Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ac1d590836f81446dab6c45b44743bb1be1720e6e312940a109a7a728c8ce8
+oid sha256:8146c7c9c8b5d79a16ce9026c20bfef0dcbe350d523a63ac4f10a412afbe5d89
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca795324b4f26cdb0bcb902bd5111576cca8b841d611d2d3425e9b72c8ada506
+oid sha256:2dcc9896aba398ed750e382f24c93b2800c990e1c13890be0025c7f87067a19f
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9ede80b3f66e522d9861dde7b8ca790eaab5eda03f7d4f55f00a8184777e5b5
+oid sha256:afb0992b7a5d25339b7430755919ad9c5c3a9ab6bcc660b9283f98bc151833ca
 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": 1.0948375463485718,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22026431718061673,
+  "best_metric": 1.0112258195877075,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.44052863436123346,
   "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": 27.688,
       "eval_steps_per_second": 3.461,
       "step": 25
+    },
+    {
+      "epoch": 0.2290748898678414,
+      "grad_norm": 13.42129135131836,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 4.2533,
+      "step": 26
+    },
+    {
+      "epoch": 0.23788546255506607,
+      "grad_norm": 12.64493179321289,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.7725,
+      "step": 27
+    },
+    {
+      "epoch": 0.24669603524229075,
+      "grad_norm": 29.31064796447754,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 5.5236,
+      "step": 28
+    },
+    {
+      "epoch": 0.2555066079295154,
+      "grad_norm": 35.704978942871094,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 5.3033,
+      "step": 29
+    },
+    {
+      "epoch": 0.2643171806167401,
+      "grad_norm": 28.72123146057129,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 5.3203,
+      "step": 30
+    },
+    {
+      "epoch": 0.27312775330396477,
+      "grad_norm": 18.05626106262207,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 4.6476,
+      "step": 31
+    },
+    {
+      "epoch": 0.28193832599118945,
+      "grad_norm": 13.088356971740723,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.4231,
+      "step": 32
+    },
+    {
+      "epoch": 0.2907488986784141,
+      "grad_norm": 10.806975364685059,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 3.9532,
+      "step": 33
+    },
+    {
+      "epoch": 0.29955947136563876,
+      "grad_norm": 10.828692436218262,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 4.0607,
+      "step": 34
+    },
+    {
+      "epoch": 0.30837004405286345,
+      "grad_norm": 10.412042617797852,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.9047,
+      "step": 35
+    },
+    {
+      "epoch": 0.31718061674008813,
+      "grad_norm": 10.715507507324219,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.8874,
+      "step": 36
+    },
+    {
+      "epoch": 0.32599118942731276,
+      "grad_norm": 10.258496284484863,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.7764,
+      "step": 37
+    },
+    {
+      "epoch": 0.33480176211453744,
+      "grad_norm": 10.750401496887207,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.9169,
+      "step": 38
+    },
+    {
+      "epoch": 0.3436123348017621,
+      "grad_norm": 10.437529563903809,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 3.5651,
+      "step": 39
+    },
+    {
+      "epoch": 0.3524229074889868,
+      "grad_norm": 12.831405639648438,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.6194,
+      "step": 40
+    },
+    {
+      "epoch": 0.36123348017621143,
+      "grad_norm": 11.199616432189941,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.1619,
+      "step": 41
+    },
+    {
+      "epoch": 0.3700440528634361,
+      "grad_norm": 10.544151306152344,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 4.0953,
+      "step": 42
+    },
+    {
+      "epoch": 0.3788546255506608,
+      "grad_norm": 11.361042022705078,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.0792,
+      "step": 43
+    },
+    {
+      "epoch": 0.3876651982378855,
+      "grad_norm": 10.676876068115234,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.7704,
+      "step": 44
+    },
+    {
+      "epoch": 0.3964757709251101,
+      "grad_norm": 12.462179183959961,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.4998,
+      "step": 45
+    },
+    {
+      "epoch": 0.4052863436123348,
+      "grad_norm": 12.595497131347656,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.9907,
+      "step": 46
+    },
+    {
+      "epoch": 0.41409691629955947,
+      "grad_norm": 11.475981712341309,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.7781,
+      "step": 47
+    },
+    {
+      "epoch": 0.42290748898678415,
+      "grad_norm": 11.69732666015625,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.6304,
+      "step": 48
+    },
+    {
+      "epoch": 0.43171806167400884,
+      "grad_norm": 14.223932266235352,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 4.1759,
+      "step": 49
+    },
+    {
+      "epoch": 0.44052863436123346,
+      "grad_norm": 12.34350872039795,
+      "learning_rate": 0.0,
+      "loss": 4.2231,
+      "step": 50
+    },
+    {
+      "epoch": 0.44052863436123346,
+      "eval_loss": 1.0112258195877075,
+      "eval_runtime": 6.9489,
+      "eval_samples_per_second": 27.63,
+      "eval_steps_per_second": 3.454,
+      "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": 1.78874751123456e+16,
+  "total_flos": 3.57749502246912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null