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:a23ac2f068060ba83252920597374aa1abe381d7af70b8564e09b564a99292fa
+oid sha256:0375dfbc1d62dbefd074b720c76a617c1dc7e1e921ac6c49a2f1a18f7a2c8a80
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fefe58d1f69ba425d93ad00aedc3d4c87f9eddd437164902217da638374d2105
+oid sha256:c3b4146d38d8bf361514952a18ec537d204441772e5420e56b371ee7bb9eb5bc
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80de3bfe8c8ad667c954ac8f82b32b6f6625228bd8f595eb12bd884d46f5eb01
+oid sha256:8246ad2f0f74a73025f6799af20b5f80df6a56da21c11a33bcea855c44859673
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.17667844522968199,
+  "epoch": 0.35335689045936397,
   "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": 57.984,
       "eval_steps_per_second": 7.278,
       "step": 25
+    },
+    {
+      "epoch": 0.18374558303886926,
+      "grad_norm": 0.0,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.19081272084805653,
+      "grad_norm": 0.0,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.1978798586572438,
+      "grad_norm": 2.0653741359710693,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.378,
+      "step": 28
+    },
+    {
+      "epoch": 0.2049469964664311,
+      "grad_norm": 0.0,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.21201413427561838,
+      "grad_norm": 0.0,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.21908127208480566,
+      "grad_norm": 0.0,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.22614840989399293,
+      "grad_norm": 8.19146728515625,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.0902,
+      "step": 32
+    },
+    {
+      "epoch": 0.2332155477031802,
+      "grad_norm": 0.0,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.24028268551236748,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.24734982332155478,
+      "grad_norm": 0.0,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.254416961130742,
+      "grad_norm": 1.1065750122070312,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.1358,
+      "step": 36
+    },
+    {
+      "epoch": 0.26148409893992935,
+      "grad_norm": 1.098425269126892,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.1901,
+      "step": 37
+    },
+    {
+      "epoch": 0.26855123674911663,
+      "grad_norm": 4.422745704650879,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.2529,
+      "step": 38
+    },
+    {
+      "epoch": 0.2756183745583039,
+      "grad_norm": 1.6350035667419434,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.1209,
+      "step": 39
+    },
+    {
+      "epoch": 0.2826855123674912,
+      "grad_norm": 0.9407490491867065,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.1377,
+      "step": 40
+    },
+    {
+      "epoch": 0.28975265017667845,
+      "grad_norm": 0.9304065704345703,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.961,
+      "step": 41
+    },
+    {
+      "epoch": 0.2968197879858657,
+      "grad_norm": 0.800937831401825,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.9086,
+      "step": 42
+    },
+    {
+      "epoch": 0.303886925795053,
+      "grad_norm": 0.9793635010719299,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.1349,
+      "step": 43
+    },
+    {
+      "epoch": 0.31095406360424027,
+      "grad_norm": 0.9108982086181641,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.1596,
+      "step": 44
+    },
+    {
+      "epoch": 0.31802120141342755,
+      "grad_norm": 0.7559174299240112,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8285,
+      "step": 45
+    },
+    {
+      "epoch": 0.3250883392226148,
+      "grad_norm": 0.9393735527992249,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.8102,
+      "step": 46
+    },
+    {
+      "epoch": 0.3321554770318021,
+      "grad_norm": 1.0659395456314087,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.0655,
+      "step": 47
+    },
+    {
+      "epoch": 0.3392226148409894,
+      "grad_norm": 0.970039427280426,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.8879,
+      "step": 48
+    },
+    {
+      "epoch": 0.3462897526501767,
+      "grad_norm": 0.7782996296882629,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.7354,
+      "step": 49
+    },
+    {
+      "epoch": 0.35335689045936397,
+      "grad_norm": 1.0545905828475952,
+      "learning_rate": 0.0,
+      "loss": 0.9708,
+      "step": 50
+    },
+    {
+      "epoch": 0.35335689045936397,
+      "eval_loss": NaN,
+      "eval_runtime": 4.0268,
+      "eval_samples_per_second": 59.352,
+      "eval_steps_per_second": 7.45,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3673953864253440.0,
+  "total_flos": 7347907728506880.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null