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:fb655d13d8599a94bf8182b03820cbaf868083eb5d75ae8ed5039ddb8b366925
+oid sha256:12e16375515c3bfea359afc9187dd3f12304e8491b00d2e977eb607506716816
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f55b178bf55336c7317fdf675eca827769e2baed7e1e7bc183bf8c12ae550712
+oid sha256:fdb9c8004eb5ef85fed7c55bf281f2dd26a1ba291cb259f76bf9590bfedddcab
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a5f3a3dd985135f49dc94bb4718d9adfabaae4b67dd785e0e528027cc3520c
+oid sha256:dc74298202c44a3384dbf93fc9e795f29fc0cbaeecdaf3919a293bf04df03c42
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906597ef04d67dc26958ce229bf415190c5f08d515f6294fd2d9234c08bdd0ae
+oid sha256:a2d58654853994c9858f9910ac561ea87c885132c91e06032104946129012e0a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:271aa2ae7312daa272ff51d7b4e696ae39783c53d349fbed81f11a4c9d7dc293
+oid sha256:40a7d7667ba31dd24e1a8dd9e9afedfda754f480ad36b8dc9099db85c4cbb5b0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e351f8ca36dd00e7a48d77c3c22aa8e644f5b11e0670617358811c35708d6516
+oid sha256:b30a4be96020a9f78ec0edc6280ce600f3442844520ea63bfad12af2cd9b2248
 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": 0.8428515195846558,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09530617107457708,
+  "best_metric": 0.8346361517906189,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.19061234214915415,
   "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": 143.571,
       "eval_steps_per_second": 17.946,
       "step": 25
+    },
+    {
+      "epoch": 0.09911841791756017,
+      "grad_norm": 0.1759335994720459,
+      "learning_rate": 5e-05,
+      "loss": 0.8758,
+      "step": 26
+    },
+    {
+      "epoch": 0.10293066476054324,
+      "grad_norm": 0.19624562561511993,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9195,
+      "step": 27
+    },
+    {
+      "epoch": 0.10674291160352632,
+      "grad_norm": 0.19254527986049652,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8493,
+      "step": 28
+    },
+    {
+      "epoch": 0.11055515844650941,
+      "grad_norm": 0.20061329007148743,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.908,
+      "step": 29
+    },
+    {
+      "epoch": 0.11436740528949249,
+      "grad_norm": 0.19461949169635773,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8234,
+      "step": 30
+    },
+    {
+      "epoch": 0.11817965213247558,
+      "grad_norm": 0.1995747834444046,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8731,
+      "step": 31
+    },
+    {
+      "epoch": 0.12199189897545866,
+      "grad_norm": 0.20301039516925812,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8031,
+      "step": 32
+    },
+    {
+      "epoch": 0.12580414581844174,
+      "grad_norm": 0.20862935483455658,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.838,
+      "step": 33
+    },
+    {
+      "epoch": 0.12961639266142483,
+      "grad_norm": 0.22189174592494965,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8665,
+      "step": 34
+    },
+    {
+      "epoch": 0.13342863950440792,
+      "grad_norm": 0.23263895511627197,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8503,
+      "step": 35
+    },
+    {
+      "epoch": 0.13724088634739098,
+      "grad_norm": 0.23706233501434326,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7954,
+      "step": 36
+    },
+    {
+      "epoch": 0.14105313319037407,
+      "grad_norm": 0.27249541878700256,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8025,
+      "step": 37
+    },
+    {
+      "epoch": 0.14486538003335717,
+      "grad_norm": 0.1823560893535614,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9405,
+      "step": 38
+    },
+    {
+      "epoch": 0.14867762687634023,
+      "grad_norm": 0.16355444490909576,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8379,
+      "step": 39
+    },
+    {
+      "epoch": 0.15248987371932332,
+      "grad_norm": 0.16927115619182587,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.8402,
+      "step": 40
+    },
+    {
+      "epoch": 0.1563021205623064,
+      "grad_norm": 0.18029265105724335,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8458,
+      "step": 41
+    },
+    {
+      "epoch": 0.1601143674052895,
+      "grad_norm": 0.18312260508537292,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8675,
+      "step": 42
+    },
+    {
+      "epoch": 0.16392661424827257,
+      "grad_norm": 0.19348792731761932,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8466,
+      "step": 43
+    },
+    {
+      "epoch": 0.16773886109125566,
+      "grad_norm": 0.1927310675382614,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7973,
+      "step": 44
+    },
+    {
+      "epoch": 0.17155110793423875,
+      "grad_norm": 0.20133088529109955,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8522,
+      "step": 45
+    },
+    {
+      "epoch": 0.1753633547772218,
+      "grad_norm": 0.20981720089912415,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8388,
+      "step": 46
+    },
+    {
+      "epoch": 0.1791756016202049,
+      "grad_norm": 0.21205788850784302,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7974,
+      "step": 47
+    },
+    {
+      "epoch": 0.182987848463188,
+      "grad_norm": 0.23205319046974182,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7912,
+      "step": 48
+    },
+    {
+      "epoch": 0.1868000953061711,
+      "grad_norm": 0.24879471957683563,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.848,
+      "step": 49
+    },
+    {
+      "epoch": 0.19061234214915415,
+      "grad_norm": 0.29144957661628723,
+      "learning_rate": 0.0,
+      "loss": 0.8512,
+      "step": 50
+    },
+    {
+      "epoch": 0.19061234214915415,
+      "eval_loss": 0.8346361517906189,
+      "eval_runtime": 12.391,
+      "eval_samples_per_second": 142.684,
+      "eval_steps_per_second": 17.836,
+      "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": 1.4783502046199808e+16,
+  "total_flos": 2.9585460372176896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null