Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a5b4d04dcc4a31e9fb391859eec2abd69340b00f5558fda8c580ac980f45039
+oid sha256:f7d18435676a33e2bf7728eaa1e324f1b3e4b208c7d9f07311bfc2d6de08a9cc
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1eab35190b4ea5101be164cf35ef8b7c262e6fb7c0b42c95c2047f236031cb2
+oid sha256:84b7afa10944d0ce96007a0a6275ee3a00e126798981bda2e312fedf8359a932
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
+oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.092531442642212,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003772161448509996,
+  "best_metric": 2.070955276489258,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005658242172764994,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 11.712,
       "eval_steps_per_second": 5.859,
       "step": 20
+    },
+    {
+      "epoch": 0.003960769520935496,
+      "grad_norm": 0.7086843252182007,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.2362,
+      "step": 21
+    },
+    {
+      "epoch": 0.004526593738211996,
+      "grad_norm": 0.8603949546813965,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.0942,
+      "step": 24
+    },
+    {
+      "epoch": 0.004715201810637495,
+      "eval_loss": 2.0762219429016113,
+      "eval_runtime": 190.7425,
+      "eval_samples_per_second": 11.707,
+      "eval_steps_per_second": 5.856,
+      "step": 25
+    },
+    {
+      "epoch": 0.005092417955488495,
+      "grad_norm": 0.7996680736541748,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.135,
+      "step": 27
+    },
+    {
+      "epoch": 0.005658242172764994,
+      "grad_norm": 0.9141614437103271,
+      "learning_rate": 0.0,
+      "loss": 2.0314,
+      "step": 30
+    },
+    {
+      "epoch": 0.005658242172764994,
+      "eval_loss": 2.070955276489258,
+      "eval_runtime": 190.8071,
+      "eval_samples_per_second": 11.703,
+      "eval_steps_per_second": 5.854,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7418872835604480.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null