Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79df07254807de12c46c494d9baeab514b958e67f678544b2adcdb93ab967eeb
+oid sha256:1b0f6692e047ef7e46eb1e330c257a8b90c245fe17450fceaa504aaf4cadf1bf
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2918dd9930948e0a23d6eaf9dcef011b01f35c8da64e3f2a2a12fc18a946bf4
+oid sha256:b57dbfd5ac13a4b63bd927a2bb96c9f64d18984b0e14f0a8b55cfea683e4207c
 size 121430

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17065f99c57af3ba2ffb856765c19e0565a50faf72893f70b9e1968da6a1f7d5
+oid sha256:657da4598c90cab5c023ea809c47b168d3c78d61049c6dc9ca0d917cad8e8949
 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": 6.743670463562012,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0975609756097561,
+  "best_metric": 6.717546463012695,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1951219512195122,
   "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": 299.83,
       "eval_steps_per_second": 149.915,
       "step": 25
+    },
+    {
+      "epoch": 0.10146341463414635,
+      "grad_norm": 0.7409495711326599,
+      "learning_rate": 0.0001,
+      "loss": 6.7454,
+      "step": 26
+    },
+    {
+      "epoch": 0.10536585365853658,
+      "grad_norm": 0.7578893899917603,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 6.7515,
+      "step": 27
+    },
+    {
+      "epoch": 0.10926829268292683,
+      "grad_norm": 0.7759184837341309,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 6.7554,
+      "step": 28
+    },
+    {
+      "epoch": 0.11317073170731708,
+      "grad_norm": 0.7387394309043884,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 6.7204,
+      "step": 29
+    },
+    {
+      "epoch": 0.11707317073170732,
+      "grad_norm": 0.705632746219635,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 6.7335,
+      "step": 30
+    },
+    {
+      "epoch": 0.12097560975609756,
+      "grad_norm": 0.6851465106010437,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 6.7493,
+      "step": 31
+    },
+    {
+      "epoch": 0.1248780487804878,
+      "grad_norm": 0.740122377872467,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 6.701,
+      "step": 32
+    },
+    {
+      "epoch": 0.12878048780487805,
+      "grad_norm": 0.638899564743042,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 6.7514,
+      "step": 33
+    },
+    {
+      "epoch": 0.1326829268292683,
+      "grad_norm": 0.7418556809425354,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 6.7595,
+      "step": 34
+    },
+    {
+      "epoch": 0.13658536585365855,
+      "grad_norm": 0.6872796416282654,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 6.75,
+      "step": 35
+    },
+    {
+      "epoch": 0.1404878048780488,
+      "grad_norm": 0.6563825011253357,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 6.7437,
+      "step": 36
+    },
+    {
+      "epoch": 0.144390243902439,
+      "grad_norm": 0.7908744215965271,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 6.7463,
+      "step": 37
+    },
+    {
+      "epoch": 0.14829268292682926,
+      "grad_norm": 0.6440786123275757,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 6.7321,
+      "step": 38
+    },
+    {
+      "epoch": 0.1521951219512195,
+      "grad_norm": 0.731747031211853,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 6.7546,
+      "step": 39
+    },
+    {
+      "epoch": 0.15609756097560976,
+      "grad_norm": 0.6230834126472473,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 6.7368,
+      "step": 40
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7506718635559082,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 6.7426,
+      "step": 41
+    },
+    {
+      "epoch": 0.16390243902439025,
+      "grad_norm": 0.7346739768981934,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.7446,
+      "step": 42
+    },
+    {
+      "epoch": 0.1678048780487805,
+      "grad_norm": 0.6999073624610901,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 6.7347,
+      "step": 43
+    },
+    {
+      "epoch": 0.17170731707317075,
+      "grad_norm": 0.6503731608390808,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 6.7496,
+      "step": 44
+    },
+    {
+      "epoch": 0.17560975609756097,
+      "grad_norm": 0.6913208365440369,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 6.7058,
+      "step": 45
+    },
+    {
+      "epoch": 0.1795121951219512,
+      "grad_norm": 0.7521505355834961,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 6.7188,
+      "step": 46
+    },
+    {
+      "epoch": 0.18341463414634146,
+      "grad_norm": 0.8142408132553101,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 6.7163,
+      "step": 47
+    },
+    {
+      "epoch": 0.1873170731707317,
+      "grad_norm": 0.6648187637329102,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 6.7262,
+      "step": 48
+    },
+    {
+      "epoch": 0.19121951219512195,
+      "grad_norm": 0.8425360321998596,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 6.7683,
+      "step": 49
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 0.710664689540863,
+      "learning_rate": 0.0,
+      "loss": 6.7291,
+      "step": 50
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "eval_loss": 6.717546463012695,
+      "eval_runtime": 0.3537,
+      "eval_samples_per_second": 305.34,
+      "eval_steps_per_second": 152.67,
+      "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": 294651494400.0,
+  "total_flos": 589302988800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null