Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:844b2eaa8747a216b6003be29f8c43e4491e2d8258b40d8b564e40ac992eb1ef
+oid sha256:72242482b824bcdca1f05e3d1d8f3cbfe9d8f1339454688c13bdab9f685c964a
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af158261f67e3d1359526771a30729fe804505b254b9ca40f9587d5b9b7968eb
+oid sha256:c8a3562f466114e028e0729dda48969f0a0a670bc33fc2f42cf2dc56d8879a82
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:010f380baa8f50d6b29a82e0712ebc2da075dc71b82ebb522e31aac8781ea0fa
+oid sha256:90d9f0dcae7eb5ce87a182da0a575715ff4041fc8ddb1a069df406d2e9bcd6ed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e38043e2488357f361a0069c9e71dcfa6ffa94299ce2ee81732286e80745da4
+oid sha256:79cfe6796d5075727a90ba1381a912c320008c4a75cf7e5e7d94bf36ba4afa0b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5a9a6c940def814122dde4982626d90aa1fa58855a46f0ae3c262fc85ea9bc9
+oid sha256:666d77a624b162688d909792e389bb2bc847b8e6590c677ae903379833dd52d0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d073531e8b6b2684fc216feb7d1426e9fe4920c7939a34fdcca21c6abaf78b2
+oid sha256:f2cc91e2446161fb9b74ee57e288c7f0c165de126559b0a66afdbd77e9053422
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8743540048599243,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.039619651347068144,
+  "best_metric": 0.7424139976501465,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07923930269413629,
   "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": 15.193,
       "eval_steps_per_second": 3.95,
       "step": 25
+    },
+    {
+      "epoch": 0.04120443740095087,
+      "grad_norm": 0.7731386423110962,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 0.8463,
+      "step": 26
+    },
+    {
+      "epoch": 0.042789223454833596,
+      "grad_norm": 0.6917439103126526,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 0.8448,
+      "step": 27
+    },
+    {
+      "epoch": 0.044374009508716325,
+      "grad_norm": 0.6431922316551208,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 0.7683,
+      "step": 28
+    },
+    {
+      "epoch": 0.04595879556259905,
+      "grad_norm": 0.7308835387229919,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 0.9075,
+      "step": 29
+    },
+    {
+      "epoch": 0.04754358161648178,
+      "grad_norm": 1.5559896230697632,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 0.7099,
+      "step": 30
+    },
+    {
+      "epoch": 0.0491283676703645,
+      "grad_norm": 0.7101494669914246,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 0.7386,
+      "step": 31
+    },
+    {
+      "epoch": 0.05071315372424723,
+      "grad_norm": 0.7161931991577148,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 0.6076,
+      "step": 32
+    },
+    {
+      "epoch": 0.05229793977812995,
+      "grad_norm": 0.7691206336021423,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 0.6235,
+      "step": 33
+    },
+    {
+      "epoch": 0.05388272583201268,
+      "grad_norm": 0.9122820496559143,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 0.7181,
+      "step": 34
+    },
+    {
+      "epoch": 0.0554675118858954,
+      "grad_norm": 1.6549066305160522,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 0.7327,
+      "step": 35
+    },
+    {
+      "epoch": 0.05705229793977813,
+      "grad_norm": 2.5280091762542725,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 0.5369,
+      "step": 36
+    },
+    {
+      "epoch": 0.058637083993660855,
+      "grad_norm": 1.9925541877746582,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 0.5835,
+      "step": 37
+    },
+    {
+      "epoch": 0.060221870047543584,
+      "grad_norm": 1.2063634395599365,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 0.8154,
+      "step": 38
+    },
+    {
+      "epoch": 0.061806656101426306,
+      "grad_norm": 0.6842193603515625,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 0.8401,
+      "step": 39
+    },
+    {
+      "epoch": 0.06339144215530904,
+      "grad_norm": 0.6004986763000488,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 0.6677,
+      "step": 40
+    },
+    {
+      "epoch": 0.06497622820919176,
+      "grad_norm": 0.5825014710426331,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 0.7524,
+      "step": 41
+    },
+    {
+      "epoch": 0.06656101426307448,
+      "grad_norm": 0.966681182384491,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 0.8021,
+      "step": 42
+    },
+    {
+      "epoch": 0.06814580031695722,
+      "grad_norm": 0.6058341860771179,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 0.6558,
+      "step": 43
+    },
+    {
+      "epoch": 0.06973058637083994,
+      "grad_norm": 0.730965256690979,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 0.5955,
+      "step": 44
+    },
+    {
+      "epoch": 0.07131537242472266,
+      "grad_norm": 0.8394338488578796,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 0.6537,
+      "step": 45
+    },
+    {
+      "epoch": 0.07290015847860538,
+      "grad_norm": 0.7698927521705627,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 0.7215,
+      "step": 46
+    },
+    {
+      "epoch": 0.07448494453248812,
+      "grad_norm": 1.0021368265151978,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 0.5779,
+      "step": 47
+    },
+    {
+      "epoch": 0.07606973058637084,
+      "grad_norm": 0.9064629077911377,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 0.4996,
+      "step": 48
+    },
+    {
+      "epoch": 0.07765451664025357,
+      "grad_norm": 1.479453682899475,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.5706,
+      "step": 49
+    },
+    {
+      "epoch": 0.07923930269413629,
+      "grad_norm": 1.81675124168396,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 0.6822,
+      "step": 50
+    },
+    {
+      "epoch": 0.07923930269413629,
+      "eval_loss": 0.7424139976501465,
+      "eval_runtime": 3.2822,
+      "eval_samples_per_second": 15.234,
+      "eval_steps_per_second": 3.961,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.66009604784128e+17,
+  "total_flos": 5.32019209568256e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null