Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5552501a1b1eeb30d6187431fca430ec92f684e7938ddd67f1ac1c281348b781
+oid sha256:ecbd9b786eca650d890315a6ec390a588931242ed1a2b2499c0f5d92dccfa121
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08fc0458ddc3bcd8d51c029ec793b4534ac50ffe946e5031cdd403e4e6b2c46c
+oid sha256:51f96732a776f0a7086d81f932e8eca37a5afd0d00b0d77dd6ced7ecafc054f5
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2b15e73b6443c35deffc5668840769e193cde02231d3175b474b56f6d942c51
+oid sha256:695cf15114f6f13e32b5b22e0fd90e0e8d4ae0a1e10eaa995097fb57ea893351
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3466814756393433,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0017794385871257618,
+  "best_metric": 1.337701439857483,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.002224298233907202,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 8.52,
       "eval_steps_per_second": 4.261,
       "step": 20
+    },
+    {
+      "epoch": 0.0018684105164820499,
+      "grad_norm": 6.964550495147705,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 4.7314,
+      "step": 21
+    },
+    {
+      "epoch": 0.001957382445838338,
+      "grad_norm": 8.814035415649414,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.2008,
+      "step": 22
+    },
+    {
+      "epoch": 0.002046354375194626,
+      "grad_norm": 7.66118860244751,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 5.1538,
+      "step": 23
+    },
+    {
+      "epoch": 0.0021353263045509143,
+      "grad_norm": 7.283710479736328,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 4.6108,
+      "step": 24
+    },
+    {
+      "epoch": 0.002224298233907202,
+      "grad_norm": 8.299412727355957,
+      "learning_rate": 0.0,
+      "loss": 5.7331,
+      "step": 25
+    },
+    {
+      "epoch": 0.002224298233907202,
+      "eval_loss": 1.337701439857483,
+      "eval_runtime": 553.3758,
+      "eval_samples_per_second": 8.553,
+      "eval_steps_per_second": 4.277,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4244442879885312.0,
+  "total_flos": 5305553599856640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null