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:ca2f70afa26735fd1cff73b993b402cb297f5dabd3a492c6854ce53cf7c31021
+oid sha256:91cbb4b4170436c489ad857c8102e2891969450414bbc45969fd5551524d1c81
 size 261131840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ecba58b19545fb1ff24fcb0613cefe9faee959761f34767173755a5d5e46c62
+oid sha256:83b313b388b56ce7bc60cf7b9ebeaf3c3a815bd8bb4ff9ec9f2ddff030b93251
 size 522406650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c97a3d1576bc417126557cff3fc766083216fb699edbe7ba6db37f88c250f2
+oid sha256:1e11747660072d6a76b35e5bb866bce98831fe9bff7f9adc1d272cdd67c11b3b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:389ab3f06b2734fb1110fcdb9ce950f898ce0aa1d7f689ab6a28d0b981c5dde4
+oid sha256:ab600cc146267a183d5ce97be6ee1b151a82cebc1a796a4d2a3fcfbd19ee4376
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34051bba19bc000961e2c5074ca378cdc5c5462303eadf746637f301a980955d
+oid sha256:8cf7e20eafdae9b08594183c008de117ef2680d73e44b2953a4fca9bf035c36e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27125517a0c7bcf909f13b74e17711f5312425549e93d73794d1f5a42045aa1b
+oid sha256:5f1bef454364e667119fab44e2e85cf50a9626a54fef8200895b8427b94197ec
 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": 0.8287287354469299,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.33812341504649196,
+  "best_metric": 0.8101484775543213,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6762468300929839,
   "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": 9.94,
       "eval_steps_per_second": 1.255,
       "step": 25
+    },
+    {
+      "epoch": 0.3516483516483517,
+      "grad_norm": 22.157114028930664,
+      "learning_rate": 5e-05,
+      "loss": 0.8506,
+      "step": 26
+    },
+    {
+      "epoch": 0.36517328825021134,
+      "grad_norm": 20.86341667175293,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.8551,
+      "step": 27
+    },
+    {
+      "epoch": 0.378698224852071,
+      "grad_norm": 16.98979377746582,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.8119,
+      "step": 28
+    },
+    {
+      "epoch": 0.39222316145393066,
+      "grad_norm": 23.05814552307129,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.8349,
+      "step": 29
+    },
+    {
+      "epoch": 0.4057480980557904,
+      "grad_norm": 11.545186996459961,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.8151,
+      "step": 30
+    },
+    {
+      "epoch": 0.41927303465765003,
+      "grad_norm": 15.064045906066895,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.815,
+      "step": 31
+    },
+    {
+      "epoch": 0.4327979712595097,
+      "grad_norm": 7.394914627075195,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8191,
+      "step": 32
+    },
+    {
+      "epoch": 0.4463229078613694,
+      "grad_norm": 14.583250045776367,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.8224,
+      "step": 33
+    },
+    {
+      "epoch": 0.45984784446322907,
+      "grad_norm": 16.12276268005371,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8024,
+      "step": 34
+    },
+    {
+      "epoch": 0.47337278106508873,
+      "grad_norm": 7.712066173553467,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.8027,
+      "step": 35
+    },
+    {
+      "epoch": 0.48689771766694845,
+      "grad_norm": 10.313910484313965,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8061,
+      "step": 36
+    },
+    {
+      "epoch": 0.5004226542688082,
+      "grad_norm": 11.785128593444824,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8099,
+      "step": 37
+    },
+    {
+      "epoch": 0.5139475908706678,
+      "grad_norm": 14.758973121643066,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.853,
+      "step": 38
+    },
+    {
+      "epoch": 0.5274725274725275,
+      "grad_norm": 16.421119689941406,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.8459,
+      "step": 39
+    },
+    {
+      "epoch": 0.5409974640743872,
+      "grad_norm": 14.737407684326172,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.812,
+      "step": 40
+    },
+    {
+      "epoch": 0.5545224006762468,
+      "grad_norm": 20.14451026916504,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.8267,
+      "step": 41
+    },
+    {
+      "epoch": 0.5680473372781065,
+      "grad_norm": 21.863866806030273,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8285,
+      "step": 42
+    },
+    {
+      "epoch": 0.5815722738799662,
+      "grad_norm": 11.37204360961914,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.8141,
+      "step": 43
+    },
+    {
+      "epoch": 0.5950972104818258,
+      "grad_norm": 5.559212684631348,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7995,
+      "step": 44
+    },
+    {
+      "epoch": 0.6086221470836856,
+      "grad_norm": 10.355339050292969,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.796,
+      "step": 45
+    },
+    {
+      "epoch": 0.6221470836855453,
+      "grad_norm": 10.827974319458008,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8014,
+      "step": 46
+    },
+    {
+      "epoch": 0.6356720202874049,
+      "grad_norm": 11.881269454956055,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.8132,
+      "step": 47
+    },
+    {
+      "epoch": 0.6491969568892646,
+      "grad_norm": 13.85914421081543,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8165,
+      "step": 48
+    },
+    {
+      "epoch": 0.6627218934911243,
+      "grad_norm": 16.662988662719727,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.8126,
+      "step": 49
+    },
+    {
+      "epoch": 0.6762468300929839,
+      "grad_norm": 9.382196426391602,
+      "learning_rate": 0.0,
+      "loss": 0.8089,
+      "step": 50
+    },
+    {
+      "epoch": 0.6762468300929839,
+      "eval_loss": 0.8101484775543213,
+      "eval_runtime": 33.7248,
+      "eval_samples_per_second": 14.796,
+      "eval_steps_per_second": 1.868,
+      "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": 2.631214808694784e+17,
+  "total_flos": 5.262429617389568e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null