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:a3f90633df8a2b11393dff0704ee34872e52e8f128ce91dd4949b68b6e518271
+oid sha256:4d36e3a04a6e2c1c3519665a5e860e8056e09de6f5abe30c00ff2ecb912cb58e
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5433459dd5a2e9dd697f61973acfef100efc4fee7505e1b3983f3a477c0914f2
+oid sha256:535fbf8bf9e3ff2267158336808f9d3378d8c6a28576a80284212941aa03af05
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ef2ecdaec37bbde46f0af15f52fef60c7f33982d007a451633c4c1fc1e1d5c
+oid sha256:e576297330d63e1efbc30ee14563cf177ebb56f8db683f741bce014c13d8c9dd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:885c275b8768e85f8c0fcd217207ece98a838e91dc9be74e4c6b17f5fce41b75
+oid sha256:50d58b0f727bc19f611bd3c42113f1f071a19baccdc5725d668335f3b299ed81
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a54f8a18f2c4e2a2786be91eeeb487c5b7153ad240853086f57a16fd195feb56
+oid sha256:adbf2bbeb6f1070dc7ae6665444a412ef1212f4691cffa415699f8b7162dfb23
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41e8ad8b74e1d57f3fda479752a4ee8db459d10c321c9d8830e9eff0ecab9881
+oid sha256:13278b3f64769f0325c9b904dd97fe04564557e43ae2c0c86fe538b8ef894fbd
 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": 1.1616710424423218,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.2875629043853343,
+  "best_metric": 1.1276211738586426,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5751258087706685,
   "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": 8.675,
       "eval_steps_per_second": 1.095,
       "step": 25
+    },
+    {
+      "epoch": 0.29906542056074764,
+      "grad_norm": 0.7918073534965515,
+      "learning_rate": 5e-05,
+      "loss": 1.1562,
+      "step": 26
+    },
+    {
+      "epoch": 0.310567936736161,
+      "grad_norm": 1.0403803586959839,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1705,
+      "step": 27
+    },
+    {
+      "epoch": 0.32207045291157443,
+      "grad_norm": 0.5075483918190002,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.1533,
+      "step": 28
+    },
+    {
+      "epoch": 0.3335729690869878,
+      "grad_norm": 0.8391026258468628,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1679,
+      "step": 29
+    },
+    {
+      "epoch": 0.34507548526240117,
+      "grad_norm": 0.4457230269908905,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1445,
+      "step": 30
+    },
+    {
+      "epoch": 0.35657800143781454,
+      "grad_norm": 0.723479151725769,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1551,
+      "step": 31
+    },
+    {
+      "epoch": 0.3680805176132279,
+      "grad_norm": 0.5515746474266052,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.1417,
+      "step": 32
+    },
+    {
+      "epoch": 0.3795830337886413,
+      "grad_norm": 0.33850058913230896,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.14,
+      "step": 33
+    },
+    {
+      "epoch": 0.39108554996405465,
+      "grad_norm": 0.4152383804321289,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1405,
+      "step": 34
+    },
+    {
+      "epoch": 0.402588066139468,
+      "grad_norm": 0.3818333148956299,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1378,
+      "step": 35
+    },
+    {
+      "epoch": 0.4140905823148814,
+      "grad_norm": 0.5444033145904541,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1445,
+      "step": 36
+    },
+    {
+      "epoch": 0.42559309849029475,
+      "grad_norm": 0.40225115418434143,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1175,
+      "step": 37
+    },
+    {
+      "epoch": 0.4370956146657081,
+      "grad_norm": 0.41632404923439026,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1086,
+      "step": 38
+    },
+    {
+      "epoch": 0.4485981308411215,
+      "grad_norm": 0.4659530818462372,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1495,
+      "step": 39
+    },
+    {
+      "epoch": 0.46010064701653486,
+      "grad_norm": 0.7380015254020691,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1556,
+      "step": 40
+    },
+    {
+      "epoch": 0.4716031631919482,
+      "grad_norm": 0.6908935308456421,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1627,
+      "step": 41
+    },
+    {
+      "epoch": 0.4831056793673616,
+      "grad_norm": 0.39957094192504883,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1222,
+      "step": 42
+    },
+    {
+      "epoch": 0.49460819554277496,
+      "grad_norm": 0.3861657381057739,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1154,
+      "step": 43
+    },
+    {
+      "epoch": 0.5061107117181883,
+      "grad_norm": 0.4914008378982544,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1446,
+      "step": 44
+    },
+    {
+      "epoch": 0.5176132278936018,
+      "grad_norm": 0.28890010714530945,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.137,
+      "step": 45
+    },
+    {
+      "epoch": 0.5291157440690151,
+      "grad_norm": 0.32409754395484924,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1171,
+      "step": 46
+    },
+    {
+      "epoch": 0.5406182602444285,
+      "grad_norm": 0.48606187105178833,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1439,
+      "step": 47
+    },
+    {
+      "epoch": 0.5521207764198418,
+      "grad_norm": 0.34273761510849,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.11,
+      "step": 48
+    },
+    {
+      "epoch": 0.5636232925952552,
+      "grad_norm": 0.4657009243965149,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1021,
+      "step": 49
+    },
+    {
+      "epoch": 0.5751258087706685,
+      "grad_norm": 0.5568671226501465,
+      "learning_rate": 0.0,
+      "loss": 1.0781,
+      "step": 50
+    },
+    {
+      "epoch": 0.5751258087706685,
+      "eval_loss": 1.1276211738586426,
+      "eval_runtime": 67.5325,
+      "eval_samples_per_second": 8.677,
+      "eval_steps_per_second": 1.096,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null