Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40145ecff317bd1f6c69b62983e0711046541ab7d790bdb86d528639e5541f1d
+oid sha256:c33d14a1446a853ffae6472e0d722e77d45aa291020d64234d30aeaf8f230620
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dff68b2babb14bc5310faa75da1034e23265149a2d6fef15dd9f08200d0a42b7
+oid sha256:4a5fb8dc5333e29e18f407ddccab9f2284913fb4dd7971c4bc59cd5bcc8f264e
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa0de0c32bf94efe74fce56eafc87e41e69cc5016d5c33867cf1c8934b8875ce
+oid sha256:02ae481c8002fa1263f712f930a5df4f2c49037e33af7892692f742d795e7bee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9abf3b00130ebbc35657fb7788755e92886d9a53e2a5677dea2a31074b05473
+oid sha256:c025e03e0d8ded968e4f23b186aaafce8f23c2a50b134c4f77cea95627049ac8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1949564218521118,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.13966480446927373,
+  "best_metric": 1.148054599761963,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.17458100558659218,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 11.608,
       "eval_steps_per_second": 2.907,
       "step": 200
+    },
+    {
+      "epoch": 0.14664804469273743,
+      "grad_norm": 0.4466894268989563,
+      "learning_rate": 0.00015102897041285315,
+      "loss": 0.9098,
+      "step": 210
+    },
+    {
+      "epoch": 0.15363128491620112,
+      "grad_norm": 0.4285886287689209,
+      "learning_rate": 0.00014433369230867077,
+      "loss": 0.9563,
+      "step": 220
+    },
+    {
+      "epoch": 0.16061452513966482,
+      "grad_norm": 0.4518221616744995,
+      "learning_rate": 0.0001374467844093695,
+      "loss": 0.748,
+      "step": 230
+    },
+    {
+      "epoch": 0.16759776536312848,
+      "grad_norm": 0.6178202033042908,
+      "learning_rate": 0.0001304017990379651,
+      "loss": 0.9594,
+      "step": 240
+    },
+    {
+      "epoch": 0.17458100558659218,
+      "grad_norm": 1.0840479135513306,
+      "learning_rate": 0.0001232330586550277,
+      "loss": 2.2842,
+      "step": 250
+    },
+    {
+      "epoch": 0.17458100558659218,
+      "eval_loss": 1.148054599761963,
+      "eval_runtime": 52.0966,
+      "eval_samples_per_second": 11.575,
+      "eval_steps_per_second": 2.898,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.652007524237312e+16,
+  "total_flos": 7.06500940529664e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null