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:c5dd2fc199e7d77fa45485ac65b1571a45ef9119debc5d8aa35a9ce4d0f6cfec
+oid sha256:fba9d35f5487ceb2a1baab656175d41c0632dface7631d20d873a87df5dcbd42
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3928520569b95bae06a1c1f9ce79c48772e2f4145cffb377ba9cdd0327f4d742
+oid sha256:789496cd739dc0adbb9e851556f92e463050497f7465a63f4c4e08cde264f8a3
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0d3036b81cbab0d9e82c39383f4fb9d8c4a9a241f3cf27f4bc2d9f232312d7
+oid sha256:5d54fcd44c05e2e5adefa313ba15b040870042c592bb969a6166322a9357cc52
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c931ece4da598a541d357f6c98f67481603252e193960022d37ddd49c584b1f
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2505565285682678,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4149377593360996,
+  "best_metric": 0.23422786593437195,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8298755186721992,
   "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": 2.653,
       "eval_steps_per_second": 0.338,
       "step": 25
+    },
+    {
+      "epoch": 0.4315352697095436,
+      "grad_norm": 0.5019552111625671,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.2942,
+      "step": 26
+    },
+    {
+      "epoch": 0.44813278008298757,
+      "grad_norm": 0.37283846735954285,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.8131,
+      "step": 27
+    },
+    {
+      "epoch": 0.46473029045643155,
+      "grad_norm": 0.32147935032844543,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.452,
+      "step": 28
+    },
+    {
+      "epoch": 0.48132780082987553,
+      "grad_norm": 0.40596452355384827,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.7471,
+      "step": 29
+    },
+    {
+      "epoch": 0.4979253112033195,
+      "grad_norm": 0.31123867630958557,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.1211,
+      "step": 30
+    },
+    {
+      "epoch": 0.5145228215767634,
+      "grad_norm": 0.3040826916694641,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.6645,
+      "step": 31
+    },
+    {
+      "epoch": 0.5311203319502075,
+      "grad_norm": 0.360746830701828,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.5069,
+      "step": 32
+    },
+    {
+      "epoch": 0.5477178423236515,
+      "grad_norm": 0.28188955783843994,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.374,
+      "step": 33
+    },
+    {
+      "epoch": 0.5643153526970954,
+      "grad_norm": 0.352664977312088,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.5923,
+      "step": 34
+    },
+    {
+      "epoch": 0.5809128630705395,
+      "grad_norm": 0.4458906054496765,
+      "learning_rate": 5e-05,
+      "loss": 0.9785,
+      "step": 35
+    },
+    {
+      "epoch": 0.5975103734439834,
+      "grad_norm": 0.37693920731544495,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.4362,
+      "step": 36
+    },
+    {
+      "epoch": 0.6141078838174274,
+      "grad_norm": 0.6866313219070435,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.8713,
+      "step": 37
+    },
+    {
+      "epoch": 0.6307053941908713,
+      "grad_norm": 0.5577489733695984,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.5318,
+      "step": 38
+    },
+    {
+      "epoch": 0.6473029045643154,
+      "grad_norm": 0.31835877895355225,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.4399,
+      "step": 39
+    },
+    {
+      "epoch": 0.6639004149377593,
+      "grad_norm": 0.4343944489955902,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7351,
+      "step": 40
+    },
+    {
+      "epoch": 0.6804979253112033,
+      "grad_norm": 0.6331047415733337,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.6234,
+      "step": 41
+    },
+    {
+      "epoch": 0.6970954356846473,
+      "grad_norm": 0.2764015793800354,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.5407,
+      "step": 42
+    },
+    {
+      "epoch": 0.7136929460580913,
+      "grad_norm": 0.28386223316192627,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.0469,
+      "step": 43
+    },
+    {
+      "epoch": 0.7302904564315352,
+      "grad_norm": 0.31652379035949707,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.5524,
+      "step": 44
+    },
+    {
+      "epoch": 0.7468879668049793,
+      "grad_norm": 0.4024736285209656,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6643,
+      "step": 45
+    },
+    {
+      "epoch": 0.7634854771784232,
+      "grad_norm": 0.38829195499420166,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.4115,
+      "step": 46
+    },
+    {
+      "epoch": 0.7800829875518672,
+      "grad_norm": 0.3871329426765442,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3885,
+      "step": 47
+    },
+    {
+      "epoch": 0.7966804979253111,
+      "grad_norm": 0.2926025986671448,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.584,
+      "step": 48
+    },
+    {
+      "epoch": 0.8132780082987552,
+      "grad_norm": 0.2687753438949585,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.907,
+      "step": 49
+    },
+    {
+      "epoch": 0.8298755186721992,
+      "grad_norm": 0.24473470449447632,
+      "learning_rate": 0.0,
+      "loss": 0.4286,
+      "step": 50
+    },
+    {
+      "epoch": 0.8298755186721992,
+      "eval_loss": 0.23422786593437195,
+      "eval_runtime": 38.453,
+      "eval_samples_per_second": 2.653,
+      "eval_steps_per_second": 0.338,
+      "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": 1.1721014891249664e+17,
+  "total_flos": 2.3699634505383936e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null