Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6b1995fa9fcc63fb410c7db155c3278321d0bf026b6a7387d83ef5d6901f49
+oid sha256:acc957fa28c312944c57b944aca060253420a7a0f5733ccb42bb4c9142605d27
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21310aac2a846d72f85a9e08f197c6b16f65b5f75bfee37498340dbc4d4c60ca
+oid sha256:de1ced7cfab97a72640abe1758f0830edc796229af8961978a441fc804e32971
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27664fe9ad8ed8445e33c7255f967acf6b37dd9b2ca722042210d22bd07b0640
+oid sha256:9b92f2c4d40b75a1c427afcc3b9f446470aabb0e122237b7afe731531934f208
 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": 2.009469509124756,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0008520246235116195,
+  "best_metric": 0.45222973823547363,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.001704049247023239,
   "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": 10.215,
       "eval_steps_per_second": 5.108,
       "step": 10
+    },
+    {
+      "epoch": 0.0009372270858627814,
+      "grad_norm": 7.095274448394775,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.804,
+      "step": 11
+    },
+    {
+      "epoch": 0.0010224295482139435,
+      "grad_norm": 7.472821235656738,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.546,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011076320105651053,
+      "grad_norm": 8.946196556091309,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.6611,
+      "step": 13
+    },
+    {
+      "epoch": 0.0011928344729162674,
+      "grad_norm": 9.248509407043457,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.7886,
+      "step": 14
+    },
+    {
+      "epoch": 0.0012780369352674292,
+      "grad_norm": 5.092668533325195,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.9369,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012780369352674292,
+      "eval_loss": 0.9628341197967529,
+      "eval_runtime": 485.7206,
+      "eval_samples_per_second": 10.175,
+      "eval_steps_per_second": 5.087,
+      "step": 15
+    },
+    {
+      "epoch": 0.001363239397618591,
+      "grad_norm": 7.571272850036621,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.0683,
+      "step": 16
+    },
+    {
+      "epoch": 0.0014484418599697531,
+      "grad_norm": 6.461460590362549,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.929,
+      "step": 17
+    },
+    {
+      "epoch": 0.001533644322320915,
+      "grad_norm": 4.5205206871032715,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.6159,
+      "step": 18
+    },
+    {
+      "epoch": 0.001618846784672077,
+      "grad_norm": 3.7055180072784424,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.487,
+      "step": 19
+    },
+    {
+      "epoch": 0.001704049247023239,
+      "grad_norm": 3.816122055053711,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.5038,
+      "step": 20
+    },
+    {
+      "epoch": 0.001704049247023239,
+      "eval_loss": 0.45222973823547363,
+      "eval_runtime": 486.2889,
+      "eval_samples_per_second": 10.163,
+      "eval_steps_per_second": 5.081,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 76723802603520.0,
+  "total_flos": 153447605207040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null