Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f8d8fbce93e0b415bc83caf2691f42996f44c36ece6cd759674fe942ec20f26
+oid sha256:3e1028187463b5568696dabeea87c96c6b4e0aaf9308d5b5b8aa0057a43a1901
 size 1342238560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1819ad50c17544d550e0509aa73fb55d46df12e6d3972f02cdc75af6d3682b85
+oid sha256:29084e3d9c53238d230c5079afe4b83459715d7997473b54cbb09ede61969611
 size 682101396

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d6be1ee61e986469888561dce8de3f492add76f3bf5cc94c3bd31234e25cafc
+oid sha256:161a33e84b4c64fa9febe6f657339b8da5f141eb4edce251ae9e5a98bceac60f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691263e55c7bb34b6e090bd89cf079f362100d7bd758be475bd3e7091c1a4ed6
+oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.037921667098999,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.00905961224859576,
+  "best_metric": 2.953709840774536,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.01811922449719152,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -93,6 +93,84 @@
       "eval_samples_per_second": 5.92,
       "eval_steps_per_second": 2.96,
       "step": 100
+    },
+    {
+      "epoch": 0.009965573473455336,
+      "grad_norm": 4.184726238250732,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.1687,
+      "step": 110
+    },
+    {
+      "epoch": 0.010871534698314912,
+      "grad_norm": 5.467559814453125,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.0523,
+      "step": 120
+    },
+    {
+      "epoch": 0.011777495923174489,
+      "grad_norm": 4.539832592010498,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.9123,
+      "step": 130
+    },
+    {
+      "epoch": 0.012683457148034065,
+      "grad_norm": 6.541698932647705,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.0405,
+      "step": 140
+    },
+    {
+      "epoch": 0.01358941837289364,
+      "grad_norm": 4.431535243988037,
+      "learning_rate": 5e-05,
+      "loss": 3.1148,
+      "step": 150
+    },
+    {
+      "epoch": 0.014495379597753216,
+      "grad_norm": 4.524734020233154,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.0427,
+      "step": 160
+    },
+    {
+      "epoch": 0.015401340822612792,
+      "grad_norm": 4.3518385887146,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.9297,
+      "step": 170
+    },
+    {
+      "epoch": 0.01630730204747237,
+      "grad_norm": 3.8135385513305664,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.9592,
+      "step": 180
+    },
+    {
+      "epoch": 0.017213263272331945,
+      "grad_norm": 3.840271472930908,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.7632,
+      "step": 190
+    },
+    {
+      "epoch": 0.01811922449719152,
+      "grad_norm": 4.834849834442139,
+      "learning_rate": 0.0,
+      "loss": 2.9525,
+      "step": 200
+    },
+    {
+      "epoch": 0.01811922449719152,
+      "eval_loss": 2.953709840774536,
+      "eval_runtime": 784.593,
+      "eval_samples_per_second": 5.924,
+      "eval_steps_per_second": 2.962,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -116,12 +194,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.70749463789568e+16,
+  "total_flos": 1.541498927579136e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null