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:c0d36da449ef3505e39362adeb278ccd34cc896f045e38e241f290a4ce582f73
+oid sha256:126a66d18f2f278dbd3cded4934a66581f83aaf7cf7a9ab2d6d79cb0d85f96b5
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df94c02421da95eeafe85461e0eea982e266895be465e6ea7e80d0055f5d193
+oid sha256:2a5c175559df9f9faf7cb805ee51a6b30c6664a101be487908b6bd4c6dbc8583
 size 250679090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec7dc567c089b9360385dc88ac6ed83e9342db25848fc49dd9956608ce39fa4a
+oid sha256:8be70d832a1bbff101f33c955af2006518b5495f9530a45087a280e66288a93d
 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": 2.4495997428894043,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.009992505620784412,
+  "best_metric": 2.0622997283935547,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.019985011241568824,
   "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": 4.916,
       "eval_steps_per_second": 2.458,
       "step": 10
+    },
+    {
+      "epoch": 0.010991756182862853,
+      "grad_norm": 4.003271579742432,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 10.2673,
+      "step": 11
+    },
+    {
+      "epoch": 0.011991006744941295,
+      "grad_norm": 4.2326555252075195,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 9.8006,
+      "step": 12
+    },
+    {
+      "epoch": 0.012990257307019736,
+      "grad_norm": 2.9779212474823,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 9.2463,
+      "step": 13
+    },
+    {
+      "epoch": 0.013989507869098177,
+      "grad_norm": 4.528616428375244,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 8.8378,
+      "step": 14
+    },
+    {
+      "epoch": 0.014988758431176618,
+      "grad_norm": 4.985352993011475,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 10.015,
+      "step": 15
+    },
+    {
+      "epoch": 0.014988758431176618,
+      "eval_loss": 2.1829171180725098,
+      "eval_runtime": 85.9558,
+      "eval_samples_per_second": 4.91,
+      "eval_steps_per_second": 2.455,
+      "step": 15
+    },
+    {
+      "epoch": 0.01598800899325506,
+      "grad_norm": 7.104391098022461,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 7.9238,
+      "step": 16
+    },
+    {
+      "epoch": 0.0169872595553335,
+      "grad_norm": 5.407159805297852,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 8.0276,
+      "step": 17
+    },
+    {
+      "epoch": 0.017986510117411942,
+      "grad_norm": 6.533193111419678,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 8.7472,
+      "step": 18
+    },
+    {
+      "epoch": 0.01898576067949038,
+      "grad_norm": 7.912476062774658,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 9.1709,
+      "step": 19
+    },
+    {
+      "epoch": 0.019985011241568824,
+      "grad_norm": 4.488398551940918,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.9152,
+      "step": 20
+    },
+    {
+      "epoch": 0.019985011241568824,
+      "eval_loss": 2.0622997283935547,
+      "eval_runtime": 85.8087,
+      "eval_samples_per_second": 4.918,
+      "eval_steps_per_second": 2.459,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3166224305356800.0,
+  "total_flos": 6332448610713600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null