Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e5ffff0046a0f025ca9533d1256e151639355ff00f4355ab51a93761d766184
+oid sha256:008d322aa4c84376e20fda39ef52f9f159b11824c35455cd3fdd35c2a2b1a356
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58de8cbb3d56b51a1d35b25d4a027d61066387b0c1ddaf4e2a35e50321cc9d07
+oid sha256:5cf68ffbfdb6d73b64a2f9b766100cb69e644bbf599e9aa2e3bd8314005cf267
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba307cd6a9ed363278408f99360d96e6758077328c7f336547ba2703db4cbec
+oid sha256:01f11ddf24e083fda89b07a80329c8526a412ba402396e24064ca68db9d078be
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e56dd04f1053c977e13ed7fac11081ca8a87a9012c86be4d24e1f775176ac72
+oid sha256:1ae85ae3a901369c126ce1f394b384723ec8a23295d93f56f3b0172ef8e42b4c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d4e6acf2206ccb499dff0f482b10e00fc15ca27cd33f880dd761fc143dfb735
+oid sha256:cf7717f8f20ad87e8273cce83d8d7548ce2f078a97d22425c6bfa8f818a9241c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0f9c580904e04f85bd4e1758dd14911c81c013508b260d1819171a7308039a
+oid sha256:d5ac4a8ea3813bdf5be472249f3f7ac48b782edeced7b3e07e42a743dbd298e1
 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": 0.7240148782730103,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017399625908042976,
+  "best_metric": 0.6901659965515137,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03479925181608595,
   "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": 77.295,
       "eval_steps_per_second": 9.662,
       "step": 25
+    },
+    {
+      "epoch": 0.018095610944364696,
+      "grad_norm": 0.32641181349754333,
+      "learning_rate": 5e-05,
+      "loss": 0.6029,
+      "step": 26
+    },
+    {
+      "epoch": 0.018791595980686415,
+      "grad_norm": 0.41020646691322327,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7155,
+      "step": 27
+    },
+    {
+      "epoch": 0.019487581017008135,
+      "grad_norm": 0.39805933833122253,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6874,
+      "step": 28
+    },
+    {
+      "epoch": 0.020183566053329854,
+      "grad_norm": 0.39660125970840454,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7375,
+      "step": 29
+    },
+    {
+      "epoch": 0.020879551089651574,
+      "grad_norm": 0.3622805178165436,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7105,
+      "step": 30
+    },
+    {
+      "epoch": 0.02157553612597329,
+      "grad_norm": 0.34297406673431396,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7426,
+      "step": 31
+    },
+    {
+      "epoch": 0.02227152116229501,
+      "grad_norm": 0.34450390934944153,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7495,
+      "step": 32
+    },
+    {
+      "epoch": 0.02296750619861673,
+      "grad_norm": 0.3421584665775299,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6989,
+      "step": 33
+    },
+    {
+      "epoch": 0.02366349123493845,
+      "grad_norm": 0.37303704023361206,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7086,
+      "step": 34
+    },
+    {
+      "epoch": 0.02435947627126017,
+      "grad_norm": 0.43865445256233215,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.694,
+      "step": 35
+    },
+    {
+      "epoch": 0.025055461307581888,
+      "grad_norm": 0.46537771821022034,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7458,
+      "step": 36
+    },
+    {
+      "epoch": 0.025751446343903608,
+      "grad_norm": 0.5680077075958252,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7136,
+      "step": 37
+    },
+    {
+      "epoch": 0.026447431380225324,
+      "grad_norm": 0.27463626861572266,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5901,
+      "step": 38
+    },
+    {
+      "epoch": 0.027143416416547043,
+      "grad_norm": 0.24753239750862122,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6592,
+      "step": 39
+    },
+    {
+      "epoch": 0.027839401452868763,
+      "grad_norm": 0.2639525532722473,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6948,
+      "step": 40
+    },
+    {
+      "epoch": 0.028535386489190483,
+      "grad_norm": 0.2715783715248108,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6954,
+      "step": 41
+    },
+    {
+      "epoch": 0.029231371525512202,
+      "grad_norm": 0.2822418510913849,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6766,
+      "step": 42
+    },
+    {
+      "epoch": 0.029927356561833922,
+      "grad_norm": 0.2924785315990448,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.646,
+      "step": 43
+    },
+    {
+      "epoch": 0.030623341598155638,
+      "grad_norm": 0.3038496673107147,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7131,
+      "step": 44
+    },
+    {
+      "epoch": 0.03131932663447736,
+      "grad_norm": 0.32502034306526184,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6559,
+      "step": 45
+    },
+    {
+      "epoch": 0.03201531167079908,
+      "grad_norm": 0.36731162667274475,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.714,
+      "step": 46
+    },
+    {
+      "epoch": 0.0327112967071208,
+      "grad_norm": 0.367169588804245,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7375,
+      "step": 47
+    },
+    {
+      "epoch": 0.03340728174344251,
+      "grad_norm": 0.4129124879837036,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7278,
+      "step": 48
+    },
+    {
+      "epoch": 0.03410326677976423,
+      "grad_norm": 0.49003276228904724,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6891,
+      "step": 49
+    },
+    {
+      "epoch": 0.03479925181608595,
+      "grad_norm": 0.6333441734313965,
+      "learning_rate": 0.0,
+      "loss": 0.7221,
+      "step": 50
+    },
+    {
+      "epoch": 0.03479925181608595,
+      "eval_loss": 0.6901659965515137,
+      "eval_runtime": 126.2193,
+      "eval_samples_per_second": 76.692,
+      "eval_steps_per_second": 9.586,
+      "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": 7.952285976808653e+16,
+  "total_flos": 1.5919473181589504e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null