Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c738d9f2774e36eef94b3ce19c346f808be6a7a58565f881e6528b56133b143
+oid sha256:6b539c829146c71af5d32bbbd0c8daa57624f482d1d23fa1e805a006ce970b2b
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:247f94149d6050e00b5781720ba3a8542c28c6a38cc1a6d7277135eab15427fa
+oid sha256:91e4c6abba4f321bf5dd1eaf40c1dcf79c9c8cb8a20714e4c4415fb49b1f87e6
 size 147359892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84337a0b5baecd930c964daa54054e5734ed5e51c3d921251b77b2277716e16c
+oid sha256:17fdeb77d06dcedbaefd3bb0d7470406b3d6cbc5bb7b22f3c7cb407555ab75a4
 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": 2.1993303298950195,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017593244194229415,
+  "best_metric": 2.10509991645813,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03518648838845883,
   "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": 63.43,
       "eval_steps_per_second": 7.949,
       "step": 25
+    },
+    {
+      "epoch": 0.018296973961998593,
+      "grad_norm": 0.8108159899711609,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.185,
+      "step": 26
+    },
+    {
+      "epoch": 0.019000703729767768,
+      "grad_norm": 0.6874377727508545,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.1766,
+      "step": 27
+    },
+    {
+      "epoch": 0.019704433497536946,
+      "grad_norm": 0.7179682850837708,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.2221,
+      "step": 28
+    },
+    {
+      "epoch": 0.02040816326530612,
+      "grad_norm": 1.216280221939087,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.4166,
+      "step": 29
+    },
+    {
+      "epoch": 0.0211118930330753,
+      "grad_norm": 0.7951951622962952,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.0194,
+      "step": 30
+    },
+    {
+      "epoch": 0.021815622800844477,
+      "grad_norm": 0.6431245803833008,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.0918,
+      "step": 31
+    },
+    {
+      "epoch": 0.022519352568613652,
+      "grad_norm": 0.7210680842399597,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.1332,
+      "step": 32
+    },
+    {
+      "epoch": 0.02322308233638283,
+      "grad_norm": 0.7762433886528015,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.2283,
+      "step": 33
+    },
+    {
+      "epoch": 0.023926812104152005,
+      "grad_norm": 0.6160893440246582,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.0208,
+      "step": 34
+    },
+    {
+      "epoch": 0.024630541871921183,
+      "grad_norm": 0.9088425636291504,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.4412,
+      "step": 35
+    },
+    {
+      "epoch": 0.025334271639690358,
+      "grad_norm": 0.790292501449585,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.0857,
+      "step": 36
+    },
+    {
+      "epoch": 0.026038001407459536,
+      "grad_norm": 0.6113930940628052,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.9494,
+      "step": 37
+    },
+    {
+      "epoch": 0.02674173117522871,
+      "grad_norm": 0.6941695809364319,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.8067,
+      "step": 38
+    },
+    {
+      "epoch": 0.02744546094299789,
+      "grad_norm": 0.6881697177886963,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8486,
+      "step": 39
+    },
+    {
+      "epoch": 0.028149190710767064,
+      "grad_norm": 0.9811816811561584,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.9745,
+      "step": 40
+    },
+    {
+      "epoch": 0.028852920478536243,
+      "grad_norm": 0.8144062757492065,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.7651,
+      "step": 41
+    },
+    {
+      "epoch": 0.029556650246305417,
+      "grad_norm": 0.8490874171257019,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7061,
+      "step": 42
+    },
+    {
+      "epoch": 0.030260380014074596,
+      "grad_norm": 1.0510660409927368,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7503,
+      "step": 43
+    },
+    {
+      "epoch": 0.03096410978184377,
+      "grad_norm": 0.9851308465003967,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.8392,
+      "step": 44
+    },
+    {
+      "epoch": 0.03166783954961295,
+      "grad_norm": 1.0835424661636353,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.7826,
+      "step": 45
+    },
+    {
+      "epoch": 0.03237156931738212,
+      "grad_norm": 1.0677682161331177,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.0415,
+      "step": 46
+    },
+    {
+      "epoch": 0.033075299085151305,
+      "grad_norm": 1.1599544286727905,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0658,
+      "step": 47
+    },
+    {
+      "epoch": 0.03377902885292048,
+      "grad_norm": 1.6693414449691772,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2281,
+      "step": 48
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 2.1483304500579834,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.0819,
+      "step": 49
+    },
+    {
+      "epoch": 0.03518648838845883,
+      "grad_norm": 3.549574375152588,
+      "learning_rate": 0.0,
+      "loss": 2.8289,
+      "step": 50
+    },
+    {
+      "epoch": 0.03518648838845883,
+      "eval_loss": 2.10509991645813,
+      "eval_runtime": 37.6616,
+      "eval_samples_per_second": 63.566,
+      "eval_steps_per_second": 7.966,
+      "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": 4384478138990592.0,
+  "total_flos": 8520778270113792.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null