Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caf43d7ee38d32144d66b6374633818a3e562433296261cb919d7209c1f61309
+oid sha256:668051b510ddefbb3696970a71406e3f1cd0f21aae397aceac4d818705969ae1
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46be77b65053903f28108f3950dc55622ddee96cf5a8a2b26870546ae31b8e19
+oid sha256:b818adc8bea35b29c070d1fd7e3fd1263fc7320b88eb8b5602f750f2ae71091f
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3344af689521146e9ec080efa24caef17a8d8781a3937d8f1997beee63ec21f8
+oid sha256:ab720254f5557cc24c31943b94b9826898477a59ea138dfef59404325b0a558d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae20548bf37ed9ce24a89f932598e5e41d81b46882f80f29333348ce3845be91
+oid sha256:335c5ad5d49110db61ad1b0e85277ad0de8eaa71b71c181fa25e7d8bd8f3fc98
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1086701154708862,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.013036534889026497,
+  "best_metric": 1.0507456064224243,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.01629566861128312,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 14.47,
       "eval_steps_per_second": 3.618,
       "step": 200
+    },
+    {
+      "epoch": 0.013688361633477822,
+      "grad_norm": 1.3613508939743042,
+      "learning_rate": 0.00014959059926606403,
+      "loss": 0.838,
+      "step": 210
+    },
+    {
+      "epoch": 0.014340188377929147,
+      "grad_norm": 1.6068763732910156,
+      "learning_rate": 0.00014295908571525487,
+      "loss": 0.9718,
+      "step": 220
+    },
+    {
+      "epoch": 0.014992015122380471,
+      "grad_norm": 2.977311849594116,
+      "learning_rate": 0.00013613776741499452,
+      "loss": 1.0673,
+      "step": 230
+    },
+    {
+      "epoch": 0.015643841866831796,
+      "grad_norm": 2.3362767696380615,
+      "learning_rate": 0.00012915987714236542,
+      "loss": 1.1417,
+      "step": 240
+    },
+    {
+      "epoch": 0.01629566861128312,
+      "grad_norm": 5.354211807250977,
+      "learning_rate": 0.00012205941047736077,
+      "loss": 1.3597,
+      "step": 250
+    },
+    {
+      "epoch": 0.01629566861128312,
+      "eval_loss": 1.0507456064224243,
+      "eval_runtime": 446.5699,
+      "eval_samples_per_second": 14.466,
+      "eval_steps_per_second": 3.616,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.160326003693978e+16,
+  "total_flos": 5.217183012696883e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null