Training in progress, step 46, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80df2ee8b473304d8804e21fdea80aad637a8ce7f7fee7d00e07d52795bd5b41
+oid sha256:c1823c6558bc70ccdb844f8eb6ddbe9627270802f5fa74fd635a47e5f3b8a187
 size 239135488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b906dc34e90a6388d0c1a15433a5cd17b1c3e3bf06c75f745a0edab00c5a1917
+oid sha256:8cff9ed5a18e116170588e815011012110371c95c642ba79d5ed229fcc8eae77
 size 478528978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da124dfdd7288f41ef0267372fe0db647ed3b93cda51aef4c0cdf02543a1b56f
+oid sha256:ad346de393b69930cd98c2d9dddc522df1b6f98a1fade4ed7cea875d94c705ed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d48cdbb9d105adc3bb0ea6c176e5d727bd3d4503626c1854c5d652b11520e15
+oid sha256:ac1fc96886b8b36c0c4e12b54b517ec1b3b53a13740b77a2b657ee0fd87838e4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641ab8398bda456359862a5efb58165dc81801155740fd2d4e5627c64144a7ba
+oid sha256:08396b0649912549a5f42912420531e94ad2f2c261e62383dc76a8fae8784d6d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feb7d5312d25517ff2ded966d5b732b14796b9a2a0bc92939da1b2b91e25f992
+oid sha256:8ec40c3e114ae92aa2ccf7d0cc201894f246f53e9c45c1c047cd9733d4254bf0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43c559cbde9153c17d7a372e6ef412013941e6297ae86a5518b43caf90efbb1f
+oid sha256:b7f1ee7e5310274a73405630534a716def8b331763fa23521c74926adf94696e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 10.230134963989258,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.6597510373443982,
+  "epoch": 3.0539419087136928,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 46,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,153 @@
       "eval_samples_per_second": 46.001,
       "eval_steps_per_second": 5.863,
       "step": 25
+    },
+    {
+      "epoch": 1.7261410788381744,
+      "grad_norm": 10009876.0,
+      "learning_rate": 4.288425808633575e-05,
+      "loss": 9.8221,
+      "step": 26
+    },
+    {
+      "epoch": 1.79253112033195,
+      "grad_norm": 1833567125504.0,
+      "learning_rate": 3.937173552235117e-05,
+      "loss": 10.6954,
+      "step": 27
+    },
+    {
+      "epoch": 1.8589211618257262,
+      "grad_norm": 7885522944.0,
+      "learning_rate": 3.591337215792852e-05,
+      "loss": 10.5914,
+      "step": 28
+    },
+    {
+      "epoch": 1.9253112033195021,
+      "grad_norm": 196838768.0,
+      "learning_rate": 3.2526791020045086e-05,
+      "loss": 10.0468,
+      "step": 29
+    },
+    {
+      "epoch": 1.991701244813278,
+      "grad_norm": 40980312.0,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 9.7479,
+      "step": 30
+    },
+    {
+      "epoch": 2.0580912863070537,
+      "grad_norm": 6157641973760.0,
+      "learning_rate": 2.603755066399718e-05,
+      "loss": 21.479,
+      "step": 31
+    },
+    {
+      "epoch": 2.12448132780083,
+      "grad_norm": 1298229624832.0,
+      "learning_rate": 2.296795912722014e-05,
+      "loss": 10.2557,
+      "step": 32
+    },
+    {
+      "epoch": 2.190871369294606,
+      "grad_norm": 43450268.0,
+      "learning_rate": 2.0036116674432654e-05,
+      "loss": 10.0097,
+      "step": 33
+    },
+    {
+      "epoch": 2.2572614107883817,
+      "grad_norm": 14252696928256.0,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 10.0475,
+      "step": 34
+    },
+    {
+      "epoch": 2.323651452282158,
+      "grad_norm": 4905431990272.0,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.6978,
+      "step": 35
+    },
+    {
+      "epoch": 2.3900414937759336,
+      "grad_norm": 11096969216.0,
+      "learning_rate": 1.2212521282287092e-05,
+      "loss": 10.4763,
+      "step": 36
+    },
+    {
+      "epoch": 2.4564315352697097,
+      "grad_norm": 18013510.0,
+      "learning_rate": 9.972937953781986e-06,
+      "loss": 9.9847,
+      "step": 37
+    },
+    {
+      "epoch": 2.5228215767634854,
+      "grad_norm": Infinity,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 10.7616,
+      "step": 38
+    },
+    {
+      "epoch": 2.5892116182572615,
+      "grad_norm": 389528780800.0,
+      "learning_rate": 6.116050521637218e-06,
+      "loss": 10.8897,
+      "step": 39
+    },
+    {
+      "epoch": 2.6556016597510372,
+      "grad_norm": 3815046144.0,
+      "learning_rate": 4.5184002322740785e-06,
+      "loss": 10.2874,
+      "step": 40
+    },
+    {
+      "epoch": 2.7219917012448134,
+      "grad_norm": 168968592.0,
+      "learning_rate": 3.1525137500119207e-06,
+      "loss": 9.8601,
+      "step": 41
+    },
+    {
+      "epoch": 2.788381742738589,
+      "grad_norm": 9.61320969127854e+16,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 10.7902,
+      "step": 42
+    },
+    {
+      "epoch": 2.854771784232365,
+      "grad_norm": 2.7052631479916954e+18,
+      "learning_rate": 1.1426567014420297e-06,
+      "loss": 10.677,
+      "step": 43
+    },
+    {
+      "epoch": 2.921161825726141,
+      "grad_norm": 2165231360.0,
+      "learning_rate": 5.089279059533658e-07,
+      "loss": 9.9808,
+      "step": 44
+    },
+    {
+      "epoch": 2.987551867219917,
+      "grad_norm": 56432456.0,
+      "learning_rate": 1.2739426948732424e-07,
+      "loss": 9.6644,
+      "step": 45
+    },
+    {
+      "epoch": 3.0539419087136928,
+      "grad_norm": 175661498368.0,
+      "learning_rate": 0.0,
+      "loss": 20.672,
+      "step": 46
     }
   ],
   "logging_steps": 1,
@@ -221,12 +368,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.487279663087616e+17,
+  "total_flos": 2.7365945800812134e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null