Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:831ec7a5d78507c2ed59b072978435f991185370353f2e7bad38a8e684786da8
+oid sha256:7f6727185c1418b361c3d325a720e65a0a14ab0bf316ce037283dd62c6fe8e9a
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a681e2d298c619173a9cc14c44aea26f9002263a07384e6dbaaa458d17eaf5fb
+oid sha256:8946613ede0ae80993df78bf7896a9a52bdc2616f92d50d423265d379e536e82
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d561b3ef7ee9b81d79b5719a65ce49d5b209cf2f4ef7bd942f690a989aa0c5d
+oid sha256:fe8575f5e3996fc878ec799488c71c97da751188021128f90d1a6227e39f6286
 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": 1.8182884454727173,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.042034468263976464,
+  "best_metric": 1.7657277584075928,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08406893652795293,
   "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": 18.688,
       "eval_steps_per_second": 2.35,
       "step": 25
+    },
+    {
+      "epoch": 0.04371584699453552,
+      "grad_norm": 5.910251617431641,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.0236,
+      "step": 26
+    },
+    {
+      "epoch": 0.04539722572509458,
+      "grad_norm": 4.699669361114502,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.6246,
+      "step": 27
+    },
+    {
+      "epoch": 0.047078604455653636,
+      "grad_norm": 4.814205169677734,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.9747,
+      "step": 28
+    },
+    {
+      "epoch": 0.0487599831862127,
+      "grad_norm": 3.9208309650421143,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4932,
+      "step": 29
+    },
+    {
+      "epoch": 0.05044136191677175,
+      "grad_norm": 4.411428928375244,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.7782,
+      "step": 30
+    },
+    {
+      "epoch": 0.052122740647330815,
+      "grad_norm": 4.461432933807373,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.8025,
+      "step": 31
+    },
+    {
+      "epoch": 0.05380411937788987,
+      "grad_norm": 4.235904216766357,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.5559,
+      "step": 32
+    },
+    {
+      "epoch": 0.05548549810844893,
+      "grad_norm": 4.2846784591674805,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.7637,
+      "step": 33
+    },
+    {
+      "epoch": 0.057166876839007986,
+      "grad_norm": 4.3279619216918945,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.6952,
+      "step": 34
+    },
+    {
+      "epoch": 0.05884825556956705,
+      "grad_norm": 4.146105766296387,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5132,
+      "step": 35
+    },
+    {
+      "epoch": 0.0605296343001261,
+      "grad_norm": 4.055689334869385,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.7825,
+      "step": 36
+    },
+    {
+      "epoch": 0.062211013030685165,
+      "grad_norm": 5.1470417976379395,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.6962,
+      "step": 37
+    },
+    {
+      "epoch": 0.06389239176124423,
+      "grad_norm": 4.025249481201172,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.5764,
+      "step": 38
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 4.1527557373046875,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.822,
+      "step": 39
+    },
+    {
+      "epoch": 0.06725514922236234,
+      "grad_norm": 4.011697769165039,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.5009,
+      "step": 40
+    },
+    {
+      "epoch": 0.06893652795292139,
+      "grad_norm": 4.686009883880615,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6967,
+      "step": 41
+    },
+    {
+      "epoch": 0.07061790668348046,
+      "grad_norm": 3.999046802520752,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.4791,
+      "step": 42
+    },
+    {
+      "epoch": 0.07229928541403952,
+      "grad_norm": 4.770431041717529,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7141,
+      "step": 43
+    },
+    {
+      "epoch": 0.07398066414459857,
+      "grad_norm": 4.217533588409424,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.662,
+      "step": 44
+    },
+    {
+      "epoch": 0.07566204287515763,
+      "grad_norm": 4.760522365570068,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.551,
+      "step": 45
+    },
+    {
+      "epoch": 0.0773434216057167,
+      "grad_norm": 3.459176778793335,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.245,
+      "step": 46
+    },
+    {
+      "epoch": 0.07902480033627575,
+      "grad_norm": 4.063365936279297,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5102,
+      "step": 47
+    },
+    {
+      "epoch": 0.0807061790668348,
+      "grad_norm": 4.177626609802246,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.2577,
+      "step": 48
+    },
+    {
+      "epoch": 0.08238755779739386,
+      "grad_norm": 4.004427433013916,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.2727,
+      "step": 49
+    },
+    {
+      "epoch": 0.08406893652795293,
+      "grad_norm": 4.922773361206055,
+      "learning_rate": 0.0,
+      "loss": 1.3563,
+      "step": 50
+    },
+    {
+      "epoch": 0.08406893652795293,
+      "eval_loss": 1.7657277584075928,
+      "eval_runtime": 53.6445,
+      "eval_samples_per_second": 18.679,
+      "eval_steps_per_second": 2.349,
+      "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": 3.02966221307904e+16,
+  "total_flos": 4.86582113009664e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null