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:de3ad745267d78d784828ff09df756814f225f21b732d31389847c918b771539
+oid sha256:dfb8ccccfc230d6a511d22df5a2b72e8dd412ed82a8c6a24d1688f2c3c1957bf
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f02beba8f5dfb943e883ba2c1ba057160d4596b7d80c5a51fb0660e2ccb5478c
+oid sha256:771754dbb117e3d7e9a1c3319463225820330403b2a178afeff419356c334e3b
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c46dea5412be6c535ec4f416bbbd89bf1124a4ac2c56cb2a93c5a7f86824620d
+oid sha256:1c02f6fcbec44fad49149f2bd77ed83553ef9d96496188e4168cbdfe5ead7f43
 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": 0.6671332120895386,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009903931860948796,
+  "best_metric": 0.6597008109092712,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.019807863721897592,
   "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": 27.141,
       "eval_steps_per_second": 3.396,
       "step": 25
+    },
+    {
+      "epoch": 0.010300089135386749,
+      "grad_norm": 12.529690742492676,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.8625,
+      "step": 26
+    },
+    {
+      "epoch": 0.0106962464098247,
+      "grad_norm": 10.027824401855469,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.5588,
+      "step": 27
+    },
+    {
+      "epoch": 0.011092403684262652,
+      "grad_norm": 10.082047462463379,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.4771,
+      "step": 28
+    },
+    {
+      "epoch": 0.011488560958700603,
+      "grad_norm": 11.15814208984375,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.4113,
+      "step": 29
+    },
+    {
+      "epoch": 0.011884718233138556,
+      "grad_norm": 10.759804725646973,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.8421,
+      "step": 30
+    },
+    {
+      "epoch": 0.012280875507576509,
+      "grad_norm": 10.599135398864746,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.6885,
+      "step": 31
+    },
+    {
+      "epoch": 0.01267703278201446,
+      "grad_norm": 11.816875457763672,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.0024,
+      "step": 32
+    },
+    {
+      "epoch": 0.013073190056452412,
+      "grad_norm": 10.234508514404297,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.0345,
+      "step": 33
+    },
+    {
+      "epoch": 0.013469347330890363,
+      "grad_norm": 12.437875747680664,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.7898,
+      "step": 34
+    },
+    {
+      "epoch": 0.013865504605328316,
+      "grad_norm": 10.455293655395508,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.2859,
+      "step": 35
+    },
+    {
+      "epoch": 0.014261661879766267,
+      "grad_norm": 10.511425971984863,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.2994,
+      "step": 36
+    },
+    {
+      "epoch": 0.01465781915420422,
+      "grad_norm": 11.496809959411621,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.7418,
+      "step": 37
+    },
+    {
+      "epoch": 0.01505397642864217,
+      "grad_norm": 13.628725051879883,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.0457,
+      "step": 38
+    },
+    {
+      "epoch": 0.015450133703080123,
+      "grad_norm": 13.12936782836914,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.5216,
+      "step": 39
+    },
+    {
+      "epoch": 0.015846290977518076,
+      "grad_norm": 10.766741752624512,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.3881,
+      "step": 40
+    },
+    {
+      "epoch": 0.016242448251956025,
+      "grad_norm": 15.045173645019531,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.1368,
+      "step": 41
+    },
+    {
+      "epoch": 0.016638605526393978,
+      "grad_norm": 10.670278549194336,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.4484,
+      "step": 42
+    },
+    {
+      "epoch": 0.01703476280083193,
+      "grad_norm": 14.797165870666504,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.4172,
+      "step": 43
+    },
+    {
+      "epoch": 0.017430920075269883,
+      "grad_norm": 12.900824546813965,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.7403,
+      "step": 44
+    },
+    {
+      "epoch": 0.017827077349707832,
+      "grad_norm": 12.451089859008789,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.1842,
+      "step": 45
+    },
+    {
+      "epoch": 0.018223234624145785,
+      "grad_norm": 14.523232460021973,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.4595,
+      "step": 46
+    },
+    {
+      "epoch": 0.018619391898583738,
+      "grad_norm": 12.919535636901855,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.0023,
+      "step": 47
+    },
+    {
+      "epoch": 0.01901554917302169,
+      "grad_norm": 13.515146255493164,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.8616,
+      "step": 48
+    },
+    {
+      "epoch": 0.019411706447459643,
+      "grad_norm": 13.035895347595215,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.3172,
+      "step": 49
+    },
+    {
+      "epoch": 0.019807863721897592,
+      "grad_norm": 19.37661361694336,
+      "learning_rate": 0.0,
+      "loss": 3.5126,
+      "step": 50
+    },
+    {
+      "epoch": 0.019807863721897592,
+      "eval_loss": 0.6597008109092712,
+      "eval_runtime": 156.6523,
+      "eval_samples_per_second": 27.143,
+      "eval_steps_per_second": 3.396,
+      "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": 1.8066349863469056e+16,
+  "total_flos": 3.5953824975814656e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null