Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d1895baeb44755b4f0b92170dc49e5042860d5bb3dcbcf28db6af25f117af5
+oid sha256:85316f59b6316c507ed3d731f6adecc5a5764d348efeb342b48124c84e87d4f3
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32c2154fcb01e0a77cc7ff23b85f94b3d3abac6ff292a4466a974f4e8097a73c
+oid sha256:d4a2e3cdb8b9e96b18d71684801614af6627c827dca5f21a81451ce21dedbef3
 size 13665274

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4638f127a71af9377082619ddd0fe8d0c1878e74e764575919e763b32ff4c7b0
+oid sha256:4f23387d2ef34d1791447be278394c15128900e9096863778b0f682aeaf54bf9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4975101947784424,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016256197675363732,
+  "best_metric": 2.427879810333252,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0032512395350727465,
   "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": 28.96,
       "eval_steps_per_second": 14.486,
       "step": 10
+    },
+    {
+      "epoch": 0.0017881817442900105,
+      "grad_norm": 0.4097574055194855,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 2.3559,
+      "step": 11
+    },
+    {
+      "epoch": 0.001950743721043648,
+      "grad_norm": 1.6412928104400635,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 2.2916,
+      "step": 12
+    },
+    {
+      "epoch": 0.002113305697797285,
+      "grad_norm": 1.0803278684616089,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.6974,
+      "step": 13
+    },
+    {
+      "epoch": 0.0022758676745509225,
+      "grad_norm": 0.5715447664260864,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 2.2765,
+      "step": 14
+    },
+    {
+      "epoch": 0.00243842965130456,
+      "grad_norm": 0.769822895526886,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 2.4568,
+      "step": 15
+    },
+    {
+      "epoch": 0.00243842965130456,
+      "eval_loss": 2.4460976123809814,
+      "eval_runtime": 82.9489,
+      "eval_samples_per_second": 31.236,
+      "eval_steps_per_second": 15.624,
+      "step": 15
+    },
+    {
+      "epoch": 0.002600991628058197,
+      "grad_norm": 0.35771793127059937,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.2896,
+      "step": 16
+    },
+    {
+      "epoch": 0.0027635536048118345,
+      "grad_norm": 0.7394500970840454,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.4351,
+      "step": 17
+    },
+    {
+      "epoch": 0.002926115581565472,
+      "grad_norm": 0.6383208632469177,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.4734,
+      "step": 18
+    },
+    {
+      "epoch": 0.003088677558319109,
+      "grad_norm": 0.6234631538391113,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.4718,
+      "step": 19
+    },
+    {
+      "epoch": 0.0032512395350727465,
+      "grad_norm": 1.1141939163208008,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.4053,
+      "step": 20
+    },
+    {
+      "epoch": 0.0032512395350727465,
+      "eval_loss": 2.427879810333252,
+      "eval_runtime": 84.8025,
+      "eval_samples_per_second": 30.553,
+      "eval_steps_per_second": 15.283,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 56582873284608.0,
+  "total_flos": 116595011616768.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null