Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54b57e4fe89a3d5378ee8715e73058598aef4437449b82e99c3dcf9d2aca01ae
+oid sha256:442d93d2333ab157ee4274edf11c139fefa2ce03e0249ebcdc63095b925a0837
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42a1fb195f980e39c570b63a5dcc7c6296aa4afc00ea1f521ea92faf2bdeda0e
+oid sha256:1cbde6f9653579255389820e1bc28a646f2d08ec0dd5e0f6f9895f3ff39c633f
 size 147359892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c327bd14cb201dc0686330c2646c83522ce3819fb7b3e037a738237b8a353a4
+oid sha256:d6ba4692d23fd3ff05a4aae932e0a21bdcaf5ec9be653a055dbc905a9c0b8c16
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:317ba05605195c1d4e2040522f74e7ab98f17d7a309d9ff3aaeabe58a301e214
+oid sha256:c9abf3b00130ebbc35657fb7788755e92886d9a53e2a5677dea2a31074b05473
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2519747018814087,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.08525149190110827,
+  "best_metric": 1.2275176048278809,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.11366865586814436,
   "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": 35.89,
       "eval_steps_per_second": 9.009,
       "step": 150
+    },
+    {
+      "epoch": 0.09093492469451549,
+      "grad_norm": 0.20803095400333405,
+      "learning_rate": 0.00018053067903555837,
+      "loss": 1.215,
+      "step": 160
+    },
+    {
+      "epoch": 0.0966183574879227,
+      "grad_norm": 0.2767871022224426,
+      "learning_rate": 0.00017525871366768012,
+      "loss": 1.1321,
+      "step": 170
+    },
+    {
+      "epoch": 0.10230179028132992,
+      "grad_norm": 0.3595309257507324,
+      "learning_rate": 0.00016964445490919413,
+      "loss": 1.0872,
+      "step": 180
+    },
+    {
+      "epoch": 0.10798522307473714,
+      "grad_norm": 0.4991762638092041,
+      "learning_rate": 0.00016371525486442843,
+      "loss": 1.1756,
+      "step": 190
+    },
+    {
+      "epoch": 0.11366865586814436,
+      "grad_norm": 1.7282116413116455,
+      "learning_rate": 0.0001575,
+      "loss": 1.286,
+      "step": 200
+    },
+    {
+      "epoch": 0.11366865586814436,
+      "eval_loss": 1.2275176048278809,
+      "eval_runtime": 20.815,
+      "eval_samples_per_second": 35.599,
+      "eval_steps_per_second": 8.936,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7217843728809984.0,
+  "total_flos": 9678942306828288.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null