Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c4d1a7e51914404c5fdce18fd82d555be6eb9bc454e6e5d14454bcb39442805
+oid sha256:3bb8aa408391aaf66dc233779a24e2cc10c3d1b6b42c9c732aed82d867962a2f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a037de3dcdda7f13db8c28af8594871b57cc047aae63ebe6f7cdad72fdd4384
+oid sha256:b0896735137ddcab1158cf8713d502baaa1c7ac803c106117d8e474ef6cde51a
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daf392a5ca670ccaa5838c2483707bccfe82d8a68dd519c0d6d55618b02042e3
+oid sha256:147a294f9a33d16934a9eb60b9f9bedc7178384ab62a9efc5e72db5352813f0b
 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": 1.2900954484939575,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005930670462295762,
+  "best_metric": 1.0417572259902954,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0011861340924591525,
   "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": 4.979,
       "eval_steps_per_second": 2.49,
       "step": 10
+    },
+    {
+      "epoch": 0.0006523737508525338,
+      "grad_norm": 4.760507583618164,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 5.1135,
+      "step": 11
+    },
+    {
+      "epoch": 0.0007116804554754915,
+      "grad_norm": 4.733860492706299,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 5.0762,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007709871600984491,
+      "grad_norm": 3.5674550533294678,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.9928,
+      "step": 13
+    },
+    {
+      "epoch": 0.0008302938647214067,
+      "grad_norm": 4.406932353973389,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 4.2712,
+      "step": 14
+    },
+    {
+      "epoch": 0.0008896005693443643,
+      "grad_norm": 5.8381028175354,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 4.7663,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008896005693443643,
+      "eval_loss": 1.112551212310791,
+      "eval_runtime": 1425.1082,
+      "eval_samples_per_second": 4.982,
+      "eval_steps_per_second": 2.491,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009489072739673221,
+      "grad_norm": 4.847886085510254,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.4438,
+      "step": 16
+    },
+    {
+      "epoch": 0.0010082139785902795,
+      "grad_norm": 5.007083892822266,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 4.1874,
+      "step": 17
+    },
+    {
+      "epoch": 0.0010675206832132373,
+      "grad_norm": 4.6717753410339355,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 3.6129,
+      "step": 18
+    },
+    {
+      "epoch": 0.001126827387836195,
+      "grad_norm": 5.144303798675537,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.2386,
+      "step": 19
+    },
+    {
+      "epoch": 0.0011861340924591525,
+      "grad_norm": 5.231932163238525,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.0511,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011861340924591525,
+      "eval_loss": 1.0417572259902954,
+      "eval_runtime": 1434.6349,
+      "eval_samples_per_second": 4.949,
+      "eval_steps_per_second": 2.474,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2972437973041152.0,
+  "total_flos": 5782002632491008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null