Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5710f43b1ca86b1ae02be0c943dbfadc7a95c80e20f4f98b8c76b6df35df0832
+oid sha256:c05a48f6984c76dd62282e9a8f73b741b5f5de14b572704b6ad73b8b848d6ed6
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9b5c4f22d6e05c9d3eb270017abc94ad216406032b64bde1e4142f1a065161
+oid sha256:b0beaa75d586714604dd7957522a8668913869ef9a54239c0652daf3195e94fc
 size 147359892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84337a0b5baecd930c964daa54054e5734ed5e51c3d921251b77b2277716e16c
+oid sha256:17fdeb77d06dcedbaefd3bb0d7470406b3d6cbc5bb7b22f3c7cb407555ab75a4
 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": 2.200383424758911,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017593244194229415,
+  "best_metric": 2.105609655380249,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03518648838845883,
   "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": 63.476,
       "eval_steps_per_second": 7.954,
       "step": 25
+    },
+    {
+      "epoch": 0.018296973961998593,
+      "grad_norm": 0.8232203722000122,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.1872,
+      "step": 26
+    },
+    {
+      "epoch": 0.019000703729767768,
+      "grad_norm": 0.6864263415336609,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.1791,
+      "step": 27
+    },
+    {
+      "epoch": 0.019704433497536946,
+      "grad_norm": 0.7136126160621643,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.2234,
+      "step": 28
+    },
+    {
+      "epoch": 0.02040816326530612,
+      "grad_norm": 1.1825441122055054,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.4192,
+      "step": 29
+    },
+    {
+      "epoch": 0.0211118930330753,
+      "grad_norm": 0.7965120077133179,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.0211,
+      "step": 30
+    },
+    {
+      "epoch": 0.021815622800844477,
+      "grad_norm": 0.6437466740608215,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.0912,
+      "step": 31
+    },
+    {
+      "epoch": 0.022519352568613652,
+      "grad_norm": 0.7274101376533508,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.1358,
+      "step": 32
+    },
+    {
+      "epoch": 0.02322308233638283,
+      "grad_norm": 0.7753286361694336,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.2257,
+      "step": 33
+    },
+    {
+      "epoch": 0.023926812104152005,
+      "grad_norm": 0.6189289689064026,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.0214,
+      "step": 34
+    },
+    {
+      "epoch": 0.024630541871921183,
+      "grad_norm": 0.909999430179596,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.4424,
+      "step": 35
+    },
+    {
+      "epoch": 0.025334271639690358,
+      "grad_norm": 0.7896960377693176,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.0872,
+      "step": 36
+    },
+    {
+      "epoch": 0.026038001407459536,
+      "grad_norm": 0.6156556010246277,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.9546,
+      "step": 37
+    },
+    {
+      "epoch": 0.02674173117522871,
+      "grad_norm": 0.6940821409225464,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.8075,
+      "step": 38
+    },
+    {
+      "epoch": 0.02744546094299789,
+      "grad_norm": 0.6875196695327759,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8502,
+      "step": 39
+    },
+    {
+      "epoch": 0.028149190710767064,
+      "grad_norm": 0.9812740087509155,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.9774,
+      "step": 40
+    },
+    {
+      "epoch": 0.028852920478536243,
+      "grad_norm": 0.8174262642860413,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.7649,
+      "step": 41
+    },
+    {
+      "epoch": 0.029556650246305417,
+      "grad_norm": 0.8707631826400757,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7106,
+      "step": 42
+    },
+    {
+      "epoch": 0.030260380014074596,
+      "grad_norm": 1.0497000217437744,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.75,
+      "step": 43
+    },
+    {
+      "epoch": 0.03096410978184377,
+      "grad_norm": 0.9923905730247498,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.8375,
+      "step": 44
+    },
+    {
+      "epoch": 0.03166783954961295,
+      "grad_norm": 1.0750401020050049,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.7751,
+      "step": 45
+    },
+    {
+      "epoch": 0.03237156931738212,
+      "grad_norm": 1.0641475915908813,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.0445,
+      "step": 46
+    },
+    {
+      "epoch": 0.033075299085151305,
+      "grad_norm": 1.1732888221740723,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0729,
+      "step": 47
+    },
+    {
+      "epoch": 0.03377902885292048,
+      "grad_norm": 1.6676044464111328,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2338,
+      "step": 48
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 2.1533820629119873,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.0833,
+      "step": 49
+    },
+    {
+      "epoch": 0.03518648838845883,
+      "grad_norm": 3.547422170639038,
+      "learning_rate": 0.0,
+      "loss": 2.8245,
+      "step": 50
+    },
+    {
+      "epoch": 0.03518648838845883,
+      "eval_loss": 2.105609655380249,
+      "eval_runtime": 37.6568,
+      "eval_samples_per_second": 63.574,
+      "eval_steps_per_second": 7.967,
+      "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": 4384478138990592.0,
+  "total_flos": 8520778270113792.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null