Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae7a3d64ccfb01accf06d61539435ad160e396cf1768124690cb993f258a3af
+oid sha256:7a2e7ae795b48079654062b03185343cc73d85495dc328fc3db72a78c1e5c19a
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c268f498d1a31f0cdd7f8c7808e96d2cedf5ee5488398665521abeca75ce54a
+oid sha256:ca7f9f78b6b9890f06599e9567e27447734a5dd7b4261958ab14ab066969252a
 size 445914554

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31d895de8d7a620050df3329558df9b74f6c829b1ec0274d3abc7ae4b6beafd5
+oid sha256:9b2afbdc2003c7a988105c1c7bed9fe94f498880cef8384cbeca36532f532b80
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 5.987125873565674,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.02557544757033248,
+  "best_metric": 5.251645565032959,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.05115089514066496,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 4.411,
       "eval_steps_per_second": 1.109,
       "step": 10
+    },
+    {
+      "epoch": 0.030690537084398978,
+      "grad_norm": 7.037360191345215,
+      "learning_rate": 0.000163742398974869,
+      "loss": 17.4451,
+      "step": 12
+    },
+    {
+      "epoch": 0.03836317135549872,
+      "grad_norm": 8.117260932922363,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 16.0837,
+      "step": 15
+    },
+    {
+      "epoch": 0.03836317135549872,
+      "eval_loss": 5.5802226066589355,
+      "eval_runtime": 75.7254,
+      "eval_samples_per_second": 4.358,
+      "eval_steps_per_second": 1.096,
+      "step": 15
+    },
+    {
+      "epoch": 0.04603580562659847,
+      "grad_norm": 7.076067924499512,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 16.2765,
+      "step": 18
+    },
+    {
+      "epoch": 0.05115089514066496,
+      "eval_loss": 5.251645565032959,
+      "eval_runtime": 75.0851,
+      "eval_samples_per_second": 4.395,
+      "eval_steps_per_second": 1.105,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.361684987904e+16,
+  "total_flos": 2.723369975808e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null