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:b257b0aa3f93b414661123f6f6bb9931f18863a3f24f006b6ed912ccf42512ce
+oid sha256:9f357683c05c2a61d7b9c183828e6103ddd95f91088e6ccd1b07f1b6b120ddf4
 size 838906392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6eedbbde8c88e00b42aee4aa5ad60c108975796b576ac9ff9ec06f33a09874
+oid sha256:3db8bccf7d200a261f7e56cc85952181324d5366ea0c94069759470409c83b12
 size 426360596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe8a72c141624911116574e1c046861acdb955188b9881493b1485dbd054ebf3
+oid sha256:79d74d9f266b885939ffcb4edcb7135c6b734dbc4a4de6ec5bb7dc7a45cb7195
 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": 1.3148045539855957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016254876462938883,
+  "best_metric": 1.2328124046325684,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.032509752925877766,
   "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": 13.592,
       "eval_steps_per_second": 1.7,
       "step": 25
+    },
+    {
+      "epoch": 0.016905071521456438,
+      "grad_norm": 1.3741412162780762,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 5.0185,
+      "step": 26
+    },
+    {
+      "epoch": 0.017555266579973992,
+      "grad_norm": 1.4687423706054688,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 5.09,
+      "step": 27
+    },
+    {
+      "epoch": 0.018205461638491547,
+      "grad_norm": 1.4390546083450317,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 5.0276,
+      "step": 28
+    },
+    {
+      "epoch": 0.0188556566970091,
+      "grad_norm": 1.5843408107757568,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 4.9976,
+      "step": 29
+    },
+    {
+      "epoch": 0.01950585175552666,
+      "grad_norm": 1.655975580215454,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 5.2854,
+      "step": 30
+    },
+    {
+      "epoch": 0.020156046814044214,
+      "grad_norm": 1.896105408668518,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 5.1154,
+      "step": 31
+    },
+    {
+      "epoch": 0.02080624187256177,
+      "grad_norm": 1.8617236614227295,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 5.1433,
+      "step": 32
+    },
+    {
+      "epoch": 0.021456436931079324,
+      "grad_norm": 2.0548999309539795,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 5.1657,
+      "step": 33
+    },
+    {
+      "epoch": 0.022106631989596878,
+      "grad_norm": 2.310459852218628,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 4.9047,
+      "step": 34
+    },
+    {
+      "epoch": 0.022756827048114433,
+      "grad_norm": 2.390486478805542,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.6746,
+      "step": 35
+    },
+    {
+      "epoch": 0.02340702210663199,
+      "grad_norm": 2.648507595062256,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 5.4504,
+      "step": 36
+    },
+    {
+      "epoch": 0.024057217165149546,
+      "grad_norm": 2.5374722480773926,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 5.028,
+      "step": 37
+    },
+    {
+      "epoch": 0.0247074122236671,
+      "grad_norm": 2.749431848526001,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 5.2102,
+      "step": 38
+    },
+    {
+      "epoch": 0.025357607282184655,
+      "grad_norm": 2.9381508827209473,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 5.0799,
+      "step": 39
+    },
+    {
+      "epoch": 0.02600780234070221,
+      "grad_norm": 3.226975440979004,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 5.2455,
+      "step": 40
+    },
+    {
+      "epoch": 0.026657997399219768,
+      "grad_norm": 3.4696147441864014,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 5.1061,
+      "step": 41
+    },
+    {
+      "epoch": 0.027308192457737322,
+      "grad_norm": 3.6344780921936035,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 5.271,
+      "step": 42
+    },
+    {
+      "epoch": 0.027958387516254877,
+      "grad_norm": 3.3182501792907715,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.8516,
+      "step": 43
+    },
+    {
+      "epoch": 0.02860858257477243,
+      "grad_norm": 3.655830144882202,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 4.6502,
+      "step": 44
+    },
+    {
+      "epoch": 0.029258777633289986,
+      "grad_norm": 3.9722137451171875,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.9073,
+      "step": 45
+    },
+    {
+      "epoch": 0.02990897269180754,
+      "grad_norm": 4.2687506675720215,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 4.9314,
+      "step": 46
+    },
+    {
+      "epoch": 0.0305591677503251,
+      "grad_norm": 4.744618892669678,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 5.4635,
+      "step": 47
+    },
+    {
+      "epoch": 0.031209362808842653,
+      "grad_norm": 5.328568458557129,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 6.124,
+      "step": 48
+    },
+    {
+      "epoch": 0.03185955786736021,
+      "grad_norm": 5.584743022918701,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 5.83,
+      "step": 49
+    },
+    {
+      "epoch": 0.032509752925877766,
+      "grad_norm": 6.429695129394531,
+      "learning_rate": 0.0,
+      "loss": 6.3232,
+      "step": 50
+    },
+    {
+      "epoch": 0.032509752925877766,
+      "eval_loss": 1.2328124046325684,
+      "eval_runtime": 190.844,
+      "eval_samples_per_second": 13.577,
+      "eval_steps_per_second": 1.698,
+      "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": 5.88748123275264e+16,
+  "total_flos": 9.06990352072704e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null