Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c32e60c57250c51934f542ff2e75446d1c4cf392e777594b077e17ea6ad239
+oid sha256:94ac5a06868d4549d8ca809aceb34d2f9203c57f47f62226617dba3c46e929b9
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78cd83f855bd80bf0c0a895685a76b346681eb6199b8673ce02a1764809414f1
+oid sha256:a1b147b7a755f582d5d04042105d6e705c48a46753db7af1c5632e3edd95f8c0
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:820fcfa3250b03ccb2011d1c28382f78231a7cd53b56f3e8494ea4c7f9ea8506
+oid sha256:67ade7c6f7575905253c20fecd77ea3dd7d528c69921646b6c58b5e79233ee72
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23b27ab0ae2b9af6f3d4c84cdaf8b0fc887acf71f8f726b270a3bce2845000a9
+oid sha256:d5c84ec0ff3c8c6aa13b25568668096db118f67ce80a9fa015a625446606f15d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.034589767456055,
-  "best_model_checkpoint": "miner_id_24/checkpoint-90",
-  "epoch": 0.004067704684639895,
+  "best_metric": 11.032732963562012,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.004519671871822106,
   "eval_steps": 5,
-  "global_step": 90,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -789,6 +789,92 @@
       "eval_samples_per_second": 52.835,
       "eval_steps_per_second": 26.421,
       "step": 90
+    },
+    {
+      "epoch": 0.004112901403358116,
+      "grad_norm": 0.5208268761634827,
+      "learning_rate": 0.00018681546242521786,
+      "loss": 44.1346,
+      "step": 91
+    },
+    {
+      "epoch": 0.004158098122076338,
+      "grad_norm": 0.6029201149940491,
+      "learning_rate": 0.00018649548579446936,
+      "loss": 44.152,
+      "step": 92
+    },
+    {
+      "epoch": 0.004203294840794558,
+      "grad_norm": 0.468414843082428,
+      "learning_rate": 0.0001861719536730795,
+      "loss": 44.117,
+      "step": 93
+    },
+    {
+      "epoch": 0.004248491559512779,
+      "grad_norm": 0.3942670226097107,
+      "learning_rate": 0.00018584487936018661,
+      "loss": 44.137,
+      "step": 94
+    },
+    {
+      "epoch": 0.004293688278231,
+      "grad_norm": 0.49822431802749634,
+      "learning_rate": 0.00018551427630053463,
+      "loss": 44.119,
+      "step": 95
+    },
+    {
+      "epoch": 0.004293688278231,
+      "eval_loss": 11.03354549407959,
+      "eval_runtime": 176.0642,
+      "eval_samples_per_second": 52.918,
+      "eval_steps_per_second": 26.462,
+      "step": 95
+    },
+    {
+      "epoch": 0.004338884996949221,
+      "grad_norm": 0.5527846813201904,
+      "learning_rate": 0.00018518015808392045,
+      "loss": 44.0893,
+      "step": 96
+    },
+    {
+      "epoch": 0.004384081715667443,
+      "grad_norm": 0.5725367665290833,
+      "learning_rate": 0.00018484253844463526,
+      "loss": 44.1162,
+      "step": 97
+    },
+    {
+      "epoch": 0.004429278434385664,
+      "grad_norm": 0.49278348684310913,
+      "learning_rate": 0.00018450143126090015,
+      "loss": 44.1031,
+      "step": 98
+    },
+    {
+      "epoch": 0.004474475153103885,
+      "grad_norm": 0.4361265301704407,
+      "learning_rate": 0.00018415685055429533,
+      "loss": 44.1386,
+      "step": 99
+    },
+    {
+      "epoch": 0.004519671871822106,
+      "grad_norm": 0.397714763879776,
+      "learning_rate": 0.00018380881048918405,
+      "loss": 44.1072,
+      "step": 100
+    },
+    {
+      "epoch": 0.004519671871822106,
+      "eval_loss": 11.032732963562012,
+      "eval_runtime": 176.1844,
+      "eval_samples_per_second": 52.882,
+      "eval_steps_per_second": 26.444,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -817,7 +903,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 945605836800.0,
+  "total_flos": 1050673152000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null