Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9258c3bf97aa3a5549055538a78ff5ecdd5a0381ae8cb44fed53bdf82e82eb7a
+oid sha256:e00c7e2ca2f7201416ee0db7548754ff0b7dad3573e16f5759f340b0edf91035
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff4e7a95fff2b96fc767f188fcd9147729a5edc6157305cc2de75ce14a9af34f
+oid sha256:80645b0c4593e3ffa5f299466cc99572408a8e260842bda9dc94271f7e380e52
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8128afb4afe4aecc26d8f0be5e4c4ed9a96e2778b2735f61e9a821ba55be2be6
+oid sha256:f59a5254780d448320ee839ee90bfa0ce534a45ff625b1caabb810d268fac3ee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b390e57be002933c68cbb0976c807a453fcfb48626c716bc0894f16432712e
+oid sha256:b7e76384fe2e1907e44b199e48722ea251cbbcfea1285f875115318fffa6d887
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7075809240341187,
-  "best_model_checkpoint": "miner_id_24/checkpoint-40",
-  "epoch": 2.2857142857142856,
+  "best_metric": 0.704846203327179,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.857142857142857,
   "eval_steps": 10,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -327,6 +327,84 @@
       "eval_samples_per_second": 7.187,
       "eval_steps_per_second": 1.917,
       "step": 40
+    },
+    {
+      "epoch": 2.342857142857143,
+      "grad_norm": 0.30310121178627014,
+      "learning_rate": 1.801634892205545e-05,
+      "loss": 0.633,
+      "step": 41
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.3069086968898773,
+      "learning_rate": 1.5296290238968303e-05,
+      "loss": 0.7029,
+      "step": 42
+    },
+    {
+      "epoch": 2.4571428571428573,
+      "grad_norm": 0.2964320182800293,
+      "learning_rate": 1.2761390862810907e-05,
+      "loss": 0.7385,
+      "step": 43
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 0.28013864159584045,
+      "learning_rate": 1.0425175578537299e-05,
+      "loss": 0.6347,
+      "step": 44
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.29106035828590393,
+      "learning_rate": 8.30010910550611e-06,
+      "loss": 0.6346,
+      "step": 45
+    },
+    {
+      "epoch": 2.6285714285714286,
+      "grad_norm": 0.28448185324668884,
+      "learning_rate": 6.397529592809614e-06,
+      "loss": 0.6148,
+      "step": 46
+    },
+    {
+      "epoch": 2.685714285714286,
+      "grad_norm": 0.2868902087211609,
+      "learning_rate": 4.727588125342669e-06,
+      "loss": 0.5431,
+      "step": 47
+    },
+    {
+      "epoch": 2.742857142857143,
+      "grad_norm": 0.28776589035987854,
+      "learning_rate": 3.299194563372604e-06,
+      "loss": 0.6296,
+      "step": 48
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.2633899748325348,
+      "learning_rate": 2.1199700045797077e-06,
+      "loss": 0.6345,
+      "step": 49
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.2832770049571991,
+      "learning_rate": 1.196206122203647e-06,
+      "loss": 0.6468,
+      "step": 50
+    },
+    {
+      "epoch": 2.857142857142857,
+      "eval_loss": 0.704846203327179,
+      "eval_runtime": 2.0892,
+      "eval_samples_per_second": 7.18,
+      "eval_steps_per_second": 1.915,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -355,7 +433,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.539491298803712e+16,
+  "total_flos": 1.92436412350464e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null