Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0991a03cbee95814707a7b9fe44252226203ee58da1b9dc5328155cc90fb1953
+oid sha256:b1c00b424bb043ab99fca644cb1d3021f5d555c9c05813209a5d5c7e3e990435
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ce0aa52396d54e36e4dc122ae660bc33f1717768a08951374ef765893eb1336
+oid sha256:eb0ef192c54a0bcaa765f56c76fc99403e737066c4ecb9d98d5f484d8232fa6f
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c87a2fcf27ca0a9d02af141f5a00e4c6af7b6652cbc9fbd57ad903158eddac7
+oid sha256:0c3669a17ed2065b0b6d69ae4da78c616d780a1019b4b09c2bbfbfa2f6f43815
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5757687091827393,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0017308224868457492,
+  "best_metric": 0.4442506432533264,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0034616449736914984,
   "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": 3.882,
       "eval_steps_per_second": 1.941,
       "step": 25
+    },
+    {
+      "epoch": 0.001800055386319579,
+      "grad_norm": 9.80317211151123,
+      "learning_rate": 0.0001,
+      "loss": 1.7549,
+      "step": 26
+    },
+    {
+      "epoch": 0.001869288285793409,
+      "grad_norm": 15.72749137878418,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 2.2773,
+      "step": 27
+    },
+    {
+      "epoch": 0.001938521185267239,
+      "grad_norm": 15.096418380737305,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.8499,
+      "step": 28
+    },
+    {
+      "epoch": 0.002007754084741069,
+      "grad_norm": 24.820247650146484,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 2.855,
+      "step": 29
+    },
+    {
+      "epoch": 0.002076986984214899,
+      "grad_norm": 14.719782829284668,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 2.5231,
+      "step": 30
+    },
+    {
+      "epoch": 0.002146219883688729,
+      "grad_norm": 9.150571823120117,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.8756,
+      "step": 31
+    },
+    {
+      "epoch": 0.002215452783162559,
+      "grad_norm": 14.688347816467285,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.7645,
+      "step": 32
+    },
+    {
+      "epoch": 0.0022846856826363887,
+      "grad_norm": 18.42392349243164,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 2.1888,
+      "step": 33
+    },
+    {
+      "epoch": 0.002353918582110219,
+      "grad_norm": 12.466184616088867,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.137,
+      "step": 34
+    },
+    {
+      "epoch": 0.002423151481584049,
+      "grad_norm": 11.869159698486328,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.9136,
+      "step": 35
+    },
+    {
+      "epoch": 0.0024923843810578787,
+      "grad_norm": 10.24367618560791,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.6125,
+      "step": 36
+    },
+    {
+      "epoch": 0.0025616172805317085,
+      "grad_norm": 10.600191116333008,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 2.1622,
+      "step": 37
+    },
+    {
+      "epoch": 0.002630850180005539,
+      "grad_norm": 9.307639122009277,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.8964,
+      "step": 38
+    },
+    {
+      "epoch": 0.0027000830794793687,
+      "grad_norm": 7.141270637512207,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.8054,
+      "step": 39
+    },
+    {
+      "epoch": 0.0027693159789531985,
+      "grad_norm": 12.76805305480957,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.6684,
+      "step": 40
+    },
+    {
+      "epoch": 0.0028385488784270284,
+      "grad_norm": 20.816078186035156,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 2.1496,
+      "step": 41
+    },
+    {
+      "epoch": 0.0029077817779008587,
+      "grad_norm": 6.196358680725098,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.3874,
+      "step": 42
+    },
+    {
+      "epoch": 0.0029770146773746885,
+      "grad_norm": 10.963146209716797,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 1.638,
+      "step": 43
+    },
+    {
+      "epoch": 0.0030462475768485184,
+      "grad_norm": 9.570157051086426,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.4989,
+      "step": 44
+    },
+    {
+      "epoch": 0.003115480476322348,
+      "grad_norm": 12.58957290649414,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.2585,
+      "step": 45
+    },
+    {
+      "epoch": 0.0031847133757961785,
+      "grad_norm": 7.2112932205200195,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.3987,
+      "step": 46
+    },
+    {
+      "epoch": 0.0032539462752700084,
+      "grad_norm": 14.840339660644531,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 1.99,
+      "step": 47
+    },
+    {
+      "epoch": 0.003323179174743838,
+      "grad_norm": 10.862496376037598,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.4887,
+      "step": 48
+    },
+    {
+      "epoch": 0.003392412074217668,
+      "grad_norm": 20.067378997802734,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 2.5822,
+      "step": 49
+    },
+    {
+      "epoch": 0.0034616449736914984,
+      "grad_norm": 15.832198143005371,
+      "learning_rate": 0.0,
+      "loss": 2.7017,
+      "step": 50
+    },
+    {
+      "epoch": 0.0034616449736914984,
+      "eval_loss": 0.4442506432533264,
+      "eval_runtime": 1568.662,
+      "eval_samples_per_second": 3.877,
+      "eval_steps_per_second": 1.939,
+      "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": 3.26729100951552e+16,
+  "total_flos": 6.53458201903104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null