Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65bd76f4b188c167698f795759a1b6cec2fb920886cf92ae204178545371e0ba
+oid sha256:d5069f1b912a694beb9da3438237c3abe4e0d65338f0c1c99bed9d11ce5b2db8
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e40dea7c43aa90995d153a0ca2047ae7909fd5a4aef936506900bff8612ca326
+oid sha256:cf6f1febce19eb06f150279e8b8a661352840ef224fec5017479086926802e80
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ac0ba37bc7cc1ace05d6a65c14ebefa26c8ca93fb97f611f87af4a5a65848b0
+oid sha256:4b76e9e24cb20845bfe94bb4ebaaf7dfcd160a0ac1e56e2351c474a3d5a39493
 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": 0.38685178756713867,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.014188422247446084,
+  "best_metric": 0.36684566736221313,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.028376844494892167,
   "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": 19.644,
       "eval_steps_per_second": 2.456,
       "step": 25
+    },
+    {
+      "epoch": 0.014755959137343927,
+      "grad_norm": 3.0787408351898193,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.2978,
+      "step": 26
+    },
+    {
+      "epoch": 0.01532349602724177,
+      "grad_norm": 3.155953884124756,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.1437,
+      "step": 27
+    },
+    {
+      "epoch": 0.015891032917139614,
+      "grad_norm": 3.611130952835083,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.4887,
+      "step": 28
+    },
+    {
+      "epoch": 0.016458569807037457,
+      "grad_norm": 3.260758876800537,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.5036,
+      "step": 29
+    },
+    {
+      "epoch": 0.0170261066969353,
+      "grad_norm": 3.7945919036865234,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.6955,
+      "step": 30
+    },
+    {
+      "epoch": 0.017593643586833144,
+      "grad_norm": 2.8555104732513428,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.3289,
+      "step": 31
+    },
+    {
+      "epoch": 0.018161180476730987,
+      "grad_norm": 3.1343414783477783,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.383,
+      "step": 32
+    },
+    {
+      "epoch": 0.01872871736662883,
+      "grad_norm": 3.477522134780884,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.5404,
+      "step": 33
+    },
+    {
+      "epoch": 0.019296254256526674,
+      "grad_norm": 3.386622190475464,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.5852,
+      "step": 34
+    },
+    {
+      "epoch": 0.019863791146424517,
+      "grad_norm": 3.3111960887908936,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5111,
+      "step": 35
+    },
+    {
+      "epoch": 0.02043132803632236,
+      "grad_norm": 3.756173610687256,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.5469,
+      "step": 36
+    },
+    {
+      "epoch": 0.020998864926220204,
+      "grad_norm": 3.696594715118408,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.6391,
+      "step": 37
+    },
+    {
+      "epoch": 0.021566401816118047,
+      "grad_norm": 3.2744596004486084,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.3505,
+      "step": 38
+    },
+    {
+      "epoch": 0.02213393870601589,
+      "grad_norm": 3.4827823638916016,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.2968,
+      "step": 39
+    },
+    {
+      "epoch": 0.022701475595913734,
+      "grad_norm": 3.311213970184326,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.2421,
+      "step": 40
+    },
+    {
+      "epoch": 0.023269012485811577,
+      "grad_norm": 3.040865898132324,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.3189,
+      "step": 41
+    },
+    {
+      "epoch": 0.02383654937570942,
+      "grad_norm": 3.5166332721710205,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.245,
+      "step": 42
+    },
+    {
+      "epoch": 0.024404086265607264,
+      "grad_norm": 3.3054957389831543,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.3139,
+      "step": 43
+    },
+    {
+      "epoch": 0.024971623155505107,
+      "grad_norm": 3.441504716873169,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.3411,
+      "step": 44
+    },
+    {
+      "epoch": 0.02553916004540295,
+      "grad_norm": 4.734251022338867,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.731,
+      "step": 45
+    },
+    {
+      "epoch": 0.026106696935300794,
+      "grad_norm": 3.543067455291748,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.3091,
+      "step": 46
+    },
+    {
+      "epoch": 0.026674233825198637,
+      "grad_norm": 3.620821475982666,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.3049,
+      "step": 47
+    },
+    {
+      "epoch": 0.02724177071509648,
+      "grad_norm": 3.8930320739746094,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.2624,
+      "step": 48
+    },
+    {
+      "epoch": 0.027809307604994324,
+      "grad_norm": 4.123157501220703,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.3782,
+      "step": 49
+    },
+    {
+      "epoch": 0.028376844494892167,
+      "grad_norm": 4.4753336906433105,
+      "learning_rate": 0.0,
+      "loss": 1.3247,
+      "step": 50
+    },
+    {
+      "epoch": 0.028376844494892167,
+      "eval_loss": 0.36684566736221313,
+      "eval_runtime": 150.9171,
+      "eval_samples_per_second": 19.666,
+      "eval_steps_per_second": 2.458,
+      "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": 3.077975441198285e+16,
+  "total_flos": 4.867496046546125e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null