Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b51b5e00add63599e762dd74bd4623b7e230745655317f198e5f3b52eda7e61
+oid sha256:89dd190ebe12be529c692ae908e00ab206bdabd09c3a7c852a414932240ab783
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc36d5994b90745c816d9f7f06d713ec8f12e1beb8681301978b983e5e47657
+oid sha256:1d85975270cb6c5f10b8e8cf74b36108e60b50b8bc24d9f8fc480457caf8cdd6
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8333bd3c0159ba2bf4812ccdfd29fc6020f725b2f642a5c9c9263a63f5186f04
+oid sha256:28bdadb0b9893998ce75768a67161bca90352a16316c1a13048c8cefc5498aa1
 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": 1.182800531387329,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0008498523381562453,
+  "best_metric": 1.0485574007034302,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0016997046763124906,
   "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": 3.726,
       "eval_steps_per_second": 1.864,
       "step": 10
+    },
+    {
+      "epoch": 0.0009348375719718699,
+      "grad_norm": 0.5133495330810547,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 1.4981,
+      "step": 11
+    },
+    {
+      "epoch": 0.0010198228057874943,
+      "grad_norm": 0.4741702377796173,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 1.0614,
+      "step": 12
+    },
+    {
+      "epoch": 0.001104808039603119,
+      "grad_norm": 0.48592695593833923,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.3289,
+      "step": 13
+    },
+    {
+      "epoch": 0.0011897932734187436,
+      "grad_norm": 0.5056785941123962,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.0073,
+      "step": 14
+    },
+    {
+      "epoch": 0.001274778507234368,
+      "grad_norm": 0.3255745768547058,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.3241,
+      "step": 15
+    },
+    {
+      "epoch": 0.001274778507234368,
+      "eval_loss": 1.0932385921478271,
+      "eval_runtime": 1319.1764,
+      "eval_samples_per_second": 3.756,
+      "eval_steps_per_second": 1.878,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013597637410499926,
+      "grad_norm": 0.3560282289981842,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.8673,
+      "step": 16
+    },
+    {
+      "epoch": 0.001444748974865617,
+      "grad_norm": 0.3492855131626129,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.9656,
+      "step": 17
+    },
+    {
+      "epoch": 0.0015297342086812416,
+      "grad_norm": 0.33957651257514954,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.0601,
+      "step": 18
+    },
+    {
+      "epoch": 0.0016147194424968661,
+      "grad_norm": 0.3338528871536255,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.025,
+      "step": 19
+    },
+    {
+      "epoch": 0.0016997046763124906,
+      "grad_norm": 0.3303922116756439,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.2887,
+      "step": 20
+    },
+    {
+      "epoch": 0.0016997046763124906,
+      "eval_loss": 1.0485574007034302,
+      "eval_runtime": 2250.8,
+      "eval_samples_per_second": 2.201,
+      "eval_steps_per_second": 1.101,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6094945454653440.0,
+  "total_flos": 1.203158063775744e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null