Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3b02e5a8c81385fa5730d91eec1f14fbe046d57d21dcf5391b425a35528ef4
+oid sha256:c1afb5528764f97cb93e85b9267e7a23fc8db10f908fb5a7fdee37b76bef9f73
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83a78435948da02d0cfa2d138f2d061af3b393de6b59272634764631184d9880
+oid sha256:ba3bf94ecbe814b006d1595fe76a7d535c3736137822c39b65a0bb41f46c9601
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:649cd8467234002353c8643765e2e073c3d57ce20df0bf1d47dc8b4d1669a785
+oid sha256:716aeefc26106e191b2eacef505040b949619326ca2973c87a2df5acccdb4af8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27fe026d1f0bfa9e715bf072c9dd04c59fb973ca2835a964bcee6c0d272867ed
+oid sha256:827993c581d1e22faad2c0b522a2cc4a4a00367a71af53c7376eff45872230fd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d1607d42ef732a2eb543c798094b4def3ac7363d63811800f2014af9d670e10
+oid sha256:a5e901111619025248001ee05146decc6694db03440c46b9b542a6a36d96cd53
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbdcd1f296bf3834cc6ddeaca7cf26e7e17c3cb392c44cdb38cf3c6a84a268cb
+oid sha256:41dd978a125c40a847e37e145e4fc678414eda57f203a3dc2ce6808a3ad5c934
 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": 0.7421436905860901,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.408450704225352,
+  "best_metric": 0.716481626033783,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.816901408450704,
   "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": 55.5,
       "eval_steps_per_second": 6.938,
       "step": 25
+    },
+    {
+      "epoch": 1.4647887323943662,
+      "grad_norm": 1.5912657976150513,
+      "learning_rate": 5e-05,
+      "loss": 0.7874,
+      "step": 26
+    },
+    {
+      "epoch": 1.5211267605633803,
+      "grad_norm": 1.138702392578125,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.7531,
+      "step": 27
+    },
+    {
+      "epoch": 1.5774647887323945,
+      "grad_norm": 0.9520484209060669,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7584,
+      "step": 28
+    },
+    {
+      "epoch": 1.6338028169014085,
+      "grad_norm": 1.482550859451294,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7781,
+      "step": 29
+    },
+    {
+      "epoch": 1.6901408450704225,
+      "grad_norm": 0.8596436381340027,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7772,
+      "step": 30
+    },
+    {
+      "epoch": 1.7464788732394365,
+      "grad_norm": 0.9368801116943359,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.768,
+      "step": 31
+    },
+    {
+      "epoch": 1.8028169014084507,
+      "grad_norm": 0.8733591437339783,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7354,
+      "step": 32
+    },
+    {
+      "epoch": 1.8591549295774648,
+      "grad_norm": 1.732266902923584,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7553,
+      "step": 33
+    },
+    {
+      "epoch": 1.915492957746479,
+      "grad_norm": 1.1270034313201904,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7765,
+      "step": 34
+    },
+    {
+      "epoch": 1.971830985915493,
+      "grad_norm": 1.083901286125183,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7909,
+      "step": 35
+    },
+    {
+      "epoch": 2.028169014084507,
+      "grad_norm": 1.0652735233306885,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8403,
+      "step": 36
+    },
+    {
+      "epoch": 2.084507042253521,
+      "grad_norm": 1.8014781475067139,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.7262,
+      "step": 37
+    },
+    {
+      "epoch": 2.140845070422535,
+      "grad_norm": 1.0287795066833496,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7236,
+      "step": 38
+    },
+    {
+      "epoch": 2.1971830985915495,
+      "grad_norm": 1.676100254058838,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.7232,
+      "step": 39
+    },
+    {
+      "epoch": 2.2535211267605635,
+      "grad_norm": 1.5167391300201416,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7333,
+      "step": 40
+    },
+    {
+      "epoch": 2.3098591549295775,
+      "grad_norm": 1.1935371160507202,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7378,
+      "step": 41
+    },
+    {
+      "epoch": 2.3661971830985915,
+      "grad_norm": 1.1125164031982422,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7881,
+      "step": 42
+    },
+    {
+      "epoch": 2.4225352112676055,
+      "grad_norm": 1.0918306112289429,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7375,
+      "step": 43
+    },
+    {
+      "epoch": 2.4788732394366195,
+      "grad_norm": 1.167810082435608,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7953,
+      "step": 44
+    },
+    {
+      "epoch": 2.535211267605634,
+      "grad_norm": 1.1466361284255981,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.731,
+      "step": 45
+    },
+    {
+      "epoch": 2.591549295774648,
+      "grad_norm": 1.0590171813964844,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7392,
+      "step": 46
+    },
+    {
+      "epoch": 2.647887323943662,
+      "grad_norm": 1.1092512607574463,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7355,
+      "step": 47
+    },
+    {
+      "epoch": 2.704225352112676,
+      "grad_norm": 2.051265001296997,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.8236,
+      "step": 48
+    },
+    {
+      "epoch": 2.76056338028169,
+      "grad_norm": 1.2893011569976807,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7104,
+      "step": 49
+    },
+    {
+      "epoch": 2.816901408450704,
+      "grad_norm": 0.5748360753059387,
+      "learning_rate": 0.0,
+      "loss": 0.7456,
+      "step": 50
+    },
+    {
+      "epoch": 2.816901408450704,
+      "eval_loss": 0.716481626033783,
+      "eval_runtime": 2.1639,
+      "eval_samples_per_second": 55.454,
+      "eval_steps_per_second": 6.932,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null