Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3de142055b5c657d76f910bd934eb60874581a637fdc6a0ce519ebd67e3731bf
+oid sha256:7cec11a9460db6814280fc752e05e7c9e9cb5dcc8b006f3df1297c9cd3b993c6
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0d36ae349dce7966fd22f73ca0122e98e2d0d91483b3f72681ca4b8ee82f0e2
+oid sha256:6d48c6ba41f99f029fd1bffcbc9f9d64a00db639985cb6eac3026096a5469aa9
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b97f64f29399b846381fe9360f9e5180addbb2652f61d7d84499d65c336824d5
+oid sha256:6e029db9b76002aaf6a940b4a0385243b2f1ca980d90462cde2b29eef8e7d56e
 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": 2.169510841369629,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01532567049808429,
+  "best_metric": 2.0704262256622314,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03065134099616858,
   "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": 97.143,
       "eval_steps_per_second": 12.165,
       "step": 25
+    },
+    {
+      "epoch": 0.015938697318007664,
+      "grad_norm": 0.16475293040275574,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.5398,
+      "step": 26
+    },
+    {
+      "epoch": 0.016551724137931035,
+      "grad_norm": 0.22766101360321045,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.229,
+      "step": 27
+    },
+    {
+      "epoch": 0.017164750957854406,
+      "grad_norm": 0.24101488292217255,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.3215,
+      "step": 28
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 0.1988028734922409,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.2015,
+      "step": 29
+    },
+    {
+      "epoch": 0.01839080459770115,
+      "grad_norm": 0.21405185759067535,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.3046,
+      "step": 30
+    },
+    {
+      "epoch": 0.01900383141762452,
+      "grad_norm": 0.17964892089366913,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.3912,
+      "step": 31
+    },
+    {
+      "epoch": 0.019616858237547892,
+      "grad_norm": 0.188919797539711,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3432,
+      "step": 32
+    },
+    {
+      "epoch": 0.020229885057471263,
+      "grad_norm": 0.26917535066604614,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.0052,
+      "step": 33
+    },
+    {
+      "epoch": 0.020842911877394635,
+      "grad_norm": 0.3175217807292938,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.9935,
+      "step": 34
+    },
+    {
+      "epoch": 0.021455938697318006,
+      "grad_norm": 0.469002902507782,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.5468,
+      "step": 35
+    },
+    {
+      "epoch": 0.022068965517241378,
+      "grad_norm": 0.653257429599762,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.6147,
+      "step": 36
+    },
+    {
+      "epoch": 0.022681992337164752,
+      "grad_norm": 1.0501368045806885,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.5708,
+      "step": 37
+    },
+    {
+      "epoch": 0.023295019157088124,
+      "grad_norm": 1.2141762971878052,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.5634,
+      "step": 38
+    },
+    {
+      "epoch": 0.023908045977011495,
+      "grad_norm": 1.6670536994934082,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 4.1478,
+      "step": 39
+    },
+    {
+      "epoch": 0.024521072796934867,
+      "grad_norm": 1.5715434551239014,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.7665,
+      "step": 40
+    },
+    {
+      "epoch": 0.025134099616858238,
+      "grad_norm": 1.349192500114441,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.5277,
+      "step": 41
+    },
+    {
+      "epoch": 0.02574712643678161,
+      "grad_norm": 1.0553473234176636,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.1882,
+      "step": 42
+    },
+    {
+      "epoch": 0.02636015325670498,
+      "grad_norm": 1.0868961811065674,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.2809,
+      "step": 43
+    },
+    {
+      "epoch": 0.026973180076628352,
+      "grad_norm": 0.9385594129562378,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.2855,
+      "step": 44
+    },
+    {
+      "epoch": 0.027586206896551724,
+      "grad_norm": 1.038495421409607,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.2324,
+      "step": 45
+    },
+    {
+      "epoch": 0.028199233716475095,
+      "grad_norm": 1.0660349130630493,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.3868,
+      "step": 46
+    },
+    {
+      "epoch": 0.028812260536398467,
+      "grad_norm": 1.0207303762435913,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.1981,
+      "step": 47
+    },
+    {
+      "epoch": 0.029425287356321838,
+      "grad_norm": 1.0714794397354126,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.2815,
+      "step": 48
+    },
+    {
+      "epoch": 0.03003831417624521,
+      "grad_norm": 1.0691288709640503,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 3.1973,
+      "step": 49
+    },
+    {
+      "epoch": 0.03065134099616858,
+      "grad_norm": 1.2095760107040405,
+      "learning_rate": 0.0,
+      "loss": 3.7897,
+      "step": 50
+    },
+    {
+      "epoch": 0.03065134099616858,
+      "eval_loss": 2.0704262256622314,
+      "eval_runtime": 28.2582,
+      "eval_samples_per_second": 97.211,
+      "eval_steps_per_second": 12.173,
+      "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": 1588428393676800.0,
+  "total_flos": 2447038336204800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null