Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3384d1fedbc8ffe4f853e47103ce5f7c461320d2598887a41cc2ef9c093599f2
+oid sha256:2114d11a3a42e9f9badca32b1b8e285f99e206308af024496580c589749c23db
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d529a01c5813134daaa5512c90743f262b1951083cd134fad105930dc388316e
+oid sha256:59f30ff423e9d220d5c3bf536579634e493b692c5eb3c4f9e4ae770cc5b7e683
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9daf21c811dedc7f2e5feac581240b0717b44a01125c3a6fbb456b6bc7876f83
+oid sha256:48b5f447fdf5275d96a8aa3fd1a386234c8c0b0a0ddf0d4ee97f8353919167c5
 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": 2.348543882369995,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0098015192354815,
+  "best_metric": 2.1507134437561035,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.019603038470963,
   "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": 14.243,
       "eval_steps_per_second": 7.122,
       "step": 10
+    },
+    {
+      "epoch": 0.01078167115902965,
+      "grad_norm": 0.7577857971191406,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.277,
+      "step": 11
+    },
+    {
+      "epoch": 0.0117618230825778,
+      "grad_norm": 0.5409818291664124,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.1708,
+      "step": 12
+    },
+    {
+      "epoch": 0.01274197500612595,
+      "grad_norm": 0.4970989227294922,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.0626,
+      "step": 13
+    },
+    {
+      "epoch": 0.0137221269296741,
+      "grad_norm": 0.7126469612121582,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.5659,
+      "step": 14
+    },
+    {
+      "epoch": 0.014702278853222249,
+      "grad_norm": 0.5474905371665955,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.0383,
+      "step": 15
+    },
+    {
+      "epoch": 0.014702278853222249,
+      "eval_loss": 2.2148451805114746,
+      "eval_runtime": 30.227,
+      "eval_samples_per_second": 14.226,
+      "eval_steps_per_second": 7.113,
+      "step": 15
+    },
+    {
+      "epoch": 0.0156824307767704,
+      "grad_norm": 0.6352144479751587,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.2655,
+      "step": 16
+    },
+    {
+      "epoch": 0.01666258270031855,
+      "grad_norm": 0.6581323742866516,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 2.1256,
+      "step": 17
+    },
+    {
+      "epoch": 0.017642734623866698,
+      "grad_norm": 0.705475389957428,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.0248,
+      "step": 18
+    },
+    {
+      "epoch": 0.018622886547414848,
+      "grad_norm": 0.8269036412239075,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.3213,
+      "step": 19
+    },
+    {
+      "epoch": 0.019603038470963,
+      "grad_norm": 0.6235066056251526,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.038,
+      "step": 20
+    },
+    {
+      "epoch": 0.019603038470963,
+      "eval_loss": 2.1507134437561035,
+      "eval_runtime": 30.2493,
+      "eval_samples_per_second": 14.215,
+      "eval_steps_per_second": 7.108,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 34292650475520.0,
+  "total_flos": 68585300951040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null