Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:629468b49f56f3c17f182c8e54e2161830723b4bfc9a055d1f233a2aef9e191c
+oid sha256:baf495d823978b7535e9cf7f1d5b7043ea2c6b33ce620d1e793ef846b846770f
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988388532a8ae5200e6d6542005a1acd43f4960d74c7dbeda5eaef92ae09e4f3
+oid sha256:2418b0d7f7167b1629b077ed0a6d306510c37126af519275839eaf6bc1d33bf6
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:282251d45affc21589b1121f2e82541399bd6364c72c978d2d06deb2ccf7e901
+oid sha256:b7270f26b0bfdcdf1ad3f27c983801cc56d17681001507c6aeb2e47c43f2b614
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac2d676c3ac951616bb2f290c23ba34c0dc92acdbe2834784c3030dfebb87c2
+oid sha256:d7205bc1924d7efe72f5e878ae9605c714e9c0c4f1bd6cb0e6a63f71a35174e1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06570e222930a1e62cdb82c9db186f13c6f175902236aec9144cfcc09e1d670
+oid sha256:fb09a8f9ac29379aee99f6dbef62d346a7c61acb23e0ba33fc424b0c8d936b9f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:132d66150aa536f9cea2f4c430d2f2944f3e4b53420871402a622d1993c240e5
+oid sha256:6f910f30dbe3497b2dcb445ac0be39ac5bd4747275e9f8253a33f62e469d43c4
 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": 3.7278997898101807,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.21534320323014805,
+  "best_metric": 3.6382930278778076,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.4306864064602961,
   "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": 30.477,
       "eval_steps_per_second": 3.817,
       "step": 25
+    },
+    {
+      "epoch": 0.22395693135935396,
+      "grad_norm": 1.2998414039611816,
+      "learning_rate": 5e-05,
+      "loss": 3.7794,
+      "step": 26
+    },
+    {
+      "epoch": 0.2325706594885599,
+      "grad_norm": 1.6861227750778198,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.756,
+      "step": 27
+    },
+    {
+      "epoch": 0.2411843876177658,
+      "grad_norm": 1.0421063899993896,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.7032,
+      "step": 28
+    },
+    {
+      "epoch": 0.24979811574697175,
+      "grad_norm": 1.0148087739944458,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.7074,
+      "step": 29
+    },
+    {
+      "epoch": 0.25841184387617766,
+      "grad_norm": 1.1693507432937622,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.682,
+      "step": 30
+    },
+    {
+      "epoch": 0.26702557200538357,
+      "grad_norm": 0.6761946082115173,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.6466,
+      "step": 31
+    },
+    {
+      "epoch": 0.2756393001345895,
+      "grad_norm": 0.856696367263794,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.6619,
+      "step": 32
+    },
+    {
+      "epoch": 0.28425302826379545,
+      "grad_norm": 0.832834005355835,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.6142,
+      "step": 33
+    },
+    {
+      "epoch": 0.29286675639300136,
+      "grad_norm": 0.8012253642082214,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.6064,
+      "step": 34
+    },
+    {
+      "epoch": 0.30148048452220727,
+      "grad_norm": 0.8955758213996887,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.6216,
+      "step": 35
+    },
+    {
+      "epoch": 0.3100942126514132,
+      "grad_norm": 0.9002861380577087,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.6473,
+      "step": 36
+    },
+    {
+      "epoch": 0.3187079407806191,
+      "grad_norm": 1.002937912940979,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.7539,
+      "step": 37
+    },
+    {
+      "epoch": 0.32732166890982506,
+      "grad_norm": 0.7870951294898987,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.7668,
+      "step": 38
+    },
+    {
+      "epoch": 0.33593539703903097,
+      "grad_norm": 0.7260990142822266,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.6595,
+      "step": 39
+    },
+    {
+      "epoch": 0.3445491251682369,
+      "grad_norm": 0.726902186870575,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.7027,
+      "step": 40
+    },
+    {
+      "epoch": 0.3531628532974428,
+      "grad_norm": 0.8145126700401306,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.6087,
+      "step": 41
+    },
+    {
+      "epoch": 0.3617765814266487,
+      "grad_norm": 0.7508212327957153,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.6261,
+      "step": 42
+    },
+    {
+      "epoch": 0.37039030955585467,
+      "grad_norm": 0.7382489442825317,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.5965,
+      "step": 43
+    },
+    {
+      "epoch": 0.3790040376850606,
+      "grad_norm": 0.6966142654418945,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.5584,
+      "step": 44
+    },
+    {
+      "epoch": 0.3876177658142665,
+      "grad_norm": 0.6668608784675598,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.575,
+      "step": 45
+    },
+    {
+      "epoch": 0.3962314939434724,
+      "grad_norm": 0.6239801645278931,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.6472,
+      "step": 46
+    },
+    {
+      "epoch": 0.4048452220726783,
+      "grad_norm": 0.6501104831695557,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.5244,
+      "step": 47
+    },
+    {
+      "epoch": 0.4134589502018843,
+      "grad_norm": 0.7032169103622437,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.5832,
+      "step": 48
+    },
+    {
+      "epoch": 0.4220726783310902,
+      "grad_norm": 0.843285858631134,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.6745,
+      "step": 49
+    },
+    {
+      "epoch": 0.4306864064602961,
+      "grad_norm": 1.0279968976974487,
+      "learning_rate": 0.0,
+      "loss": 3.8446,
+      "step": 50
+    },
+    {
+      "epoch": 0.4306864064602961,
+      "eval_loss": 3.6382930278778076,
+      "eval_runtime": 51.2906,
+      "eval_samples_per_second": 30.512,
+      "eval_steps_per_second": 3.821,
+      "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": 6.174479344467968e+17,
+  "total_flos": 1.2348958688935936e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null