Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2110b3beace0778c82f69d3a8bfacd3012172b7d4514fe104a435dbc7498c954
+oid sha256:79ef9c768288875ba42105c9b7e33c6c74b287d5bc89681f1e65a465e8b2f071
 size 159712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71ac19aa47f745c45f132e0610b5ff5cd237f270c551a411373d617fc36f8ce9
+oid sha256:0416923b5ba8eb5712edf4cb6581a7627d06051cf03619e0acd1ba949bf26c2d
 size 336202

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.836539268493652,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005401974421651113,
+  "best_metric": 10.82991886138916,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0010803948843302227,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 193.367,
       "eval_steps_per_second": 96.696,
       "step": 10
+    },
+    {
+      "epoch": 0.0006482369305981337,
+      "grad_norm": 0.11939119547605515,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 10.8375,
+      "step": 12
+    },
+    {
+      "epoch": 0.0008102961632476671,
+      "grad_norm": 0.1792188137769699,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 10.8329,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008102961632476671,
+      "eval_loss": 10.833067893981934,
+      "eval_runtime": 40.3375,
+      "eval_samples_per_second": 193.244,
+      "eval_steps_per_second": 96.635,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009723553958972004,
+      "grad_norm": 0.16819672286510468,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.8347,
+      "step": 18
+    },
+    {
+      "epoch": 0.0010803948843302227,
+      "eval_loss": 10.82991886138916,
+      "eval_runtime": 40.4851,
+      "eval_samples_per_second": 192.54,
+      "eval_steps_per_second": 96.282,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1691440644096.0,
+  "total_flos": 3382881288192.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null