Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef4c98cd6fe237255b766d064e60752991172fa8438613c00f8e7c9967bcbe9
+oid sha256:1abb5a217b4afa1aff29d837030185effe1e2669fac770bd908a7a3d5fed377d
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d17d8750046461926a3fc4da9906f4b6d39c4b86c33792cf9d4c0f56b9ea58
+oid sha256:39ccf994355869bc6f968b72a407d8bdcfcfd64947b52a3a70e940c71b06af02
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6293cf66f9c869994415282866263b7d7f292834d1960442a44e775a9e4ee8cf
+oid sha256:27cb5235c1ebbb48cb918a59bbc1e418b725efcf661ee3dc443715df256b3d4c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d65cf705427ed2674e6aeebeb22308f3acdd494cdcbe917989f59cb90e3a612e
+oid sha256:63cfa84b4e965fc9304291253951d06be7c350c99ee9d222b64adbdbd4a9d81f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa819954577aca468cbb20ecd6e34c28f4e617ebf937efcdc3af64ce2f67ae8
+oid sha256:6bb3b0488f922e17ddfbc0d3fbf54c96e5be8e1c4648d069cc6351d87d1f1cea
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23e558ebf9c565cb2fba0b38a6184580c03a3e7b20ae5432f856167178e1783d
+oid sha256:51e2a23ebe218cc5d170d66c1fe8c40de4190dc2ad1fd93cd6e1297e7f3281c2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.034134864807129,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006465064408204167,
+  "best_metric": 2.9313533306121826,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.012930128816408334,
   "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": 87.834,
       "eval_steps_per_second": 10.981,
       "step": 25
+    },
+    {
+      "epoch": 0.006723666984532334,
+      "grad_norm": 1.964606523513794,
+      "learning_rate": 5e-05,
+      "loss": 2.7854,
+      "step": 26
+    },
+    {
+      "epoch": 0.0069822695608605,
+      "grad_norm": 1.8417248725891113,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.9155,
+      "step": 27
+    },
+    {
+      "epoch": 0.0072408721371886664,
+      "grad_norm": 1.793028473854065,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.8597,
+      "step": 28
+    },
+    {
+      "epoch": 0.007499474713516833,
+      "grad_norm": 1.854422926902771,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.9504,
+      "step": 29
+    },
+    {
+      "epoch": 0.007758077289845,
+      "grad_norm": 1.4125136137008667,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.8636,
+      "step": 30
+    },
+    {
+      "epoch": 0.008016679866173167,
+      "grad_norm": 1.5822298526763916,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.033,
+      "step": 31
+    },
+    {
+      "epoch": 0.008275282442501333,
+      "grad_norm": 1.4431718587875366,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.0272,
+      "step": 32
+    },
+    {
+      "epoch": 0.0085338850188295,
+      "grad_norm": 2.054440975189209,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.1003,
+      "step": 33
+    },
+    {
+      "epoch": 0.008792487595157666,
+      "grad_norm": 1.8294641971588135,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.9858,
+      "step": 34
+    },
+    {
+      "epoch": 0.009051090171485834,
+      "grad_norm": 1.8595656156539917,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.0471,
+      "step": 35
+    },
+    {
+      "epoch": 0.009309692747814,
+      "grad_norm": 2.144545316696167,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.9967,
+      "step": 36
+    },
+    {
+      "epoch": 0.009568295324142167,
+      "grad_norm": 2.1275172233581543,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.1765,
+      "step": 37
+    },
+    {
+      "epoch": 0.009826897900470333,
+      "grad_norm": 1.1156597137451172,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.7978,
+      "step": 38
+    },
+    {
+      "epoch": 0.0100855004767985,
+      "grad_norm": 1.2987682819366455,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.6641,
+      "step": 39
+    },
+    {
+      "epoch": 0.010344103053126667,
+      "grad_norm": 1.2446664571762085,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.7144,
+      "step": 40
+    },
+    {
+      "epoch": 0.010602705629454834,
+      "grad_norm": 1.220151662826538,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.8118,
+      "step": 41
+    },
+    {
+      "epoch": 0.010861308205783,
+      "grad_norm": 1.4637597799301147,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.8893,
+      "step": 42
+    },
+    {
+      "epoch": 0.011119910782111166,
+      "grad_norm": 1.2210360765457153,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.9138,
+      "step": 43
+    },
+    {
+      "epoch": 0.011378513358439334,
+      "grad_norm": 1.2036255598068237,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.0561,
+      "step": 44
+    },
+    {
+      "epoch": 0.0116371159347675,
+      "grad_norm": 1.1922022104263306,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.8757,
+      "step": 45
+    },
+    {
+      "epoch": 0.011895718511095667,
+      "grad_norm": 1.218916416168213,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.9347,
+      "step": 46
+    },
+    {
+      "epoch": 0.012154321087423833,
+      "grad_norm": 1.652422547340393,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.9598,
+      "step": 47
+    },
+    {
+      "epoch": 0.012412923663752,
+      "grad_norm": 1.3585187196731567,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.0889,
+      "step": 48
+    },
+    {
+      "epoch": 0.012671526240080166,
+      "grad_norm": 1.5648044347763062,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.1441,
+      "step": 49
+    },
+    {
+      "epoch": 0.012930128816408334,
+      "grad_norm": 2.3186755180358887,
+      "learning_rate": 0.0,
+      "loss": 3.2848,
+      "step": 50
+    },
+    {
+      "epoch": 0.012930128816408334,
+      "eval_loss": 2.9313533306121826,
+      "eval_runtime": 296.4974,
+      "eval_samples_per_second": 87.862,
+      "eval_steps_per_second": 10.985,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null