Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5a08da0ee0b418d960bbc7e08594d1873c63fb666a0f4c0d7776ad3c6af394
+oid sha256:7c77bd252404343d59fa47e11d87b9d7494bdc0ce74fb6444c47871aca36d1f6
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f91c2b58570527b5de8d11055402027f916823c5e8256d59a932459e7bac2373
+oid sha256:65cf1d6e092f1f2385667e8efd41a0118af57063735c60905ff65cddd11c6b83
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:342d36d482e38fbc36cc0a28040792e6a4257d06cd930a5ace345aee66811294
+oid sha256:597c452dbb6d2e2055a44445aa9e337aa4085eacd11fcbc7213a5eb6f6055867
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1074437c4c638775a20a86de2e689d1a14d0ff4e4137df2ddeb45e94a776caef
+oid sha256:7803647d52fbd7429a283dc695ba7cf653ff890c06d5c50f67d0a09610438889
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6243711709976196,
-  "best_model_checkpoint": "miner_id_24/checkpoint-70",
-  "epoch": 0.019767031415460642,
+  "best_metric": 1.617271900177002,
+  "best_model_checkpoint": "miner_id_24/checkpoint-80",
+  "epoch": 0.022590893046240734,
   "eval_steps": 10,
-  "global_step": 70,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -561,6 +561,84 @@
       "eval_samples_per_second": 5.542,
       "eval_steps_per_second": 5.542,
       "step": 70
+    },
+    {
+      "epoch": 0.02004941757853865,
+      "grad_norm": 2.2794175148010254,
+      "learning_rate": 0.00019244917309000817,
+      "loss": 1.624,
+      "step": 71
+    },
+    {
+      "epoch": 0.02033180374161666,
+      "grad_norm": 1.5373339653015137,
+      "learning_rate": 0.00019220287022200707,
+      "loss": 1.8068,
+      "step": 72
+    },
+    {
+      "epoch": 0.02061418990469467,
+      "grad_norm": 0.9991006255149841,
+      "learning_rate": 0.0001919527772551451,
+      "loss": 1.6704,
+      "step": 73
+    },
+    {
+      "epoch": 0.02089657606777268,
+      "grad_norm": 1.392340064048767,
+      "learning_rate": 0.00019169890446976454,
+      "loss": 2.378,
+      "step": 74
+    },
+    {
+      "epoch": 0.02117896223085069,
+      "grad_norm": 1.1224641799926758,
+      "learning_rate": 0.00019144126230158127,
+      "loss": 1.6227,
+      "step": 75
+    },
+    {
+      "epoch": 0.021461348393928697,
+      "grad_norm": 1.2003456354141235,
+      "learning_rate": 0.0001911798613412557,
+      "loss": 2.4362,
+      "step": 76
+    },
+    {
+      "epoch": 0.021743734557006705,
+      "grad_norm": 1.102264642715454,
+      "learning_rate": 0.0001909147123339575,
+      "loss": 2.3662,
+      "step": 77
+    },
+    {
+      "epoch": 0.022026120720084717,
+      "grad_norm": 0.7298341989517212,
+      "learning_rate": 0.0001906458261789238,
+      "loss": 2.8474,
+      "step": 78
+    },
+    {
+      "epoch": 0.022308506883162726,
+      "grad_norm": 1.0796235799789429,
+      "learning_rate": 0.00019037321392901136,
+      "loss": 1.5521,
+      "step": 79
+    },
+    {
+      "epoch": 0.022590893046240734,
+      "grad_norm": 0.7039556503295898,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 2.47,
+      "step": 80
+    },
+    {
+      "epoch": 0.022590893046240734,
+      "eval_loss": 1.617271900177002,
+      "eval_runtime": 134.9383,
+      "eval_samples_per_second": 5.528,
+      "eval_steps_per_second": 5.528,
+      "step": 80
     }
   ],
   "logging_steps": 1,
@@ -589,7 +667,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6851625096314880.0,
+  "total_flos": 7830428681502720.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null