Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4db56bb2075420794a7aa4257e6f467bce5f2a5feedd5cc798ddd3e7d40543a1
+oid sha256:7f00799a0b7c27a7b4b1c71fd2caf79a8aaf220df9f935895bf2835a07b0beaa
 size 912336848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c6811b162c75c4f51af3623162970bae65edbf910a3c03fc44da91ca64fe3bf
+oid sha256:af8b3eaba9c093ead6ffbd85961f9a21de75fe15be5eecdebffbc439f02a5e4b
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa090964efd49714eeb3ff52685595de7f43acd1bae2f113e1633ed8d6bda1b5
+oid sha256:fb6bc7cdb2886d851dce064963de096520d80a048f8567fb8afca8483908dfc0
 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": 1.1567610502243042,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016223231667748216,
+  "best_metric": 1.0394631624221802,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03244646333549643,
   "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": 17.443,
       "eval_steps_per_second": 2.184,
       "step": 25
+    },
+    {
+      "epoch": 0.016872160934458143,
+      "grad_norm": 423.1258239746094,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 4.3783,
+      "step": 26
+    },
+    {
+      "epoch": 0.01752109020116807,
+      "grad_norm": 19.292482376098633,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.7328,
+      "step": 27
+    },
+    {
+      "epoch": 0.018170019467878003,
+      "grad_norm": 3.9839913845062256,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 3.9131,
+      "step": 28
+    },
+    {
+      "epoch": 0.01881894873458793,
+      "grad_norm": 5.250899314880371,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 3.8158,
+      "step": 29
+    },
+    {
+      "epoch": 0.01946787800129786,
+      "grad_norm": 3.4630203247070312,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 4.1871,
+      "step": 30
+    },
+    {
+      "epoch": 0.020116807268007787,
+      "grad_norm": 4.317551612854004,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 4.7563,
+      "step": 31
+    },
+    {
+      "epoch": 0.020765736534717714,
+      "grad_norm": 4.866771221160889,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.3659,
+      "step": 32
+    },
+    {
+      "epoch": 0.021414665801427646,
+      "grad_norm": 5.2690839767456055,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 4.1365,
+      "step": 33
+    },
+    {
+      "epoch": 0.022063595068137574,
+      "grad_norm": 5.08319091796875,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 4.5015,
+      "step": 34
+    },
+    {
+      "epoch": 0.0227125243348475,
+      "grad_norm": 4.986558437347412,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.2522,
+      "step": 35
+    },
+    {
+      "epoch": 0.02336145360155743,
+      "grad_norm": 5.291998386383057,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.7079,
+      "step": 36
+    },
+    {
+      "epoch": 0.024010382868267358,
+      "grad_norm": 7.075346946716309,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 4.3515,
+      "step": 37
+    },
+    {
+      "epoch": 0.02465931213497729,
+      "grad_norm": 6.59442663192749,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 4.4537,
+      "step": 38
+    },
+    {
+      "epoch": 0.025308241401687217,
+      "grad_norm": 7.289731502532959,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 4.6425,
+      "step": 39
+    },
+    {
+      "epoch": 0.025957170668397145,
+      "grad_norm": 8.14652156829834,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.7023,
+      "step": 40
+    },
+    {
+      "epoch": 0.026606099935107073,
+      "grad_norm": 8.087379455566406,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.0411,
+      "step": 41
+    },
+    {
+      "epoch": 0.027255029201817,
+      "grad_norm": 8.625016212463379,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 4.4971,
+      "step": 42
+    },
+    {
+      "epoch": 0.027903958468526932,
+      "grad_norm": 8.698261260986328,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.0275,
+      "step": 43
+    },
+    {
+      "epoch": 0.02855288773523686,
+      "grad_norm": 9.690203666687012,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 4.6694,
+      "step": 44
+    },
+    {
+      "epoch": 0.029201817001946788,
+      "grad_norm": 10.64246940612793,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.3358,
+      "step": 45
+    },
+    {
+      "epoch": 0.029850746268656716,
+      "grad_norm": 9.350142478942871,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 3.6146,
+      "step": 46
+    },
+    {
+      "epoch": 0.030499675535366644,
+      "grad_norm": 9.56218433380127,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 3.4644,
+      "step": 47
+    },
+    {
+      "epoch": 0.031148604802076575,
+      "grad_norm": 16.128480911254883,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 5.3455,
+      "step": 48
+    },
+    {
+      "epoch": 0.0317975340687865,
+      "grad_norm": 15.799928665161133,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 4.5824,
+      "step": 49
+    },
+    {
+      "epoch": 0.03244646333549643,
+      "grad_norm": 13.623414993286133,
+      "learning_rate": 0.0,
+      "loss": 3.5276,
+      "step": 50
+    },
+    {
+      "epoch": 0.03244646333549643,
+      "eval_loss": 1.0394631624221802,
+      "eval_runtime": 148.7645,
+      "eval_samples_per_second": 17.45,
+      "eval_steps_per_second": 2.185,
+      "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": 3.19125133983744e+16,
+  "total_flos": 6.09238892150784e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null