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:dbdc7a69349684bf08a3ff39ac59dbcb2fef3a70839f09e5b0e789bb0fe54ac4
+oid sha256:ef1e48c0a8c1b17de6362ec56784914c3ad7cc3dfc6cf6f4a65fdb64d08281e7
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f8cb71c7d6f8df54ef8061666af2e35e8e4d2fbfb60de6c5d8b56672af27c25
+oid sha256:a6eb7a6d9f4820f73c8b9d2613469b9bdc3ada75de1ee86607f04ed44e9f8d34
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744a236b7ff40b2da8f17533a805042c65dc262a61c46f05855a28eb600793b7
+oid sha256:845614e2f59fda4ead6c0973115f7f83016732685fe92124b66ae3eb92f9d67d
 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": 1.2919340133666992,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008592910848549946,
+  "best_metric": 1.2084153890609741,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.017185821697099892,
   "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": 5.488,
       "eval_steps_per_second": 2.744,
       "step": 10
+    },
+    {
+      "epoch": 0.00945220193340494,
+      "grad_norm": 0.34370872378349304,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.3213,
+      "step": 11
+    },
+    {
+      "epoch": 0.010311493018259935,
+      "grad_norm": 0.36485376954078674,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.2443,
+      "step": 12
+    },
+    {
+      "epoch": 0.01117078410311493,
+      "grad_norm": 0.3609774708747864,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.2118,
+      "step": 13
+    },
+    {
+      "epoch": 0.012030075187969926,
+      "grad_norm": 0.35284292697906494,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.2783,
+      "step": 14
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "grad_norm": 0.33930206298828125,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.1851,
+      "step": 15
+    },
+    {
+      "epoch": 0.01288936627282492,
+      "eval_loss": 1.2357568740844727,
+      "eval_runtime": 88.6348,
+      "eval_samples_per_second": 5.528,
+      "eval_steps_per_second": 2.764,
+      "step": 15
+    },
+    {
+      "epoch": 0.013748657357679914,
+      "grad_norm": 0.3349703252315521,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2026,
+      "step": 16
+    },
+    {
+      "epoch": 0.014607948442534909,
+      "grad_norm": 0.3912203311920166,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.2502,
+      "step": 17
+    },
+    {
+      "epoch": 0.015467239527389903,
+      "grad_norm": 0.29497820138931274,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.096,
+      "step": 18
+    },
+    {
+      "epoch": 0.0163265306122449,
+      "grad_norm": 0.37179771065711975,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.2139,
+      "step": 19
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "grad_norm": 0.34736475348472595,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.1715,
+      "step": 20
+    },
+    {
+      "epoch": 0.017185821697099892,
+      "eval_loss": 1.2084153890609741,
+      "eval_runtime": 84.5012,
+      "eval_samples_per_second": 5.799,
+      "eval_steps_per_second": 2.899,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3013156301438976.0,
+  "total_flos": 5944875946082304.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null