Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37218cbce08c23edb7033b1c5a5a11873eef860e07093ba52a0c56edc3797a3e
+oid sha256:5eedbdd9d92b949b0559942c67f6d800ba3e62986c6fcaf0dad2ddb985081fec
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15dac8417312ec8a770d6e0224523f16704e3564f2965c0e00c5fe08e68b636b
+oid sha256:d9e89f6e121591af8455f63514e90395c5e2ca3428315e546e4b2944bdfd352d
 size 40177764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a30009fc2d967b07eb25eb65b770b86de9350cad7919958dcc27ac07a24a997
+oid sha256:a649a471c0ea4ef958005b394da250a22a8389d6e850efa914a1b486e3856a1b
 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": 2.055764675140381,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.373134328358209,
+  "best_metric": 1.9968057870864868,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.746268656716418,
   "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": 119.362,
       "eval_steps_per_second": 15.845,
       "step": 25
+    },
+    {
+      "epoch": 0.3880597014925373,
+      "grad_norm": 0.39158010482788086,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.1612,
+      "step": 26
+    },
+    {
+      "epoch": 0.40298507462686567,
+      "grad_norm": 0.42965012788772583,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.2331,
+      "step": 27
+    },
+    {
+      "epoch": 0.417910447761194,
+      "grad_norm": 0.4510224759578705,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.1721,
+      "step": 28
+    },
+    {
+      "epoch": 0.43283582089552236,
+      "grad_norm": 0.4704110622406006,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.0252,
+      "step": 29
+    },
+    {
+      "epoch": 0.44776119402985076,
+      "grad_norm": 0.5712336301803589,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.0158,
+      "step": 30
+    },
+    {
+      "epoch": 0.4626865671641791,
+      "grad_norm": 0.5858246684074402,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.0812,
+      "step": 31
+    },
+    {
+      "epoch": 0.47761194029850745,
+      "grad_norm": 0.9474906325340271,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.0843,
+      "step": 32
+    },
+    {
+      "epoch": 0.4925373134328358,
+      "grad_norm": 0.24608998000621796,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.6666,
+      "step": 33
+    },
+    {
+      "epoch": 0.5074626865671642,
+      "grad_norm": 0.2545487582683563,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.8542,
+      "step": 34
+    },
+    {
+      "epoch": 0.5223880597014925,
+      "grad_norm": 0.25772571563720703,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8961,
+      "step": 35
+    },
+    {
+      "epoch": 0.5373134328358209,
+      "grad_norm": 0.3282116949558258,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.9271,
+      "step": 36
+    },
+    {
+      "epoch": 0.5522388059701493,
+      "grad_norm": 0.30054324865341187,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.99,
+      "step": 37
+    },
+    {
+      "epoch": 0.5671641791044776,
+      "grad_norm": 0.33032283186912537,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.9075,
+      "step": 38
+    },
+    {
+      "epoch": 0.582089552238806,
+      "grad_norm": 0.3541136384010315,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.1065,
+      "step": 39
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.36783766746520996,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.1716,
+      "step": 40
+    },
+    {
+      "epoch": 0.6119402985074627,
+      "grad_norm": 0.3704308569431305,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.0668,
+      "step": 41
+    },
+    {
+      "epoch": 0.6268656716417911,
+      "grad_norm": 0.41871926188468933,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.0886,
+      "step": 42
+    },
+    {
+      "epoch": 0.6417910447761194,
+      "grad_norm": 0.4612567126750946,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.176,
+      "step": 43
+    },
+    {
+      "epoch": 0.6567164179104478,
+      "grad_norm": 0.43885257840156555,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.0272,
+      "step": 44
+    },
+    {
+      "epoch": 0.6716417910447762,
+      "grad_norm": 0.5096978545188904,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.1226,
+      "step": 45
+    },
+    {
+      "epoch": 0.6865671641791045,
+      "grad_norm": 0.49920862913131714,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.8736,
+      "step": 46
+    },
+    {
+      "epoch": 0.7014925373134329,
+      "grad_norm": 0.6098780632019043,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.9208,
+      "step": 47
+    },
+    {
+      "epoch": 0.7164179104477612,
+      "grad_norm": 0.7482870817184448,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.972,
+      "step": 48
+    },
+    {
+      "epoch": 0.7313432835820896,
+      "grad_norm": 0.2268557995557785,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.6986,
+      "step": 49
+    },
+    {
+      "epoch": 0.746268656716418,
+      "grad_norm": 0.2336985319852829,
+      "learning_rate": 0.0,
+      "loss": 1.7152,
+      "step": 50
+    },
+    {
+      "epoch": 0.746268656716418,
+      "eval_loss": 1.9968057870864868,
+      "eval_runtime": 0.9661,
+      "eval_samples_per_second": 116.963,
+      "eval_steps_per_second": 15.526,
+      "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": 352285086449664.0,
+  "total_flos": 704570172899328.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null