Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c9d718762ac09e696c7a98dbf9fe822367dda4b899c1e9728d4fb279183c74
+oid sha256:98a1cd7937804a8c8c1e5fadc19659ad30559e3271009714f4f7d73def65933c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7b9c986d1cd47f2feaddf3da934e72fd6ebc2b63bc42c519e16803c301ebd55
+oid sha256:075a89a66f4b1079e4a115a767a0ed3a318fa38c6a6916b220074048be908547
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ea5395be9f3770f7d0e563c3e4fee06b4570ed277072c3eacc3ff5b4a8799d3
+oid sha256:4b27ec6d313848d7f46276ecd0ba150ca6b07f29b12cf2bbd5620c9f4a819644
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c22ab587f148e086318213ddb462011853925e47b27a2e90d9c4fb549c894eb
+oid sha256:5ce6cab51d99c210bfad42a6e2c47702db9f85bcb4a0198d5cc71e0e655a4578
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5370ea3231d546738e2622fea4c71b80e31fcaf1c8918230c012c21860f89b99
+oid sha256:a11305ae74fe5c7fad4abc119227840c09e7979297322b0205372ffbba91942b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d4a6e460aeb8829c65826656dcc5d7dcbeabcebf5e3fe8cda40b200bc81fd8
+oid sha256:17824de924a6432b0997131923cf03e279c6d4e8151b0fb66fc9597b1ae59e46
 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": 0.7292673587799072,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07809449433814916,
+  "best_metric": 0.6981587409973145,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.15618898867629832,
   "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": 34.731,
       "eval_steps_per_second": 4.347,
       "step": 25
+    },
+    {
+      "epoch": 0.08121827411167512,
+      "grad_norm": 20.802223205566406,
+      "learning_rate": 5e-05,
+      "loss": 0.614,
+      "step": 26
+    },
+    {
+      "epoch": 0.0843420538852011,
+      "grad_norm": 25.634445190429688,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6549,
+      "step": 27
+    },
+    {
+      "epoch": 0.08746583365872707,
+      "grad_norm": 24.01685905456543,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7213,
+      "step": 28
+    },
+    {
+      "epoch": 0.09058961343225302,
+      "grad_norm": 25.094823837280273,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6263,
+      "step": 29
+    },
+    {
+      "epoch": 0.093713393205779,
+      "grad_norm": 25.876249313354492,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.679,
+      "step": 30
+    },
+    {
+      "epoch": 0.09683717297930496,
+      "grad_norm": 21.759727478027344,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.6216,
+      "step": 31
+    },
+    {
+      "epoch": 0.09996095275283093,
+      "grad_norm": 24.143407821655273,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.636,
+      "step": 32
+    },
+    {
+      "epoch": 0.10308473252635689,
+      "grad_norm": 25.804513931274414,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6894,
+      "step": 33
+    },
+    {
+      "epoch": 0.10620851229988286,
+      "grad_norm": 27.420663833618164,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8195,
+      "step": 34
+    },
+    {
+      "epoch": 0.10933229207340882,
+      "grad_norm": 29.06009292602539,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7946,
+      "step": 35
+    },
+    {
+      "epoch": 0.11245607184693479,
+      "grad_norm": 28.592594146728516,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.786,
+      "step": 36
+    },
+    {
+      "epoch": 0.11557985162046076,
+      "grad_norm": 32.12931823730469,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8086,
+      "step": 37
+    },
+    {
+      "epoch": 0.11870363139398672,
+      "grad_norm": 23.032005310058594,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.69,
+      "step": 38
+    },
+    {
+      "epoch": 0.1218274111675127,
+      "grad_norm": 16.44974136352539,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4579,
+      "step": 39
+    },
+    {
+      "epoch": 0.12495119094103865,
+      "grad_norm": 20.0357666015625,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5951,
+      "step": 40
+    },
+    {
+      "epoch": 0.1280749707145646,
+      "grad_norm": 21.83281898498535,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6761,
+      "step": 41
+    },
+    {
+      "epoch": 0.1311987504880906,
+      "grad_norm": 24.00539779663086,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6549,
+      "step": 42
+    },
+    {
+      "epoch": 0.13432253026161656,
+      "grad_norm": 26.342254638671875,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6536,
+      "step": 43
+    },
+    {
+      "epoch": 0.13744631003514252,
+      "grad_norm": 24.765623092651367,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7236,
+      "step": 44
+    },
+    {
+      "epoch": 0.1405700898086685,
+      "grad_norm": 27.13953399658203,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7191,
+      "step": 45
+    },
+    {
+      "epoch": 0.14369386958219446,
+      "grad_norm": 23.938737869262695,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6521,
+      "step": 46
+    },
+    {
+      "epoch": 0.14681764935572042,
+      "grad_norm": 41.53923416137695,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.709,
+      "step": 47
+    },
+    {
+      "epoch": 0.14994142912924638,
+      "grad_norm": 26.58255386352539,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6992,
+      "step": 48
+    },
+    {
+      "epoch": 0.15306520890277237,
+      "grad_norm": 29.302122116088867,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7472,
+      "step": 49
+    },
+    {
+      "epoch": 0.15618898867629832,
+      "grad_norm": 29.7325496673584,
+      "learning_rate": 0.0,
+      "loss": 0.85,
+      "step": 50
+    },
+    {
+      "epoch": 0.15618898867629832,
+      "eval_loss": 0.6981587409973145,
+      "eval_runtime": 62.0993,
+      "eval_samples_per_second": 34.735,
+      "eval_steps_per_second": 4.348,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null