Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5215dca261181749826a3409a6825682777b1d2c750a70b5d564ad9159e2f536
+oid sha256:923fa313d8679cc884c92aab0e426238c34dcd913d55a1197f539e4ab4f575f0
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ba348efa6c1f5dbb03283b9f10a0cde2d8f02d84cd076230e0dc1401ca4e38
+oid sha256:5afdfccaa55446d6a2f952332d16e23c4a36a2c21e96636162a91c019de4560e
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407f5c9b6af2a742f731abbb266c70fdf14e42c85315e2e37dbf2d700405b585
+oid sha256:d646911cbd5472e15899709713a62f2f25707fa75757266e6f364923e2551d50
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e075d53a3d4b24eee9eac689f3415da502ff4dfd26a7a144abd59edf54d785d8
+oid sha256:2185c32880d6a7747cdd043a3c72783f1c8962b825ef99f73a9b9d6d4e5a5769
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fab25c64beb86817a5eeb89ecf3ef80c52c9067619ed5e28f9d0737cb141453
+oid sha256:bb6052e9cf4e51930110d54a18dceb701117bc7a68af032316c5b9dbef39ecfd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c6015c683fcdb7aea20c3f97af5254c34603aacf08d74b194e2530e892247ac
+oid sha256:6749a48bc4d357716a540f53e7b545d2810ac8d731e12351668e1e57f87726a4
 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": 1.759958028793335,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08362952122099102,
+  "best_metric": 1.5961111783981323,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.16725904244198203,
   "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": 19.283,
       "eval_steps_per_second": 2.413,
       "step": 25
+    },
+    {
+      "epoch": 0.08697470206983066,
+      "grad_norm": 1.0084614753723145,
+      "learning_rate": 5e-05,
+      "loss": 1.6066,
+      "step": 26
+    },
+    {
+      "epoch": 0.0903198829186703,
+      "grad_norm": 1.0460926294326782,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.6602,
+      "step": 27
+    },
+    {
+      "epoch": 0.09366506376750994,
+      "grad_norm": 1.0078924894332886,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6295,
+      "step": 28
+    },
+    {
+      "epoch": 0.09701024461634958,
+      "grad_norm": 1.0543190240859985,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6352,
+      "step": 29
+    },
+    {
+      "epoch": 0.10035542546518922,
+      "grad_norm": 1.0644540786743164,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6549,
+      "step": 30
+    },
+    {
+      "epoch": 0.10370060631402885,
+      "grad_norm": 1.1043634414672852,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7471,
+      "step": 31
+    },
+    {
+      "epoch": 0.10704578716286849,
+      "grad_norm": 1.1335960626602173,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.7029,
+      "step": 32
+    },
+    {
+      "epoch": 0.11039096801170813,
+      "grad_norm": 1.2425991296768188,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.7174,
+      "step": 33
+    },
+    {
+      "epoch": 0.11373614886054777,
+      "grad_norm": 1.2737070322036743,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.718,
+      "step": 34
+    },
+    {
+      "epoch": 0.11708132970938741,
+      "grad_norm": 1.4903675317764282,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6766,
+      "step": 35
+    },
+    {
+      "epoch": 0.12042651055822705,
+      "grad_norm": 1.6684659719467163,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.6386,
+      "step": 36
+    },
+    {
+      "epoch": 0.12377169140706669,
+      "grad_norm": 2.2402453422546387,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8643,
+      "step": 37
+    },
+    {
+      "epoch": 0.12711687225590634,
+      "grad_norm": 1.0088212490081787,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5225,
+      "step": 38
+    },
+    {
+      "epoch": 0.13046205310474598,
+      "grad_norm": 0.778500497341156,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.46,
+      "step": 39
+    },
+    {
+      "epoch": 0.13380723395358562,
+      "grad_norm": 0.8704653382301331,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5428,
+      "step": 40
+    },
+    {
+      "epoch": 0.13715241480242527,
+      "grad_norm": 0.9207085371017456,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.6426,
+      "step": 41
+    },
+    {
+      "epoch": 0.1404975956512649,
+      "grad_norm": 0.9859210848808289,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.6149,
+      "step": 42
+    },
+    {
+      "epoch": 0.14384277650010455,
+      "grad_norm": 1.0169706344604492,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.5638,
+      "step": 43
+    },
+    {
+      "epoch": 0.1471879573489442,
+      "grad_norm": 1.1154978275299072,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6267,
+      "step": 44
+    },
+    {
+      "epoch": 0.15053313819778383,
+      "grad_norm": 1.179999589920044,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.6497,
+      "step": 45
+    },
+    {
+      "epoch": 0.15387831904662347,
+      "grad_norm": 1.3208422660827637,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5948,
+      "step": 46
+    },
+    {
+      "epoch": 0.1572234998954631,
+      "grad_norm": 1.452532410621643,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.6376,
+      "step": 47
+    },
+    {
+      "epoch": 0.16056868074430275,
+      "grad_norm": 1.700157880783081,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.7256,
+      "step": 48
+    },
+    {
+      "epoch": 0.1639138615931424,
+      "grad_norm": 2.0633585453033447,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.7677,
+      "step": 49
+    },
+    {
+      "epoch": 0.16725904244198203,
+      "grad_norm": 3.042532205581665,
+      "learning_rate": 0.0,
+      "loss": 2.0048,
+      "step": 50
+    },
+    {
+      "epoch": 0.16725904244198203,
+      "eval_loss": 1.5961111783981323,
+      "eval_runtime": 104.3423,
+      "eval_samples_per_second": 19.302,
+      "eval_steps_per_second": 2.415,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null