Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e46077fc1a3040eb50bb152c0a951dfe4bcd17e2c429b9d3cd532457b7af09a
+oid sha256:4ceef834195bc2954f74c02be8f51a9abf729d79cfb8c59195d2c6cbe6bc7670
 size 50358496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4a25b91608577961dddcd7505c54d0bd77f5208b7613312ad99fae5a2abe307
+oid sha256:3e08b029a9f23234c32d7b91622e4b0f803a31b42083e9399d4be42c5f81b660
 size 25785082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a4c552b46c6720173c5a7c3347ea515913a4ebcfa74e90d8ad9d5f9099c799c
+oid sha256:ead17f185899a3642251f609a2cb22baef3b373008df3f089a2536f9cd97f924
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a982b0cf4aa3113be3ccf8c7c44abbcbdbc330e78e6392b70eb543df2118de5
+oid sha256:705cabf5cbc3a6ab0feb67c77b9b453d59efcc939ce90d310af96e621810f990
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.8305675983428955,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.006758273454225972,
+  "best_metric": 2.8287272453308105,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.007723741090543968,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,28 @@
       "eval_samples_per_second": 76.246,
       "eval_steps_per_second": 38.123,
       "step": 350
+    },
+    {
+      "epoch": 0.0069513669814895715,
+      "grad_norm": 34.094635009765625,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 23.7975,
+      "step": 360
+    },
+    {
+      "epoch": 0.007723741090543968,
+      "grad_norm": 126.58602142333984,
+      "learning_rate": 0.0,
+      "loss": 23.1161,
+      "step": 400
+    },
+    {
+      "epoch": 0.007723741090543968,
+      "eval_loss": 2.8287272453308105,
+      "eval_runtime": 571.1268,
+      "eval_samples_per_second": 76.361,
+      "eval_steps_per_second": 38.181,
+      "step": 400
     }
   ],
   "logging_steps": 40,
@@ -150,12 +172,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7323141248385024.0,
+  "total_flos": 8354189109362688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null