Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:203a6ca27c6fee76db92195c336954ada4023366ef0108ce5d7a4bd556c97ee5
+oid sha256:efe36a94f99d499fa1028d4fcb22e45ac493603d6236eae9f0dddecf33d008f9
 size 16794864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40564ecfcdf085763b0bdd67ac3184b60b87618c175e32e6e52fb38c210a8b26
+oid sha256:d204e5cbea2854cf468fd8e88d3a9b91735f508a66d871c6869f222bf5c4a26d
 size 8671162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efd99f1a17c322a8c0bd17151f0781fb499d1c01590259af17da9016d419d648
+oid sha256:de9277331b4a0c0a7edd4efcef7468e5c12a03150c0fcc67581dc8d9184679ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4930000305175781,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00343554066821266,
+  "best_metric": 1.2720811367034912,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00687108133642532,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 19.125,
       "eval_steps_per_second": 9.562,
       "step": 10
+    },
+    {
+      "epoch": 0.003779094735033926,
+      "grad_norm": 1.548321008682251,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 5.2723,
+      "step": 11
+    },
+    {
+      "epoch": 0.004122648801855192,
+      "grad_norm": 1.9904747009277344,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.3602,
+      "step": 12
+    },
+    {
+      "epoch": 0.004466202868676458,
+      "grad_norm": 3.255831480026245,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 6.9055,
+      "step": 13
+    },
+    {
+      "epoch": 0.004809756935497724,
+      "grad_norm": 2.463453769683838,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 5.5229,
+      "step": 14
+    },
+    {
+      "epoch": 0.00515331100231899,
+      "grad_norm": 2.633448362350464,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.1913,
+      "step": 15
+    },
+    {
+      "epoch": 0.00515331100231899,
+      "eval_loss": 1.3465347290039062,
+      "eval_runtime": 66.8518,
+      "eval_samples_per_second": 18.339,
+      "eval_steps_per_second": 9.17,
+      "step": 15
+    },
+    {
+      "epoch": 0.005496865069140256,
+      "grad_norm": 2.5608341693878174,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.3199,
+      "step": 16
+    },
+    {
+      "epoch": 0.005840419135961522,
+      "grad_norm": 2.9444522857666016,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 5.6491,
+      "step": 17
+    },
+    {
+      "epoch": 0.006183973202782788,
+      "grad_norm": 2.5232174396514893,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 4.9963,
+      "step": 18
+    },
+    {
+      "epoch": 0.006527527269604054,
+      "grad_norm": 2.6302788257598877,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 5.24,
+      "step": 19
+    },
+    {
+      "epoch": 0.00687108133642532,
+      "grad_norm": 2.6670913696289062,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 5.5155,
+      "step": 20
+    },
+    {
+      "epoch": 0.00687108133642532,
+      "eval_loss": 1.2720811367034912,
+      "eval_runtime": 64.0406,
+      "eval_samples_per_second": 19.144,
+      "eval_steps_per_second": 9.572,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 437516456951808.0,
+  "total_flos": 869423728558080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null