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:ce8c89a6b40b213e7c8663a4bb012bc77f3f1d7a9d2d6b09f3c4ba3611442fb8
+oid sha256:57529d2e7ff89384cdcdc19d3d0fd6052683d4d4c42c2e7f5f8583d677d2389f
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9daae6b6f779502e248eb1917b4502e3a307f26e36f26a23e0d4d505fe24b72
+oid sha256:31626b3b2332bea0633cc86a4a3bb609db088bf4c8d0b2935afa278c5ab9b36e
 size 323290986

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d6792e9b414510316c8f1a16ef94aa8aa0fab206f0faf53b6d86c25074a686
+oid sha256:f85a5f1cf076f32701c7cad6bb87b5ea068ccda67315a01aa03f8660c4c6a0b2
 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": 1.7710518836975098,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0349283967865875,
+  "best_metric": 1.7017016410827637,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.069856793573175,
   "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": 3.141,
       "eval_steps_per_second": 1.571,
       "step": 25
+    },
+    {
+      "epoch": 0.036325532658050996,
+      "grad_norm": 1.1468117237091064,
+      "learning_rate": 0.0001,
+      "loss": 2.0482,
+      "step": 26
+    },
+    {
+      "epoch": 0.037722668529514496,
+      "grad_norm": 0.8366401791572571,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.6346,
+      "step": 27
+    },
+    {
+      "epoch": 0.039119804400977995,
+      "grad_norm": 0.7719747424125671,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.5849,
+      "step": 28
+    },
+    {
+      "epoch": 0.040516940272441494,
+      "grad_norm": 0.9361782670021057,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.8551,
+      "step": 29
+    },
+    {
+      "epoch": 0.041914076143904994,
+      "grad_norm": 1.128204345703125,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.9648,
+      "step": 30
+    },
+    {
+      "epoch": 0.04331121201536849,
+      "grad_norm": 1.0024124383926392,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.8017,
+      "step": 31
+    },
+    {
+      "epoch": 0.04470834788683199,
+      "grad_norm": 0.9835119843482971,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.7692,
+      "step": 32
+    },
+    {
+      "epoch": 0.04610548375829549,
+      "grad_norm": 1.0458788871765137,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.456,
+      "step": 33
+    },
+    {
+      "epoch": 0.04750261962975899,
+      "grad_norm": 1.029359221458435,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.1277,
+      "step": 34
+    },
+    {
+      "epoch": 0.0488997555012225,
+      "grad_norm": 0.8961425423622131,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.6894,
+      "step": 35
+    },
+    {
+      "epoch": 0.050296891372685996,
+      "grad_norm": 0.9357238411903381,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.6413,
+      "step": 36
+    },
+    {
+      "epoch": 0.051694027244149496,
+      "grad_norm": 0.9889127612113953,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.7025,
+      "step": 37
+    },
+    {
+      "epoch": 0.053091163115612995,
+      "grad_norm": 0.9021267890930176,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.3933,
+      "step": 38
+    },
+    {
+      "epoch": 0.054488298987076494,
+      "grad_norm": 1.259774088859558,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.6318,
+      "step": 39
+    },
+    {
+      "epoch": 0.055885434858539994,
+      "grad_norm": 0.9996725916862488,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.6355,
+      "step": 40
+    },
+    {
+      "epoch": 0.05728257073000349,
+      "grad_norm": 1.31227707862854,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.8715,
+      "step": 41
+    },
+    {
+      "epoch": 0.05867970660146699,
+      "grad_norm": 1.266066312789917,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.0598,
+      "step": 42
+    },
+    {
+      "epoch": 0.06007684247293049,
+      "grad_norm": 1.1719212532043457,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.1243,
+      "step": 43
+    },
+    {
+      "epoch": 0.06147397834439399,
+      "grad_norm": 1.2561590671539307,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.7084,
+      "step": 44
+    },
+    {
+      "epoch": 0.06287111421585749,
+      "grad_norm": 1.4959790706634521,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 1.8423,
+      "step": 45
+    },
+    {
+      "epoch": 0.064268250087321,
+      "grad_norm": 1.5612496137619019,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.8425,
+      "step": 46
+    },
+    {
+      "epoch": 0.06566538595878449,
+      "grad_norm": 1.473332166671753,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 1.5454,
+      "step": 47
+    },
+    {
+      "epoch": 0.067062521830248,
+      "grad_norm": 1.9833347797393799,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.099,
+      "step": 48
+    },
+    {
+      "epoch": 0.06845965770171149,
+      "grad_norm": 1.5466455221176147,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 1.6702,
+      "step": 49
+    },
+    {
+      "epoch": 0.069856793573175,
+      "grad_norm": 1.9173717498779297,
+      "learning_rate": 0.0,
+      "loss": 1.8048,
+      "step": 50
+    },
+    {
+      "epoch": 0.069856793573175,
+      "eval_loss": 1.7017016410827637,
+      "eval_runtime": 96.2516,
+      "eval_samples_per_second": 3.138,
+      "eval_steps_per_second": 1.569,
+      "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": 3.49519346663424e+16,
+  "total_flos": 6.99038693326848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null