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:a100ebbdd9154155e516c0ce5d1b92fbcbbc6d5e14db1b9333e0ca55deb86849
+oid sha256:89ace21b1ba72cbed6ad2a7d038938e867c3367c6af2951f8acf4099764dd87d
 size 119975656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4d993127355e6a2d6642c840e81ce7ce40eebb6b0f3d38e9c8f117747616d0
+oid sha256:00e7de917bddf78aa82bb395e9fadf3e4516081b5d329a7cbb8e5431b3bdbb44
 size 240145026

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2079cea96c0bb3e6e340774b5a854f44917f6d3550d3e80b86a26207bda54f9c
+oid sha256:a88ec51efc4b3760b7bedd3c55ac45cf0e4933718229c7ffee5b209b76ae4ffe
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:142033beddee2db196e2e84cd984f93b646b57fb4027d9c3ee64eab4af70ebdd
+oid sha256:d37f600083f53a5298119d68c608720181fbbf4cc6bbecb73fe7f243482d2ea3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac094880bc693ab7f3abebb22db2bfefbfe08d6662df2fd63a5747a7fe6b9399
+oid sha256:42b72bc570d63cdd48033084e43567dbb5289267612068d6abe0b05e59663e2c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:805a782ea9bca56dc47ca13221989dfa8e79c26f739c18154309b2fe1d096be8
+oid sha256:29115f00d9e38f258b8ad1bd66ea6b9bd124b631b7326158fe5f5cfa50f8ba23
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7703685760498047,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.023945643389505823,
+  "best_metric": 0.6595383286476135,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.047891286779011645,
   "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": 18.115,
       "eval_steps_per_second": 4.71,
       "step": 25
+    },
+    {
+      "epoch": 0.024903469125086054,
+      "grad_norm": 3.212273120880127,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.8884,
+      "step": 26
+    },
+    {
+      "epoch": 0.025861294860666288,
+      "grad_norm": 3.1316325664520264,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.8394,
+      "step": 27
+    },
+    {
+      "epoch": 0.02681912059624652,
+      "grad_norm": 2.400233507156372,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7776,
+      "step": 28
+    },
+    {
+      "epoch": 0.027776946331826754,
+      "grad_norm": 1.5806422233581543,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7254,
+      "step": 29
+    },
+    {
+      "epoch": 0.028734772067406985,
+      "grad_norm": 1.1703928709030151,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.7256,
+      "step": 30
+    },
+    {
+      "epoch": 0.02969259780298722,
+      "grad_norm": 1.0857999324798584,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.6946,
+      "step": 31
+    },
+    {
+      "epoch": 0.03065042353856745,
+      "grad_norm": 1.0689618587493896,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.6785,
+      "step": 32
+    },
+    {
+      "epoch": 0.03160824927414768,
+      "grad_norm": 1.065096378326416,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.6666,
+      "step": 33
+    },
+    {
+      "epoch": 0.03256607500972792,
+      "grad_norm": 1.090894341468811,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.6828,
+      "step": 34
+    },
+    {
+      "epoch": 0.03352390074530815,
+      "grad_norm": 0.8290038108825684,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.6704,
+      "step": 35
+    },
+    {
+      "epoch": 0.03448172648088838,
+      "grad_norm": 0.8014963865280151,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.6749,
+      "step": 36
+    },
+    {
+      "epoch": 0.03543955221646861,
+      "grad_norm": 0.9459187984466553,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6879,
+      "step": 37
+    },
+    {
+      "epoch": 0.03639737795204885,
+      "grad_norm": 1.419850468635559,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7928,
+      "step": 38
+    },
+    {
+      "epoch": 0.03735520368762908,
+      "grad_norm": 2.180847406387329,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.7293,
+      "step": 39
+    },
+    {
+      "epoch": 0.03831302942320931,
+      "grad_norm": 1.8599144220352173,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.6973,
+      "step": 40
+    },
+    {
+      "epoch": 0.039270855158789544,
+      "grad_norm": 1.7160967588424683,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.6738,
+      "step": 41
+    },
+    {
+      "epoch": 0.04022868089436978,
+      "grad_norm": 1.5232151746749878,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.6755,
+      "step": 42
+    },
+    {
+      "epoch": 0.041186506629950013,
+      "grad_norm": 1.1328383684158325,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6505,
+      "step": 43
+    },
+    {
+      "epoch": 0.042144332365530245,
+      "grad_norm": 0.9517636895179749,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6339,
+      "step": 44
+    },
+    {
+      "epoch": 0.04310215810111048,
+      "grad_norm": 0.9324932098388672,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6245,
+      "step": 45
+    },
+    {
+      "epoch": 0.044059983836690714,
+      "grad_norm": 0.7847539782524109,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6317,
+      "step": 46
+    },
+    {
+      "epoch": 0.045017809572270945,
+      "grad_norm": 0.9269770383834839,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6517,
+      "step": 47
+    },
+    {
+      "epoch": 0.045975635307851176,
+      "grad_norm": 1.0401601791381836,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.6545,
+      "step": 48
+    },
+    {
+      "epoch": 0.046933461043431414,
+      "grad_norm": 1.3331917524337769,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.6781,
+      "step": 49
+    },
+    {
+      "epoch": 0.047891286779011645,
+      "grad_norm": 1.9794204235076904,
+      "learning_rate": 1e-05,
+      "loss": 0.7522,
+      "step": 50
+    },
+    {
+      "epoch": 0.047891286779011645,
+      "eval_loss": 0.6595383286476135,
+      "eval_runtime": 2.7637,
+      "eval_samples_per_second": 18.092,
+      "eval_steps_per_second": 4.704,
+      "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": 6.11705079988224e+16,
+  "total_flos": 1.223410159976448e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null