Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94d20e7e6575534abd4af2ede79d4b9da5252bdf7c436bd2bfd50e4bd0dd6722
+oid sha256:305926bde55f5b13dbb7d777cfd69225b5a3e434834c2a6f2bafd24dd813fc39
 size 144748392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9969a96ef38544cb447007b23546b0ebb38a1841e1576c46e499779e532c31
+oid sha256:b6495433d524caa00935d97ff086a6319ba6aa443d3529ae3cbc55e4bdb8e053
 size 289690242

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e71fa7573c120e383ca630eec03d35cc7e5eb879a53db7739a83effb7452ca0
+oid sha256:8e02c163804d7ff88b73cf085713a817afd8a14dc280b9bf6db08996f802befd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd632b0a85ceeda04804b0bab58aa9ba2bcd881ae5936d0601869d525325203
+oid sha256:05b0ee202fc3d5f400dbcbb571d58ed9781eea09659b9943597df3756229c5ad
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ed3361f2ed09ffb2738f32d8bd397793db5978a9f02ceb35ebca27804f9ff44
+oid sha256:230e8ebd90f969d020b04133fde0fb502d2a1d6aa743cb5ec1ebab0b66d05834
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1afd5ff54c627052c3833d283766dd24092b06177831ff743d5fe285e37bb5bf
+oid sha256:b466cbaba96f05a4e2e91e61de947cc172780221e84bebb89ade993c59b5f81f
 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": 1.534497618675232,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09711094925952901,
+  "best_metric": 1.3836418390274048,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.19422189851905802,
   "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": 39.572,
       "eval_steps_per_second": 4.949,
       "step": 25
+    },
+    {
+      "epoch": 0.10099538722991017,
+      "grad_norm": 0.1270134299993515,
+      "learning_rate": 5e-05,
+      "loss": 0.7049,
+      "step": 26
+    },
+    {
+      "epoch": 0.10487982520029134,
+      "grad_norm": 0.13075926899909973,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7464,
+      "step": 27
+    },
+    {
+      "epoch": 0.10876426317067249,
+      "grad_norm": 0.15523023903369904,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9013,
+      "step": 28
+    },
+    {
+      "epoch": 0.11264870114105366,
+      "grad_norm": 0.15631172060966492,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9871,
+      "step": 29
+    },
+    {
+      "epoch": 0.11653313911143481,
+      "grad_norm": 0.17590728402137756,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.106,
+      "step": 30
+    },
+    {
+      "epoch": 0.12041757708181597,
+      "grad_norm": 0.22378630936145782,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.228,
+      "step": 31
+    },
+    {
+      "epoch": 0.12430201505219714,
+      "grad_norm": 0.3813501000404358,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2546,
+      "step": 32
+    },
+    {
+      "epoch": 0.1281864530225783,
+      "grad_norm": 1.0118165016174316,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.3369,
+      "step": 33
+    },
+    {
+      "epoch": 0.13207089099295946,
+      "grad_norm": 0.38092735409736633,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3886,
+      "step": 34
+    },
+    {
+      "epoch": 0.13595532896334062,
+      "grad_norm": 0.13921162486076355,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0392,
+      "step": 35
+    },
+    {
+      "epoch": 0.13983976693372177,
+      "grad_norm": 0.10157951712608337,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.975,
+      "step": 36
+    },
+    {
+      "epoch": 0.14372420490410293,
+      "grad_norm": 0.15304253995418549,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1748,
+      "step": 37
+    },
+    {
+      "epoch": 0.1476086428744841,
+      "grad_norm": 0.11945773661136627,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7164,
+      "step": 38
+    },
+    {
+      "epoch": 0.15149308084486526,
+      "grad_norm": 0.11390524357557297,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7256,
+      "step": 39
+    },
+    {
+      "epoch": 0.15537751881524642,
+      "grad_norm": 0.15027418732643127,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9102,
+      "step": 40
+    },
+    {
+      "epoch": 0.15926195678562757,
+      "grad_norm": 0.14749252796173096,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9521,
+      "step": 41
+    },
+    {
+      "epoch": 0.16314639475600873,
+      "grad_norm": 0.17073273658752441,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0067,
+      "step": 42
+    },
+    {
+      "epoch": 0.1670308327263899,
+      "grad_norm": 0.19954727590084076,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0895,
+      "step": 43
+    },
+    {
+      "epoch": 0.17091527069677107,
+      "grad_norm": 0.3001015782356262,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2653,
+      "step": 44
+    },
+    {
+      "epoch": 0.17479970866715222,
+      "grad_norm": 0.6356985569000244,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.5735,
+      "step": 45
+    },
+    {
+      "epoch": 0.17868414663753338,
+      "grad_norm": 3.531977653503418,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 5.085,
+      "step": 46
+    },
+    {
+      "epoch": 0.18256858460791453,
+      "grad_norm": 0.15248890221118927,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9541,
+      "step": 47
+    },
+    {
+      "epoch": 0.1864530225782957,
+      "grad_norm": 0.10179020464420319,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0162,
+      "step": 48
+    },
+    {
+      "epoch": 0.19033746054867687,
+      "grad_norm": 0.11615335941314697,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0128,
+      "step": 49
+    },
+    {
+      "epoch": 0.19422189851905802,
+      "grad_norm": 0.2607570290565491,
+      "learning_rate": 0.0,
+      "loss": 1.2386,
+      "step": 50
+    },
+    {
+      "epoch": 0.19422189851905802,
+      "eval_loss": 1.3836418390274048,
+      "eval_runtime": 43.9694,
+      "eval_samples_per_second": 39.459,
+      "eval_steps_per_second": 4.935,
+      "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": 1.1004865101902643e+17,
+  "total_flos": 2.195711408954409e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null