Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:594ed2705466b742823f881749b129029b0ccbe7ab7f00f40351d2af513eaa41
+oid sha256:2e003598caa526fb5635c4952935f8fd70bf457219d4a16646bcb452f2219d1b
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20fa0182088b8625a48382482424a7f1285a8d2cf92bd968c9dbae8a92204a54
+oid sha256:f38db2c0cccaceb489e9e4407d62163d6c42990b1297f80e35a46a181e722f59
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45bd5b58e5e84ac4c2b56f9128f64021729566b6b5ae932fe03473b24f49f906
+oid sha256:88089b75d6b623f34c98becff8927336b43ddcda017bf8dd6cdbc2ddbbe5dcbc
 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": 1.330490231513977,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003608805485384338,
+  "best_metric": 0.9086689949035645,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.007217610970768676,
   "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": 4.183,
       "eval_steps_per_second": 2.093,
       "step": 10
+    },
+    {
+      "epoch": 0.003969686033922772,
+      "grad_norm": 4.434789180755615,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.8738,
+      "step": 11
+    },
+    {
+      "epoch": 0.004330566582461205,
+      "grad_norm": 8.491475105285645,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 5.4193,
+      "step": 12
+    },
+    {
+      "epoch": 0.004691447130999639,
+      "grad_norm": 4.193347930908203,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.4848,
+      "step": 13
+    },
+    {
+      "epoch": 0.005052327679538073,
+      "grad_norm": 4.052431583404541,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.5256,
+      "step": 14
+    },
+    {
+      "epoch": 0.0054132082280765065,
+      "grad_norm": 4.638420581817627,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.3011,
+      "step": 15
+    },
+    {
+      "epoch": 0.0054132082280765065,
+      "eval_loss": 1.0189849138259888,
+      "eval_runtime": 277.1724,
+      "eval_samples_per_second": 4.21,
+      "eval_steps_per_second": 2.107,
+      "step": 15
+    },
+    {
+      "epoch": 0.00577408877661494,
+      "grad_norm": 3.6194562911987305,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.9049,
+      "step": 16
+    },
+    {
+      "epoch": 0.006134969325153374,
+      "grad_norm": 4.051806449890137,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.0198,
+      "step": 17
+    },
+    {
+      "epoch": 0.006495849873691808,
+      "grad_norm": 4.909851551055908,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.7369,
+      "step": 18
+    },
+    {
+      "epoch": 0.006856730422230242,
+      "grad_norm": 4.357086181640625,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.7799,
+      "step": 19
+    },
+    {
+      "epoch": 0.007217610970768676,
+      "grad_norm": 4.044589042663574,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.7341,
+      "step": 20
+    },
+    {
+      "epoch": 0.007217610970768676,
+      "eval_loss": 0.9086689949035645,
+      "eval_runtime": 278.662,
+      "eval_samples_per_second": 4.188,
+      "eval_steps_per_second": 2.096,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5705610716774400.0,
+  "total_flos": 1.14112214335488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null