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:bc99545f5f606083171e3e214161c806e265dc509596c89856f1f2efc86d2856
+oid sha256:d275af3079f6e3a4ce6cf952a0659462d83ffd7c985691663f084e77b4adf514
 size 479005064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0aafd564f876973adefb8fcbec5c40b266969f2e99c3ef445107a8152e23790f
+oid sha256:e39f4c90c4236769566e06a23141ff6ad32ed0264f9653faf7d85322ae026cbd
 size 243802484

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b715564a2df94f5d8473ca535b9a73d646270d5b66bba192ceb60cd8170ea8f5
+oid sha256:7b617580621838811c20b6fedce3e82eae4dc24b7ba784e9efb5ec8c67845aaa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2763649821281433,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016909029421711193,
+  "best_metric": 0.12468638271093369,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.033818058843422386,
   "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": 28.393,
       "eval_steps_per_second": 3.558,
       "step": 25
+    },
+    {
+      "epoch": 0.01758539059857964,
+      "grad_norm": 2.093113660812378,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.25,
+      "step": 26
+    },
+    {
+      "epoch": 0.01826175177544809,
+      "grad_norm": 1.6162835359573364,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2373,
+      "step": 27
+    },
+    {
+      "epoch": 0.018938112952316538,
+      "grad_norm": 1.4689679145812988,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.1982,
+      "step": 28
+    },
+    {
+      "epoch": 0.019614474129184985,
+      "grad_norm": 0.8921065926551819,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.156,
+      "step": 29
+    },
+    {
+      "epoch": 0.020290835306053433,
+      "grad_norm": 0.7960008978843689,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.1295,
+      "step": 30
+    },
+    {
+      "epoch": 0.02096719648292188,
+      "grad_norm": 0.8615506291389465,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.1504,
+      "step": 31
+    },
+    {
+      "epoch": 0.021643557659790327,
+      "grad_norm": 0.9851981997489929,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1528,
+      "step": 32
+    },
+    {
+      "epoch": 0.022319918836658775,
+      "grad_norm": 0.8852011561393738,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.163,
+      "step": 33
+    },
+    {
+      "epoch": 0.022996280013527222,
+      "grad_norm": 0.9167941212654114,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.1478,
+      "step": 34
+    },
+    {
+      "epoch": 0.023672641190395673,
+      "grad_norm": 0.6924282312393188,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1175,
+      "step": 35
+    },
+    {
+      "epoch": 0.02434900236726412,
+      "grad_norm": 0.7075855135917664,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0975,
+      "step": 36
+    },
+    {
+      "epoch": 0.025025363544132567,
+      "grad_norm": 0.8667000532150269,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0851,
+      "step": 37
+    },
+    {
+      "epoch": 0.025701724721001015,
+      "grad_norm": 0.6054403781890869,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0999,
+      "step": 38
+    },
+    {
+      "epoch": 0.026378085897869462,
+      "grad_norm": 0.723283588886261,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.1018,
+      "step": 39
+    },
+    {
+      "epoch": 0.02705444707473791,
+      "grad_norm": 0.8060293793678284,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0908,
+      "step": 40
+    },
+    {
+      "epoch": 0.027730808251606356,
+      "grad_norm": 1.0525263547897339,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.126,
+      "step": 41
+    },
+    {
+      "epoch": 0.028407169428474807,
+      "grad_norm": 0.8337423205375671,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.1003,
+      "step": 42
+    },
+    {
+      "epoch": 0.029083530605343254,
+      "grad_norm": 0.7337478995323181,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.1106,
+      "step": 43
+    },
+    {
+      "epoch": 0.029759891782211702,
+      "grad_norm": 0.8262754678726196,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.1441,
+      "step": 44
+    },
+    {
+      "epoch": 0.03043625295908015,
+      "grad_norm": 0.834556519985199,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.1245,
+      "step": 45
+    },
+    {
+      "epoch": 0.031112614135948596,
+      "grad_norm": 1.1409804821014404,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.1717,
+      "step": 46
+    },
+    {
+      "epoch": 0.03178897531281705,
+      "grad_norm": 0.7930788397789001,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1191,
+      "step": 47
+    },
+    {
+      "epoch": 0.03246533648968549,
+      "grad_norm": 0.903258740901947,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.1307,
+      "step": 48
+    },
+    {
+      "epoch": 0.03314169766655394,
+      "grad_norm": 1.2521153688430786,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.169,
+      "step": 49
+    },
+    {
+      "epoch": 0.033818058843422386,
+      "grad_norm": 1.3574105501174927,
+      "learning_rate": 0.0,
+      "loss": 0.172,
+      "step": 50
+    },
+    {
+      "epoch": 0.033818058843422386,
+      "eval_loss": 0.12468638271093369,
+      "eval_runtime": 87.9013,
+      "eval_samples_per_second": 28.327,
+      "eval_steps_per_second": 3.549,
+      "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": 1.42270858788864e+16,
+  "total_flos": 2.1554035106512896e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null