Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96b0f673d934bce426e5518cba6336dfa721175d6061da6b1d10238d976944cc
+oid sha256:f3fc86f2c61c685d86292237dbde5254df1b82d6856775897d7c7269a5eb51a3
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af6b529d72f1efa88c07f35348154e953ccc72a49b0850bbb5eab6b4d8e3d6f
+oid sha256:10d423327a6a441a655092b6c53bcefcd888bffa8880b1ca354f6cc783b1c8ee
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2f8d836fc74ab1dcd19c00e141e586a98256bb27f2b43f2fea9ac75779943de
+oid sha256:542da8d551e0c417e013011b8706e763ab5b1bc78b1362718ff9c733b64229b8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80e3c543dd881d7b92b58f753c91bcd488f8269b3e4ffd67623431c55e782209
+oid sha256:8e4a64d71eed58bad723d1496b310be4dbd45cd96d8ef2f7cd1e195fe59bff7c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.181504249572754,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.21770682148040638,
+  "best_metric": 2.118581533432007,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.29027576197387517,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 11.785,
       "eval_steps_per_second": 2.967,
       "step": 150
+    },
+    {
+      "epoch": 0.23222060957910015,
+      "grad_norm": 1.0636928081512451,
+      "learning_rate": 0.0001779516693350504,
+      "loss": 2.1444,
+      "step": 160
+    },
+    {
+      "epoch": 0.2467343976777939,
+      "grad_norm": 1.1345711946487427,
+      "learning_rate": 0.00017275501775814182,
+      "loss": 2.0798,
+      "step": 170
+    },
+    {
+      "epoch": 0.2612481857764877,
+      "grad_norm": 1.450459361076355,
+      "learning_rate": 0.00016722096269620562,
+      "loss": 2.1037,
+      "step": 180
+    },
+    {
+      "epoch": 0.2757619738751814,
+      "grad_norm": 1.63530695438385,
+      "learning_rate": 0.00016137646550922228,
+      "loss": 2.1009,
+      "step": 190
+    },
+    {
+      "epoch": 0.29027576197387517,
+      "grad_norm": 4.483078479766846,
+      "learning_rate": 0.00015525,
+      "loss": 2.0577,
+      "step": 200
+    },
+    {
+      "epoch": 0.29027576197387517,
+      "eval_loss": 2.118581533432007,
+      "eval_runtime": 24.8624,
+      "eval_samples_per_second": 11.664,
+      "eval_steps_per_second": 2.936,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.874994255403418e+16,
+  "total_flos": 5.157230797337395e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null