Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84c54a9afbc4eb7c75bfb55a139724528a733d50ecc9d9480c15b439b13db8e5
+oid sha256:8c67cb69054ec58aa440717cdfb6bb73eed282ad38d6f1d8876b92f689dce4a3
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a80b398665c89896098c06ce44d0aab9ee6573cafe59740768c374973eee82c0
-size 341314196
+oid sha256:a3277342f65874d847ea16268cf966c19181a740039e3a76dc9dfa826e4bb748
+size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07f82241b9e643be3241205d5eb1a2f2a9fc078760341a2caefd27106208888a
+oid sha256:835154b511893bb89c75363ca2b5e39fbfa155a8e7afb051eb41d91d2f9e28a0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eaa4c8e8f9133451ddb25d9cc07f61c13ab6775afadbfb025eb8a3e054e859c
+oid sha256:61b5a82b906ef255ed934ff84d648a93ce52daed15c002b1d3821ff35829eb10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 3.1905009746551514,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.08915304606240713,
+  "epoch": 0.17830609212481427,
   "eval_steps": 150,
-  "global_step": 150,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -128,6 +128,119 @@
       "eval_samples_per_second": 13.326,
       "eval_steps_per_second": 3.334,
       "step": 150
+    },
+    {
+      "epoch": 0.0950965824665676,
+      "grad_norm": 1.8121700286865234,
+      "learning_rate": 9.888459804735679e-05,
+      "loss": 3.1284,
+      "step": 160
+    },
+    {
+      "epoch": 0.10104011887072809,
+      "grad_norm": 2.5314412117004395,
+      "learning_rate": 9.867352156521488e-05,
+      "loss": 3.1552,
+      "step": 170
+    },
+    {
+      "epoch": 0.10698365527488855,
+      "grad_norm": 2.6681604385375977,
+      "learning_rate": 9.844443122444238e-05,
+      "loss": 2.9376,
+      "step": 180
+    },
+    {
+      "epoch": 0.11292719167904904,
+      "grad_norm": 2.87355375289917,
+      "learning_rate": 9.819741181037799e-05,
+      "loss": 2.8799,
+      "step": 190
+    },
+    {
+      "epoch": 0.1188707280832095,
+      "grad_norm": 4.919130325317383,
+      "learning_rate": 9.793255474383249e-05,
+      "loss": 2.8424,
+      "step": 200
+    },
+    {
+      "epoch": 0.12481426448736999,
+      "grad_norm": 2.0036211013793945,
+      "learning_rate": 9.764995804725424e-05,
+      "loss": 3.2481,
+      "step": 210
+    },
+    {
+      "epoch": 0.13075780089153047,
+      "grad_norm": 2.4777944087982178,
+      "learning_rate": 9.734972630845151e-05,
+      "loss": 3.0006,
+      "step": 220
+    },
+    {
+      "epoch": 0.13670133729569092,
+      "grad_norm": 2.4493539333343506,
+      "learning_rate": 9.703197064188498e-05,
+      "loss": 2.9379,
+      "step": 230
+    },
+    {
+      "epoch": 0.1426448736998514,
+      "grad_norm": 3.2666187286376953,
+      "learning_rate": 9.669680864754484e-05,
+      "loss": 2.8128,
+      "step": 240
+    },
+    {
+      "epoch": 0.1485884101040119,
+      "grad_norm": 7.568844795227051,
+      "learning_rate": 9.63443643674274e-05,
+      "loss": 2.8483,
+      "step": 250
+    },
+    {
+      "epoch": 0.15453194650817237,
+      "grad_norm": 1.986729383468628,
+      "learning_rate": 9.597476823962784e-05,
+      "loss": 3.2472,
+      "step": 260
+    },
+    {
+      "epoch": 0.16047548291233285,
+      "grad_norm": 2.4101827144622803,
+      "learning_rate": 9.558815705006555e-05,
+      "loss": 3.0007,
+      "step": 270
+    },
+    {
+      "epoch": 0.1664190193164933,
+      "grad_norm": 2.539492607116699,
+      "learning_rate": 9.51846738818602e-05,
+      "loss": 2.9353,
+      "step": 280
+    },
+    {
+      "epoch": 0.1723625557206538,
+      "grad_norm": 2.762788772583008,
+      "learning_rate": 9.476446806237749e-05,
+      "loss": 2.8221,
+      "step": 290
+    },
+    {
+      "epoch": 0.17830609212481427,
+      "grad_norm": 7.846682071685791,
+      "learning_rate": 9.432769510796353e-05,
+      "loss": 2.8917,
+      "step": 300
+    },
+    {
+      "epoch": 0.17830609212481427,
+      "eval_loss": 3.3436031341552734,
+      "eval_runtime": 212.4479,
+      "eval_samples_per_second": 13.34,
+      "eval_steps_per_second": 3.337,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -142,7 +255,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -156,7 +269,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2194006027298406e+17,
+  "total_flos": 4.436915563486249e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null