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:aa30d38a1776c6a65d6f940ee6538d1848071053f63da14a46a693a8a9ff6ea0
+oid sha256:43ab0107df543e535c4293e0be8a9acf7f28451b2be4fd430922587acd84a2a7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cccea2c3278b619f4baee8e5c63fa17d5093d81eb671691c28a8873ebdfe7205
+oid sha256:9770be047cb804cb2bf5436de8c99a17024ddd77f060bf17b0e85793c09efaaa
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c79ce16733b6db80aea90add053d7250afe407dd6159d54ee4a13e9dc59595aa
+oid sha256:eff7fd73f973e46014ca0cba260ef1bf771431578dfc80d8fcdb5d9fe1ecc859
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b8bc8abd4c9f82dfc46828b9bd127304694d7b33110834b4b23e29a7f6b47fd
+oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.556506872177124,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.002201067517746107,
+  "best_metric": 1.4073567390441895,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.004402135035492214,
   "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": 8.02,
       "eval_steps_per_second": 4.012,
       "step": 10
+    },
+    {
+      "epoch": 0.0024211742695207177,
+      "grad_norm": 2.3803887367248535,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 1.5437,
+      "step": 11
+    },
+    {
+      "epoch": 0.0026412810212953284,
+      "grad_norm": 1.5120227336883545,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 1.5937,
+      "step": 12
+    },
+    {
+      "epoch": 0.0028613877730699388,
+      "grad_norm": 1.4125422239303589,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 1.4758,
+      "step": 13
+    },
+    {
+      "epoch": 0.0030814945248445495,
+      "grad_norm": 1.1811188459396362,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 1.404,
+      "step": 14
+    },
+    {
+      "epoch": 0.0033016012766191602,
+      "grad_norm": 1.0221134424209595,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.2909,
+      "step": 15
+    },
+    {
+      "epoch": 0.0033016012766191602,
+      "eval_loss": 1.476494550704956,
+      "eval_runtime": 238.2339,
+      "eval_samples_per_second": 8.03,
+      "eval_steps_per_second": 4.017,
+      "step": 15
+    },
+    {
+      "epoch": 0.003521708028393771,
+      "grad_norm": 1.1143208742141724,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 1.187,
+      "step": 16
+    },
+    {
+      "epoch": 0.0037418147801683817,
+      "grad_norm": 1.5501571893692017,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 1.6458,
+      "step": 17
+    },
+    {
+      "epoch": 0.0039619215319429925,
+      "grad_norm": 4.555670261383057,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 1.2275,
+      "step": 18
+    },
+    {
+      "epoch": 0.004182028283717603,
+      "grad_norm": 1.250296711921692,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 1.2713,
+      "step": 19
+    },
+    {
+      "epoch": 0.004402135035492214,
+      "grad_norm": 1.27157723903656,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 1.2806,
+      "step": 20
+    },
+    {
+      "epoch": 0.004402135035492214,
+      "eval_loss": 1.4073567390441895,
+      "eval_runtime": 238.2087,
+      "eval_samples_per_second": 8.031,
+      "eval_steps_per_second": 4.017,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null