Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615578988577e62a1cb4092695d8731fb479d4409219aed6069f2a09d2f48ea5
+oid sha256:90c283f8b29b73c9442f1613fc375ce6183a9e253334a7c5c489eaa4b105e6a2
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3a711e722f140dd4e24e38b0b07c139b70940dc1c95259455dba80ec38ed0ff
+oid sha256:9df867ffba37fff14b33edd21d22ea35bb3ced5ebc80b39424c37b2eb326ea26
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0038f9c4cc916603d95a744848cb9dbe6901f5564389c4acdeed724e7671d314
+oid sha256:ed3ba44f15b28a4eea6f452eb1f09b01f882170e1a8ec791ffc2d4b9e0e5bdb4
 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": 1.3844151496887207,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0014164807535677608,
+  "best_metric": 1.369350790977478,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0021247211303516414,
   "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": 16.933,
       "eval_steps_per_second": 8.467,
       "step": 20
+    },
+    {
+      "epoch": 0.001487304791246149,
+      "grad_norm": 0.5099649429321289,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.284,
+      "step": 21
+    },
+    {
+      "epoch": 0.001699776904281313,
+      "grad_norm": 0.3888559639453888,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.2964,
+      "step": 24
+    },
+    {
+      "epoch": 0.0017706009419597012,
+      "eval_loss": 1.3718374967575073,
+      "eval_runtime": 351.7983,
+      "eval_samples_per_second": 16.902,
+      "eval_steps_per_second": 8.451,
+      "step": 25
+    },
+    {
+      "epoch": 0.0019122490173164772,
+      "grad_norm": 0.4067215025424957,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.2082,
+      "step": 27
+    },
+    {
+      "epoch": 0.0021247211303516414,
+      "grad_norm": 0.6029534339904785,
+      "learning_rate": 0.0,
+      "loss": 1.611,
+      "step": 30
+    },
+    {
+      "epoch": 0.0021247211303516414,
+      "eval_loss": 1.369350790977478,
+      "eval_runtime": 351.5987,
+      "eval_samples_per_second": 16.911,
+      "eval_steps_per_second": 8.456,
+      "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": 6941488227287040.0,
+  "total_flos": 1.049486910554112e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null