Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:974cf3e06c99061a796c60ffea14e58bd658dc34e5d7e9536f46dd8c5b5b3dcf
+oid sha256:f1e51d6369a88c457d271c456cc1d83e854875aa4dd139f278696f65f45a3ed7
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768bb1a70bf2f420162a465857d2e454dcd27db99fe5ba6384740c044d680594
+oid sha256:3537d29a719f5ed78fbbbdbfa560e2a1890ce9e2926a0576c82b8b4899d8a2d5
 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": 1.1055799722671509,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22026431718061673,
+  "best_metric": 1.0106004476547241,
+  "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": 27.723,
       "eval_steps_per_second": 3.465,
       "step": 25
+    },
+    {
+      "epoch": 0.2290748898678414,
+      "grad_norm": 13.63646411895752,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 4.2333,
+      "step": 26
+    },
+    {
+      "epoch": 0.23788546255506607,
+      "grad_norm": 12.906288146972656,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.7754,
+      "step": 27
+    },
+    {
+      "epoch": 0.24669603524229075,
+      "grad_norm": 32.98773956298828,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 5.5734,
+      "step": 28
+    },
+    {
+      "epoch": 0.2555066079295154,
+      "grad_norm": 36.30422592163086,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 5.2083,
+      "step": 29
+    },
+    {
+      "epoch": 0.2643171806167401,
+      "grad_norm": 29.99471092224121,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 5.2787,
+      "step": 30
+    },
+    {
+      "epoch": 0.27312775330396477,
+      "grad_norm": 17.82193374633789,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 4.5795,
+      "step": 31
+    },
+    {
+      "epoch": 0.28193832599118945,
+      "grad_norm": 13.2213716506958,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.3673,
+      "step": 32
+    },
+    {
+      "epoch": 0.2907488986784141,
+      "grad_norm": 11.667417526245117,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 3.9109,
+      "step": 33
+    },
+    {
+      "epoch": 0.29955947136563876,
+      "grad_norm": 10.663423538208008,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 4.0043,
+      "step": 34
+    },
+    {
+      "epoch": 0.30837004405286345,
+      "grad_norm": 10.346181869506836,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.8749,
+      "step": 35
+    },
+    {
+      "epoch": 0.31718061674008813,
+      "grad_norm": 10.776055335998535,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.8847,
+      "step": 36
+    },
+    {
+      "epoch": 0.32599118942731276,
+      "grad_norm": 10.248950004577637,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.7897,
+      "step": 37
+    },
+    {
+      "epoch": 0.33480176211453744,
+      "grad_norm": 10.948817253112793,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.9268,
+      "step": 38
+    },
+    {
+      "epoch": 0.3436123348017621,
+      "grad_norm": 10.441291809082031,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 3.5599,
+      "step": 39
+    },
+    {
+      "epoch": 0.3524229074889868,
+      "grad_norm": 12.858811378479004,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.607,
+      "step": 40
+    },
+    {
+      "epoch": 0.36123348017621143,
+      "grad_norm": 11.29244327545166,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.1881,
+      "step": 41
+    },
+    {
+      "epoch": 0.3700440528634361,
+      "grad_norm": 10.727145195007324,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 4.1046,
+      "step": 42
+    },
+    {
+      "epoch": 0.3788546255506608,
+      "grad_norm": 11.454111099243164,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.0834,
+      "step": 43
+    },
+    {
+      "epoch": 0.3876651982378855,
+      "grad_norm": 10.730988502502441,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.7658,
+      "step": 44
+    },
+    {
+      "epoch": 0.3964757709251101,
+      "grad_norm": 12.551647186279297,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.5078,
+      "step": 45
+    },
+    {
+      "epoch": 0.4052863436123348,
+      "grad_norm": 12.465065956115723,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.9693,
+      "step": 46
+    },
+    {
+      "epoch": 0.41409691629955947,
+      "grad_norm": 11.369115829467773,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.7502,
+      "step": 47
+    },
+    {
+      "epoch": 0.42290748898678415,
+      "grad_norm": 11.680598258972168,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.6231,
+      "step": 48
+    },
+    {
+      "epoch": 0.43171806167400884,
+      "grad_norm": 14.236860275268555,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 4.1521,
+      "step": 49
+    },
+    {
+      "epoch": 0.44052863436123346,
+      "grad_norm": 12.475255966186523,
+      "learning_rate": 0.0,
+      "loss": 4.2304,
+      "step": 50
+    },
+    {
+      "epoch": 0.44052863436123346,
+      "eval_loss": 1.0106004476547241,
+      "eval_runtime": 6.9593,
+      "eval_samples_per_second": 27.589,
+      "eval_steps_per_second": 3.449,
+      "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