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:a50f8f602a899452866b3e6fecef13711318104668b5573d2dd66728d2af36fd
+oid sha256:a5268dd2575d3de5543a4bb69c8edf258866b8d120bede324bee008b052f1066
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82409b72d0fe6e9d19b23af92e67bd9b71c3a2140c0063dd02e0ce679c3579a4
+oid sha256:73891941d3510cbde7e9a398ea1cd383679ca6121e72fade501c547f8a65bdec
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25650721c5c1577c20cf2d049bc0878d39349f4b1063c1a34377ef9083acbf51
+oid sha256:1fd9022e411d87a6394495beaa489e8314d129b05914f05f5a73a7a6fdbab1ea
 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": 2.1580612659454346,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0035709184402228254,
+  "best_metric": 2.0983710289001465,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.007141836880445651,
   "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": 28.437,
       "eval_steps_per_second": 3.555,
       "step": 25
+    },
+    {
+      "epoch": 0.0037137551778317385,
+      "grad_norm": 1.06201171875,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.9601,
+      "step": 26
+    },
+    {
+      "epoch": 0.003856591915440651,
+      "grad_norm": 0.8033665418624878,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.1786,
+      "step": 27
+    },
+    {
+      "epoch": 0.003999428653049564,
+      "grad_norm": 0.7216453552246094,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.7456,
+      "step": 28
+    },
+    {
+      "epoch": 0.004142265390658477,
+      "grad_norm": 0.6949120759963989,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.1063,
+      "step": 29
+    },
+    {
+      "epoch": 0.0042851021282673905,
+      "grad_norm": 0.775617241859436,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.0092,
+      "step": 30
+    },
+    {
+      "epoch": 0.004427938865876303,
+      "grad_norm": 0.8930774927139282,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.3109,
+      "step": 31
+    },
+    {
+      "epoch": 0.004570775603485217,
+      "grad_norm": 0.8304359912872314,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.3366,
+      "step": 32
+    },
+    {
+      "epoch": 0.004713612341094129,
+      "grad_norm": 0.8414106369018555,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.2098,
+      "step": 33
+    },
+    {
+      "epoch": 0.004856449078703042,
+      "grad_norm": 0.8435922861099243,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.1496,
+      "step": 34
+    },
+    {
+      "epoch": 0.0049992858163119555,
+      "grad_norm": 0.8119814991950989,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0754,
+      "step": 35
+    },
+    {
+      "epoch": 0.005142122553920868,
+      "grad_norm": 0.9691965579986572,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.1919,
+      "step": 36
+    },
+    {
+      "epoch": 0.005284959291529782,
+      "grad_norm": 1.102478265762329,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.3687,
+      "step": 37
+    },
+    {
+      "epoch": 0.005427796029138694,
+      "grad_norm": 0.9064949750900269,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.9269,
+      "step": 38
+    },
+    {
+      "epoch": 0.005570632766747607,
+      "grad_norm": 0.9010732173919678,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.913,
+      "step": 39
+    },
+    {
+      "epoch": 0.005713469504356521,
+      "grad_norm": 0.9198305606842041,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.3678,
+      "step": 40
+    },
+    {
+      "epoch": 0.005856306241965433,
+      "grad_norm": 0.8860936164855957,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.9271,
+      "step": 41
+    },
+    {
+      "epoch": 0.005999142979574347,
+      "grad_norm": 0.9916243553161621,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.502,
+      "step": 42
+    },
+    {
+      "epoch": 0.0061419797171832595,
+      "grad_norm": 1.2482694387435913,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.5281,
+      "step": 43
+    },
+    {
+      "epoch": 0.006284816454792172,
+      "grad_norm": 1.1935791969299316,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.058,
+      "step": 44
+    },
+    {
+      "epoch": 0.006427653192401086,
+      "grad_norm": 1.5026168823242188,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.0744,
+      "step": 45
+    },
+    {
+      "epoch": 0.006570489930009998,
+      "grad_norm": 1.4007118940353394,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.1313,
+      "step": 46
+    },
+    {
+      "epoch": 0.006713326667618912,
+      "grad_norm": 1.4725250005722046,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.8529,
+      "step": 47
+    },
+    {
+      "epoch": 0.006856163405227825,
+      "grad_norm": 1.8374519348144531,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.7987,
+      "step": 48
+    },
+    {
+      "epoch": 0.006999000142836737,
+      "grad_norm": 1.6353298425674438,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.858,
+      "step": 49
+    },
+    {
+      "epoch": 0.007141836880445651,
+      "grad_norm": 3.107301950454712,
+      "learning_rate": 0.0,
+      "loss": 1.7803,
+      "step": 50
+    },
+    {
+      "epoch": 0.007141836880445651,
+      "eval_loss": 2.0983710289001465,
+      "eval_runtime": 413.8651,
+      "eval_samples_per_second": 28.49,
+      "eval_steps_per_second": 3.562,
+      "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": 1.795134465245184e+16,
+  "total_flos": 3.572495321923584e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null