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:ff2c58132ad55251f9a7bddcf8215c3d89c52de9db193dba942ac3d06e22f630
+oid sha256:f9a123f6696c71abf46d60b53a35eda9c0a9215cc7940e7995a56fa361e132fa
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb3abcbfaab6e7bb6e1efe2739eec6b135191a586d88a6c7becacc5e600d696
+oid sha256:492545ca0f696ac6aa0bf99cc03b429bb06dcae81c66a5b060098217dc924987
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:412b8fed44624ccb0fa21d51d1e2d66e137afdfff2e249732ec5b3e9cd89104a
+oid sha256:a323860ec34b86fcc7226d41058b64eea59fd2ee0d48489ab5d7b70a46519bb0
 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": 0.5400802493095398,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0019007431905875198,
+  "best_metric": 0.4710901975631714,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0038014863811750396,
   "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": 2.132,
       "eval_steps_per_second": 1.066,
       "step": 25
+    },
+    {
+      "epoch": 0.0019767729182110206,
+      "grad_norm": 2.6046080589294434,
+      "learning_rate": 0.0001,
+      "loss": 0.4354,
+      "step": 26
+    },
+    {
+      "epoch": 0.002052802645834521,
+      "grad_norm": 1.5984587669372559,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.4151,
+      "step": 27
+    },
+    {
+      "epoch": 0.002128832373458022,
+      "grad_norm": 3.0031909942626953,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.5274,
+      "step": 28
+    },
+    {
+      "epoch": 0.002204862101081523,
+      "grad_norm": 0.9939762353897095,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.2949,
+      "step": 29
+    },
+    {
+      "epoch": 0.0022808918287050236,
+      "grad_norm": 1.2130672931671143,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.3297,
+      "step": 30
+    },
+    {
+      "epoch": 0.0023569215563285246,
+      "grad_norm": 3.6291580200195312,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.6363,
+      "step": 31
+    },
+    {
+      "epoch": 0.002432951283952025,
+      "grad_norm": 1.8360271453857422,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.4268,
+      "step": 32
+    },
+    {
+      "epoch": 0.002508981011575526,
+      "grad_norm": 1.8505597114562988,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.4135,
+      "step": 33
+    },
+    {
+      "epoch": 0.0025850107391990266,
+      "grad_norm": 3.646937370300293,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.9458,
+      "step": 34
+    },
+    {
+      "epoch": 0.0026610404668225276,
+      "grad_norm": 1.7447396516799927,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.3567,
+      "step": 35
+    },
+    {
+      "epoch": 0.0027370701944460286,
+      "grad_norm": 1.7719615697860718,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.4307,
+      "step": 36
+    },
+    {
+      "epoch": 0.002813099922069529,
+      "grad_norm": 1.2421600818634033,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.3624,
+      "step": 37
+    },
+    {
+      "epoch": 0.00288912964969303,
+      "grad_norm": 2.101491689682007,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.7057,
+      "step": 38
+    },
+    {
+      "epoch": 0.0029651593773165306,
+      "grad_norm": 1.3107458353042603,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.3915,
+      "step": 39
+    },
+    {
+      "epoch": 0.0030411891049400316,
+      "grad_norm": 1.219789743423462,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.2561,
+      "step": 40
+    },
+    {
+      "epoch": 0.003117218832563532,
+      "grad_norm": 1.4853408336639404,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.4317,
+      "step": 41
+    },
+    {
+      "epoch": 0.003193248560187033,
+      "grad_norm": 1.8641315698623657,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.7191,
+      "step": 42
+    },
+    {
+      "epoch": 0.003269278287810534,
+      "grad_norm": 1.435045599937439,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.5681,
+      "step": 43
+    },
+    {
+      "epoch": 0.0033453080154340347,
+      "grad_norm": 1.6989673376083374,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.4162,
+      "step": 44
+    },
+    {
+      "epoch": 0.0034213377430575356,
+      "grad_norm": 1.5967341661453247,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.4313,
+      "step": 45
+    },
+    {
+      "epoch": 0.003497367470681036,
+      "grad_norm": 1.6816807985305786,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.4867,
+      "step": 46
+    },
+    {
+      "epoch": 0.003573397198304537,
+      "grad_norm": 1.977468729019165,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.4679,
+      "step": 47
+    },
+    {
+      "epoch": 0.0036494269259280377,
+      "grad_norm": 1.6482903957366943,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.6017,
+      "step": 48
+    },
+    {
+      "epoch": 0.0037254566535515387,
+      "grad_norm": 1.3200818300247192,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.347,
+      "step": 49
+    },
+    {
+      "epoch": 0.0038014863811750396,
+      "grad_norm": 2.0896034240722656,
+      "learning_rate": 0.0,
+      "loss": 0.5163,
+      "step": 50
+    },
+    {
+      "epoch": 0.0038014863811750396,
+      "eval_loss": 0.4710901975631714,
+      "eval_runtime": 2597.4917,
+      "eval_samples_per_second": 2.132,
+      "eval_steps_per_second": 1.066,
+      "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": 6.3619630891008e+16,
+  "total_flos": 1.27239261782016e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null