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:da840809cb499a0f3a9f2a28e7e81e18f847f5eb08eded00a6784061f8e16a7a
+oid sha256:e49130569d2b403c7818ecb47283bed19d3213a82280b34a9bb02bbe3e6f6457
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd1364c9800f6c847dc4f2e87b8333e9808fa330be2b536be9e35d85b60073c
+oid sha256:9b20b518719c076c44f9cc777e5c87b9290821c15c2ad56858ff2bf07d8df052
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16d78e5103d1ae31795f05170dd1970e73bbc2d01fc52b3cd623de2f6df7d8e3
+oid sha256:6145e14b286899fb3639a20bdd7bea93b8cb93230b2b4b487d8437fb28227578
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bacc6724eb17da2ad5388c325845138a53aee03eb399fad162e0b55838cb5cc
+oid sha256:680c2975a09fc26151ce5abd99e24fd3331886ffb6580f605f9f3d26c1cf284a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6a399cc1cb072293948d300c74926aa65a38e3e71ef1535cca34a194002aab0
+oid sha256:91020138e6866123b7a586f2dddc248b44df80a97b7d44bcb35fb68a7e5fa152
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc4b1166df2a6794902bc1f55262970d808320d3a8a225d6c0347e6b7a649734
+oid sha256:8d9beb2ddd0baa1be9df6571e27a77bfc156ccdd6e2d48412742e84a40e91108
 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": 5.067764759063721,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.91324200913242,
+  "best_metric": 4.699856281280518,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.82648401826484,
   "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": 21.734,
       "eval_steps_per_second": 2.82,
       "step": 25
+    },
+    {
+      "epoch": 0.9497716894977168,
+      "grad_norm": 1.1494016647338867,
+      "learning_rate": 5e-05,
+      "loss": 4.9949,
+      "step": 26
+    },
+    {
+      "epoch": 0.9863013698630136,
+      "grad_norm": 1.3044017553329468,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 5.4347,
+      "step": 27
+    },
+    {
+      "epoch": 1.0228310502283104,
+      "grad_norm": 1.5397518873214722,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 8.0895,
+      "step": 28
+    },
+    {
+      "epoch": 1.0593607305936072,
+      "grad_norm": 0.9091172218322754,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 4.8388,
+      "step": 29
+    },
+    {
+      "epoch": 1.095890410958904,
+      "grad_norm": 1.22693932056427,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 4.8633,
+      "step": 30
+    },
+    {
+      "epoch": 1.1324200913242009,
+      "grad_norm": 1.2246487140655518,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 4.8881,
+      "step": 31
+    },
+    {
+      "epoch": 1.1689497716894977,
+      "grad_norm": 0.8879066705703735,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 4.8103,
+      "step": 32
+    },
+    {
+      "epoch": 1.2054794520547945,
+      "grad_norm": 0.7668063044548035,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 5.0477,
+      "step": 33
+    },
+    {
+      "epoch": 1.2420091324200913,
+      "grad_norm": 0.7298935055732727,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.6508,
+      "step": 34
+    },
+    {
+      "epoch": 1.278538812785388,
+      "grad_norm": 1.2785840034484863,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 5.7769,
+      "step": 35
+    },
+    {
+      "epoch": 1.3150684931506849,
+      "grad_norm": 0.949729859828949,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.7667,
+      "step": 36
+    },
+    {
+      "epoch": 1.3515981735159817,
+      "grad_norm": 0.7023199200630188,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.7287,
+      "step": 37
+    },
+    {
+      "epoch": 1.3881278538812785,
+      "grad_norm": 0.6441393494606018,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.7706,
+      "step": 38
+    },
+    {
+      "epoch": 1.4246575342465753,
+      "grad_norm": 0.7533347606658936,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 4.6801,
+      "step": 39
+    },
+    {
+      "epoch": 1.461187214611872,
+      "grad_norm": 0.8559792637825012,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 5.0761,
+      "step": 40
+    },
+    {
+      "epoch": 1.4977168949771689,
+      "grad_norm": 0.5455217957496643,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.2281,
+      "step": 41
+    },
+    {
+      "epoch": 1.5342465753424657,
+      "grad_norm": 0.8446364998817444,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 5.7794,
+      "step": 42
+    },
+    {
+      "epoch": 1.5707762557077625,
+      "grad_norm": 0.6307662129402161,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 4.5922,
+      "step": 43
+    },
+    {
+      "epoch": 1.6073059360730593,
+      "grad_norm": 0.5937629342079163,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.7273,
+      "step": 44
+    },
+    {
+      "epoch": 1.643835616438356,
+      "grad_norm": 0.5854556560516357,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 4.6734,
+      "step": 45
+    },
+    {
+      "epoch": 1.6803652968036529,
+      "grad_norm": 0.6003574132919312,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.6983,
+      "step": 46
+    },
+    {
+      "epoch": 1.7168949771689497,
+      "grad_norm": 0.6816158294677734,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 5.2173,
+      "step": 47
+    },
+    {
+      "epoch": 1.7534246575342465,
+      "grad_norm": 0.49603208899497986,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.7616,
+      "step": 48
+    },
+    {
+      "epoch": 1.7899543378995433,
+      "grad_norm": 0.6312745809555054,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.9952,
+      "step": 49
+    },
+    {
+      "epoch": 1.82648401826484,
+      "grad_norm": 0.569425106048584,
+      "learning_rate": 0.0,
+      "loss": 4.5945,
+      "step": 50
+    },
+    {
+      "epoch": 1.82648401826484,
+      "eval_loss": 4.699856281280518,
+      "eval_runtime": 8.4954,
+      "eval_samples_per_second": 21.776,
+      "eval_steps_per_second": 2.825,
+      "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": 4.5449417477586944e+17,
+  "total_flos": 8.945766995329024e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null