Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d392d771e4ee422adb87c223887cd36eba6effa2cea5b7f4030005d50e8124
+oid sha256:c8b49ab7badb4d081fbe8ae053f58e65420fb9cd80c377d2388b25c4bee9955f
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91c537ffd57e6ca529634cce7ed120e8de0da66450d253ab506eaef1a0e16c2b
+oid sha256:1b30bebb06bb2ad64fe98609d96c0a464b4b3f0c653afad17b58860640b4e81c
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e0fe826f98369530d76c56e931e0463848c81119fbcf242bfa2459e400cde0b
+oid sha256:bd4c8df25e7b7f0e406180a0dd8083cd2543adfa12a68517c9fc33e635bf513e
 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": 2.8525774478912354,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.023391812865497075,
+  "best_metric": 1.9674196243286133,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.04678362573099415,
   "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": 3.424,
       "eval_steps_per_second": 1.712,
       "step": 10
+    },
+    {
+      "epoch": 0.025730994152046785,
+      "grad_norm": 4.353909015655518,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 10.8984,
+      "step": 11
+    },
+    {
+      "epoch": 0.028070175438596492,
+      "grad_norm": 3.5024590492248535,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 11.0107,
+      "step": 12
+    },
+    {
+      "epoch": 0.0304093567251462,
+      "grad_norm": 7.128164768218994,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 11.8648,
+      "step": 13
+    },
+    {
+      "epoch": 0.03274853801169591,
+      "grad_norm": 7.6712141036987305,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 8.9836,
+      "step": 14
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 12.34415340423584,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 14.5467,
+      "step": 15
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "eval_loss": 2.3073062896728516,
+      "eval_runtime": 52.5708,
+      "eval_samples_per_second": 3.424,
+      "eval_steps_per_second": 1.712,
+      "step": 15
+    },
+    {
+      "epoch": 0.03742690058479532,
+      "grad_norm": 8.823278427124023,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.7913,
+      "step": 16
+    },
+    {
+      "epoch": 0.03976608187134503,
+      "grad_norm": 9.27376937866211,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 10.8245,
+      "step": 17
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": 9.13545036315918,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 8.807,
+      "step": 18
+    },
+    {
+      "epoch": 0.044444444444444446,
+      "grad_norm": 6.375463962554932,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 7.6188,
+      "step": 19
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "grad_norm": 7.590856075286865,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 7.2438,
+      "step": 20
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "eval_loss": 1.9674196243286133,
+      "eval_runtime": 52.4841,
+      "eval_samples_per_second": 3.43,
+      "eval_steps_per_second": 1.715,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6253293003079680.0,
+  "total_flos": 1.22691191832576e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null