Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428e955bbede31d05cbdff0c32030129e1c11ce3d7ca4c7cf8ce3ad3659435fc
+oid sha256:f946888c0dab4d8d97db807bbbc2830ab4fea1903d214fee15db3070186a1858
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c9711937ce41dcd72ee2e35196e1d77217c2542566a2c23077bd381b26038
+oid sha256:4c79bca2114ed6743c3244833ef2af17d4863b23e3b7baf9923160383b239ff3
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8724b2e7ed891a79c9869570ca4e624b32f20b400ff46b49b7d1399574016125
+oid sha256:2f91aa5becd9b8092ed131cffb9a2d5d92f135f9915262f2439d08d34eae3b96
 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": 3.111262798309326,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004969191015702644,
+  "best_metric": 3.0149381160736084,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.009938382031405287,
   "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": 126.255,
       "eval_steps_per_second": 15.793,
       "step": 25
+    },
+    {
+      "epoch": 0.00516795865633075,
+      "grad_norm": 0.3099224269390106,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 3.1568,
+      "step": 26
+    },
+    {
+      "epoch": 0.005366726296958855,
+      "grad_norm": 0.2683943808078766,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.3075,
+      "step": 27
+    },
+    {
+      "epoch": 0.005565493937586961,
+      "grad_norm": 0.290770560503006,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 3.1469,
+      "step": 28
+    },
+    {
+      "epoch": 0.005764261578215067,
+      "grad_norm": 0.2689608931541443,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 3.1745,
+      "step": 29
+    },
+    {
+      "epoch": 0.005963029218843173,
+      "grad_norm": 0.27947020530700684,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.1196,
+      "step": 30
+    },
+    {
+      "epoch": 0.006161796859471278,
+      "grad_norm": 0.3059743344783783,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 3.2627,
+      "step": 31
+    },
+    {
+      "epoch": 0.006360564500099384,
+      "grad_norm": 0.2834652066230774,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.0715,
+      "step": 32
+    },
+    {
+      "epoch": 0.00655933214072749,
+      "grad_norm": 0.31416839361190796,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 3.1854,
+      "step": 33
+    },
+    {
+      "epoch": 0.006758099781355596,
+      "grad_norm": 0.3347357213497162,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 3.1765,
+      "step": 34
+    },
+    {
+      "epoch": 0.006956867421983701,
+      "grad_norm": 0.30826708674430847,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.223,
+      "step": 35
+    },
+    {
+      "epoch": 0.007155635062611807,
+      "grad_norm": 0.32336822152137756,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.3838,
+      "step": 36
+    },
+    {
+      "epoch": 0.007354402703239913,
+      "grad_norm": 0.3186890482902527,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.1607,
+      "step": 37
+    },
+    {
+      "epoch": 0.007553170343868018,
+      "grad_norm": 0.330779105424881,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.2356,
+      "step": 38
+    },
+    {
+      "epoch": 0.007751937984496124,
+      "grad_norm": 0.3563855290412903,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 3.1177,
+      "step": 39
+    },
+    {
+      "epoch": 0.007950705625124229,
+      "grad_norm": 0.36722344160079956,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.0539,
+      "step": 40
+    },
+    {
+      "epoch": 0.008149473265752336,
+      "grad_norm": 0.3383886516094208,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.2582,
+      "step": 41
+    },
+    {
+      "epoch": 0.008348240906380441,
+      "grad_norm": 0.35494890809059143,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.0954,
+      "step": 42
+    },
+    {
+      "epoch": 0.008547008547008548,
+      "grad_norm": 0.3515838086605072,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.3631,
+      "step": 43
+    },
+    {
+      "epoch": 0.008745776187636653,
+      "grad_norm": 0.37979280948638916,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.3569,
+      "step": 44
+    },
+    {
+      "epoch": 0.008944543828264758,
+      "grad_norm": 0.3924817144870758,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.2494,
+      "step": 45
+    },
+    {
+      "epoch": 0.009143311468892865,
+      "grad_norm": 0.39909616112709045,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.3279,
+      "step": 46
+    },
+    {
+      "epoch": 0.00934207910952097,
+      "grad_norm": 0.46893322467803955,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.1981,
+      "step": 47
+    },
+    {
+      "epoch": 0.009540846750149075,
+      "grad_norm": 0.4818413555622101,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.4108,
+      "step": 48
+    },
+    {
+      "epoch": 0.009739614390777182,
+      "grad_norm": 0.6217837333679199,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 3.674,
+      "step": 49
+    },
+    {
+      "epoch": 0.009938382031405287,
+      "grad_norm": 0.9694095253944397,
+      "learning_rate": 0.0,
+      "loss": 4.1192,
+      "step": 50
+    },
+    {
+      "epoch": 0.009938382031405287,
+      "eval_loss": 3.0149381160736084,
+      "eval_runtime": 67.076,
+      "eval_samples_per_second": 126.334,
+      "eval_steps_per_second": 15.803,
+      "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": 867196041953280.0,
+  "total_flos": 1725805984481280.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null