Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd153d86bc5f2321d5a0b61a05c5aace52e3e3710eb9f11eeec0b5ad7b1eda5
+oid sha256:34afe2a83fc2cbfe2a93e7fe9c215a90c92d92d6acbe8ba9cbdc3c630db86108
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7bd4065a32d1b91435820b40a9e8431eab5de0e4e2e1bd1fb03e2588db3f67
+oid sha256:183851343ec8dbb2bdabc458c7fca956c015fcf6a80042846823b01aa5a55970
 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": 2.168886423110962,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01532567049808429,
+  "best_metric": 2.070686101913452,
+  "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": 97.02,
       "eval_steps_per_second": 12.15,
       "step": 25
+    },
+    {
+      "epoch": 0.015938697318007664,
+      "grad_norm": 0.16530576348304749,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.5389,
+      "step": 26
+    },
+    {
+      "epoch": 0.016551724137931035,
+      "grad_norm": 0.22750288248062134,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.2282,
+      "step": 27
+    },
+    {
+      "epoch": 0.017164750957854406,
+      "grad_norm": 0.24150137603282928,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.3227,
+      "step": 28
+    },
+    {
+      "epoch": 0.017777777777777778,
+      "grad_norm": 0.19981791079044342,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.2012,
+      "step": 29
+    },
+    {
+      "epoch": 0.01839080459770115,
+      "grad_norm": 0.2150210738182068,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.3041,
+      "step": 30
+    },
+    {
+      "epoch": 0.01900383141762452,
+      "grad_norm": 0.18099938333034515,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.3913,
+      "step": 31
+    },
+    {
+      "epoch": 0.019616858237547892,
+      "grad_norm": 0.18963854014873505,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.3419,
+      "step": 32
+    },
+    {
+      "epoch": 0.020229885057471263,
+      "grad_norm": 0.2710677683353424,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.0058,
+      "step": 33
+    },
+    {
+      "epoch": 0.020842911877394635,
+      "grad_norm": 0.31980398297309875,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.9938,
+      "step": 34
+    },
+    {
+      "epoch": 0.021455938697318006,
+      "grad_norm": 0.46993303298950195,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.5471,
+      "step": 35
+    },
+    {
+      "epoch": 0.022068965517241378,
+      "grad_norm": 0.6509338021278381,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.6094,
+      "step": 36
+    },
+    {
+      "epoch": 0.022681992337164752,
+      "grad_norm": 1.0531455278396606,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 3.5737,
+      "step": 37
+    },
+    {
+      "epoch": 0.023295019157088124,
+      "grad_norm": 1.2123762369155884,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 3.5545,
+      "step": 38
+    },
+    {
+      "epoch": 0.023908045977011495,
+      "grad_norm": 1.6725916862487793,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 4.1425,
+      "step": 39
+    },
+    {
+      "epoch": 0.024521072796934867,
+      "grad_norm": 1.577296495437622,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 3.7685,
+      "step": 40
+    },
+    {
+      "epoch": 0.025134099616858238,
+      "grad_norm": 1.354356288909912,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.5323,
+      "step": 41
+    },
+    {
+      "epoch": 0.02574712643678161,
+      "grad_norm": 1.0672824382781982,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 3.1902,
+      "step": 42
+    },
+    {
+      "epoch": 0.02636015325670498,
+      "grad_norm": 1.0935691595077515,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 3.2807,
+      "step": 43
+    },
+    {
+      "epoch": 0.026973180076628352,
+      "grad_norm": 0.9405376315116882,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 3.2881,
+      "step": 44
+    },
+    {
+      "epoch": 0.027586206896551724,
+      "grad_norm": 1.0448395013809204,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.2325,
+      "step": 45
+    },
+    {
+      "epoch": 0.028199233716475095,
+      "grad_norm": 1.070504903793335,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.385,
+      "step": 46
+    },
+    {
+      "epoch": 0.028812260536398467,
+      "grad_norm": 1.0256659984588623,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.1968,
+      "step": 47
+    },
+    {
+      "epoch": 0.029425287356321838,
+      "grad_norm": 1.0779807567596436,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 3.2781,
+      "step": 48
+    },
+    {
+      "epoch": 0.03003831417624521,
+      "grad_norm": 1.0722178220748901,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 3.1937,
+      "step": 49
+    },
+    {
+      "epoch": 0.03065134099616858,
+      "grad_norm": 1.2146779298782349,
+      "learning_rate": 0.0,
+      "loss": 3.7941,
+      "step": 50
+    },
+    {
+      "epoch": 0.03065134099616858,
+      "eval_loss": 2.070686101913452,
+      "eval_runtime": 28.2908,
+      "eval_samples_per_second": 97.099,
+      "eval_steps_per_second": 12.159,
+      "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