Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b41978e35ad48987b406a343a55a14e6a554b1b7f2a1d6ea54cf7a12e65c53d
+oid sha256:6b0fe35e02dbadb8de42027ba07ea418e0ffa3420ebce31759c286fa4ea9874d
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4efd559db0e5347b94e3d89ebe953c6456fff8d82d3d4a18cca567d059831d63
+oid sha256:5f6c486737d8cad5b774ee54c889a55abe2b72aa44c3cbbb4abb5534e6660cc7
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e068d075621359f9b11121ec8234fcdab4fd7ab5c2c54d370657a4569cd9f5e
+oid sha256:ab8caf8fe21de20081071c159f729edd33aed262ad01c0aed650dc7791934001
 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": 1.5030826330184937,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0005232725465058476,
+  "best_metric": 1.3482195138931274,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0010465450930116952,
   "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": 5.203,
       "eval_steps_per_second": 1.301,
       "step": 10
+    },
+    {
+      "epoch": 0.0006279270558070171,
+      "grad_norm": 0.3684312105178833,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.044,
+      "step": 12
+    },
+    {
+      "epoch": 0.0007849088197587713,
+      "grad_norm": 0.3923090994358063,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.997,
+      "step": 15
+    },
+    {
+      "epoch": 0.0007849088197587713,
+      "eval_loss": 1.3932478427886963,
+      "eval_runtime": 3094.3973,
+      "eval_samples_per_second": 5.201,
+      "eval_steps_per_second": 1.3,
+      "step": 15
+    },
+    {
+      "epoch": 0.0009418905837105256,
+      "grad_norm": 0.34257999062538147,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.0033,
+      "step": 18
+    },
+    {
+      "epoch": 0.0010465450930116952,
+      "eval_loss": 1.3482195138931274,
+      "eval_runtime": 3086.4995,
+      "eval_samples_per_second": 5.214,
+      "eval_steps_per_second": 1.304,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.30129688788992e+16,
+  "total_flos": 2.57085482729472e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null