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:fdc0478b53ed78f51e90464f3d65e1a7ba052b8eb2d50aca4dd8c1c8cc562dc2
+oid sha256:7f9d480b288a25b8098b3d24ef3f19a0402e6f35dd65be0dc22956b9ed256641
 size 94422368

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e752c7bbed0ee0043ecd9df2485a16b89099b2b71ffc8b1e2b17257536456041
+oid sha256:f7b7560c4fe0661d55cd362563f3bcd0e4e014960c1678c6f5b28e48e87ae231
 size 189066386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ecfb4c4e6b7535785b654f3c9d1bdbc310c0538d547b0a867c4831f2326a5a7
+oid sha256:8a28c047751e255051d4da6b05b0821ba04d6c3223457654de2dcce262c838eb
 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": 1.9770020246505737,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01768033946251768,
+  "best_metric": 1.8582121133804321,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03536067892503536,
   "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": 4.444,
       "eval_steps_per_second": 2.222,
       "step": 25
+    },
+    {
+      "epoch": 0.018387553041018388,
+      "grad_norm": 7.82539176940918,
+      "learning_rate": 0.0001,
+      "loss": 1.8744,
+      "step": 26
+    },
+    {
+      "epoch": 0.019094766619519095,
+      "grad_norm": 7.731629371643066,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.8641,
+      "step": 27
+    },
+    {
+      "epoch": 0.019801980198019802,
+      "grad_norm": 4.9687724113464355,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.9843,
+      "step": 28
+    },
+    {
+      "epoch": 0.02050919377652051,
+      "grad_norm": 8.137701034545898,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.8602,
+      "step": 29
+    },
+    {
+      "epoch": 0.021216407355021217,
+      "grad_norm": 6.364139556884766,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.6738,
+      "step": 30
+    },
+    {
+      "epoch": 0.021923620933521924,
+      "grad_norm": 7.106420516967773,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.727,
+      "step": 31
+    },
+    {
+      "epoch": 0.02263083451202263,
+      "grad_norm": 7.26156759262085,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.9805,
+      "step": 32
+    },
+    {
+      "epoch": 0.02333804809052334,
+      "grad_norm": 6.520480632781982,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.7086,
+      "step": 33
+    },
+    {
+      "epoch": 0.024045261669024046,
+      "grad_norm": 8.08383846282959,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.2126,
+      "step": 34
+    },
+    {
+      "epoch": 0.024752475247524754,
+      "grad_norm": 9.672865867614746,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.926,
+      "step": 35
+    },
+    {
+      "epoch": 0.02545968882602546,
+      "grad_norm": 7.996883869171143,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.9595,
+      "step": 36
+    },
+    {
+      "epoch": 0.02616690240452617,
+      "grad_norm": 6.572012424468994,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.9952,
+      "step": 37
+    },
+    {
+      "epoch": 0.026874115983026876,
+      "grad_norm": 13.477945327758789,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.1519,
+      "step": 38
+    },
+    {
+      "epoch": 0.027581329561527583,
+      "grad_norm": 8.22754955291748,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 2.3224,
+      "step": 39
+    },
+    {
+      "epoch": 0.028288543140028287,
+      "grad_norm": 6.019199848175049,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.1815,
+      "step": 40
+    },
+    {
+      "epoch": 0.028995756718528994,
+      "grad_norm": 6.724240779876709,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 2.3388,
+      "step": 41
+    },
+    {
+      "epoch": 0.0297029702970297,
+      "grad_norm": 8.860747337341309,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.1412,
+      "step": 42
+    },
+    {
+      "epoch": 0.03041018387553041,
+      "grad_norm": 7.679854869842529,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.3033,
+      "step": 43
+    },
+    {
+      "epoch": 0.031117397454031116,
+      "grad_norm": 7.3515543937683105,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.912,
+      "step": 44
+    },
+    {
+      "epoch": 0.03182461103253183,
+      "grad_norm": 6.8346476554870605,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.3716,
+      "step": 45
+    },
+    {
+      "epoch": 0.03253182461103253,
+      "grad_norm": 9.228812217712402,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.2762,
+      "step": 46
+    },
+    {
+      "epoch": 0.03323903818953324,
+      "grad_norm": 7.8867011070251465,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 2.3511,
+      "step": 47
+    },
+    {
+      "epoch": 0.033946251768033946,
+      "grad_norm": 7.230483531951904,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.0595,
+      "step": 48
+    },
+    {
+      "epoch": 0.034653465346534656,
+      "grad_norm": 8.049776077270508,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 2.3028,
+      "step": 49
+    },
+    {
+      "epoch": 0.03536067892503536,
+      "grad_norm": 7.5476179122924805,
+      "learning_rate": 0.0,
+      "loss": 2.5329,
+      "step": 50
+    },
+    {
+      "epoch": 0.03536067892503536,
+      "eval_loss": 1.8582121133804321,
+      "eval_runtime": 134.1457,
+      "eval_samples_per_second": 4.443,
+      "eval_steps_per_second": 2.221,
+      "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": 1.313442103296e+16,
+  "total_flos": 2.626884206592e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null