Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f4c806112e7eb02491deb7dfed1331cc26589a9dd2dab5305bfc1bed6b90055
+oid sha256:e31d059a58523abaae0ddeffb76c2da6a9df97bfffce2108437948f4878269ae
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3d98159bd7171abbd4fc422f92d655d5198f5fd56d2cb6eadafe3fb951f8dc9
+oid sha256:56cbbbe9a53e2a859952aefba5201bd5aefa0db1573234ec941bfa33b1c6661a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7739c28e2282b0be0ad3d8c5a3b0f7f9c2b0c36f696d58170b548e46acaedcc
+oid sha256:647617a5b8873881ec555b7bbc314145999492030dd45fc0b6e58c2f7c8f80a1
 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": 1.2411974668502808,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.020080321285140562,
+  "best_metric": 1.1164677143096924,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.040160642570281124,
   "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": 5.126,
       "eval_steps_per_second": 2.563,
       "step": 10
+    },
+    {
+      "epoch": 0.02208835341365462,
+      "grad_norm": 1.008229374885559,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.1722,
+      "step": 11
+    },
+    {
+      "epoch": 0.024096385542168676,
+      "grad_norm": 0.8678027987480164,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.1109,
+      "step": 12
+    },
+    {
+      "epoch": 0.02610441767068273,
+      "grad_norm": 0.9450435042381287,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.1563,
+      "step": 13
+    },
+    {
+      "epoch": 0.028112449799196786,
+      "grad_norm": 0.816157877445221,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.1604,
+      "step": 14
+    },
+    {
+      "epoch": 0.030120481927710843,
+      "grad_norm": 0.8615245223045349,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.3244,
+      "step": 15
+    },
+    {
+      "epoch": 0.030120481927710843,
+      "eval_loss": 1.1586683988571167,
+      "eval_runtime": 41.0322,
+      "eval_samples_per_second": 5.118,
+      "eval_steps_per_second": 2.559,
+      "step": 15
+    },
+    {
+      "epoch": 0.0321285140562249,
+      "grad_norm": 0.7571508884429932,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.1881,
+      "step": 16
+    },
+    {
+      "epoch": 0.03413654618473896,
+      "grad_norm": 0.8747928142547607,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.0047,
+      "step": 17
+    },
+    {
+      "epoch": 0.03614457831325301,
+      "grad_norm": 0.8475907444953918,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.0417,
+      "step": 18
+    },
+    {
+      "epoch": 0.03815261044176707,
+      "grad_norm": 1.19319486618042,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.4018,
+      "step": 19
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "grad_norm": 0.7098384499549866,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.1257,
+      "step": 20
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "eval_loss": 1.1164677143096924,
+      "eval_runtime": 41.0533,
+      "eval_samples_per_second": 5.115,
+      "eval_steps_per_second": 2.558,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2311955310182400.0,
+  "total_flos": 4346475983142912.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null