Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc0fe4a40e69729f04b16e2dd526c10979dae3dcfde9b901827455608352be0
+oid sha256:6a2c534f2f9333b0ed53f9ceedaa3005e9aec316289b0bb8c685dd50de111248
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b6ab2dac733edf7c90cea313031e5cb517de401ee83b0b6c27a1716aec5d221
+oid sha256:3df993674050f894dab63dfb4a8acc4717450d6ae8ed8313687960a3b49af659
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0de55acbad9edf28315a05b92b99a77b13cbfd3408899ffeede081c856f10011
+oid sha256:22adc71b0291bf50d9a06af81163a3147a99a13484e21e37d4824565b981ee99
 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": 1.6063923835754395,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016256197675363732,
+  "best_metric": 1.4639239311218262,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0032512395350727465,
   "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": 4.787,
       "eval_steps_per_second": 2.394,
       "step": 10
+    },
+    {
+      "epoch": 0.0017881817442900105,
+      "grad_norm": 1.4203264713287354,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 6.0159,
+      "step": 11
+    },
+    {
+      "epoch": 0.001950743721043648,
+      "grad_norm": 1.2493367195129395,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 7.1809,
+      "step": 12
+    },
+    {
+      "epoch": 0.002113305697797285,
+      "grad_norm": 2.142144203186035,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 5.2994,
+      "step": 13
+    },
+    {
+      "epoch": 0.0022758676745509225,
+      "grad_norm": 2.612400770187378,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 5.3049,
+      "step": 14
+    },
+    {
+      "epoch": 0.00243842965130456,
+      "grad_norm": 2.3758747577667236,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 5.4849,
+      "step": 15
+    },
+    {
+      "epoch": 0.00243842965130456,
+      "eval_loss": 1.531221866607666,
+      "eval_runtime": 540.1619,
+      "eval_samples_per_second": 4.797,
+      "eval_steps_per_second": 2.399,
+      "step": 15
+    },
+    {
+      "epoch": 0.002600991628058197,
+      "grad_norm": 2.8996591567993164,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.7643,
+      "step": 16
+    },
+    {
+      "epoch": 0.0027635536048118345,
+      "grad_norm": 3.941735029220581,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 6.3934,
+      "step": 17
+    },
+    {
+      "epoch": 0.002926115581565472,
+      "grad_norm": 2.863781690597534,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 6.2186,
+      "step": 18
+    },
+    {
+      "epoch": 0.003088677558319109,
+      "grad_norm": 3.3763999938964844,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 5.9787,
+      "step": 19
+    },
+    {
+      "epoch": 0.0032512395350727465,
+      "grad_norm": 2.3317129611968994,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 5.9861,
+      "step": 20
+    },
+    {
+      "epoch": 0.0032512395350727465,
+      "eval_loss": 1.4639239311218262,
+      "eval_runtime": 543.415,
+      "eval_samples_per_second": 4.768,
+      "eval_steps_per_second": 2.385,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4862853953617920.0,
+  "total_flos": 9961007292088320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null