Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46801154b2614f4323cc077e0bb25096e18951199a5aabb8af61fa4941ffb41d
+oid sha256:4c48040d5f4dcdfb0212cdd9847d4104bc15bb453b626c43fd198d81ee08fca2
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7a8d482daa1a7fca137255b8fa097ffceddacefbf213e07077e153e67b27001
+oid sha256:8fe89604d961d4a51883d86fdae4d4686eafa9a8c2e6271cdd5c860d86a4ca86
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719b40faf8a2961c800aa5d39302a83f9fd7fbec2a7f89c83f8b3e6499806c63
+oid sha256:65072b1b6c28a74f8da9eb58e2888536595e89ac6c79dde321f112aa66624e44
 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": 1.837178349494934,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0032144005143040825,
+  "best_metric": 1.7709662914276123,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.006428801028608165,
   "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": 5.336,
       "eval_steps_per_second": 2.668,
       "step": 10
+    },
+    {
+      "epoch": 0.0035358405657344907,
+      "grad_norm": 3.1442389488220215,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 7.5973,
+      "step": 11
+    },
+    {
+      "epoch": 0.003857280617164899,
+      "grad_norm": 2.9277398586273193,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 6.729,
+      "step": 12
+    },
+    {
+      "epoch": 0.004178720668595307,
+      "grad_norm": 2.930840492248535,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 7.53,
+      "step": 13
+    },
+    {
+      "epoch": 0.004500160720025715,
+      "grad_norm": 3.4834635257720947,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 7.2058,
+      "step": 14
+    },
+    {
+      "epoch": 0.0048216007714561235,
+      "grad_norm": 4.19149112701416,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 7.0573,
+      "step": 15
+    },
+    {
+      "epoch": 0.0048216007714561235,
+      "eval_loss": 1.829241156578064,
+      "eval_runtime": 244.9163,
+      "eval_samples_per_second": 5.349,
+      "eval_steps_per_second": 2.674,
+      "step": 15
+    },
+    {
+      "epoch": 0.005143040822886531,
+      "grad_norm": 3.4479832649230957,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.0653,
+      "step": 16
+    },
+    {
+      "epoch": 0.00546448087431694,
+      "grad_norm": 4.002652645111084,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 6.5003,
+      "step": 17
+    },
+    {
+      "epoch": 0.0057859209257473485,
+      "grad_norm": 3.030047655105591,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 7.5556,
+      "step": 18
+    },
+    {
+      "epoch": 0.006107360977177756,
+      "grad_norm": 3.8863916397094727,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 5.7633,
+      "step": 19
+    },
+    {
+      "epoch": 0.006428801028608165,
+      "grad_norm": 3.2730555534362793,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 7.2346,
+      "step": 20
+    },
+    {
+      "epoch": 0.006428801028608165,
+      "eval_loss": 1.7709662914276123,
+      "eval_runtime": 244.8426,
+      "eval_samples_per_second": 5.35,
+      "eval_steps_per_second": 2.675,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4065247635701760.0,
+  "total_flos": 7916534869524480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null