Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36edf614b20a1aa8758888ea3f482cfe75473aae473e74f4ac5f6d787dd503f3
+oid sha256:febd23472a2b7e47182a0d7c32bb8f9d7df17f2c0c433568c1bcc9a83e46a940
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ff62577a4db80a25dcb1273af75947e8e407faa08fdbbac2bf65793acc28949
+oid sha256:1aed61d3bff959418bccdc9396dbb40d5eabe31326739368d1114fab8e965cb7
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:129741bc16e0b3a154ff5dee0e729dee66fdc1335cfc27c7606c77964d52f427
+oid sha256:7394a64b3e962f909e29e04b6ddee797f7f39f051dba4f976eaf89c2daf7a5dc
 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": 4.618052005767822,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0017106079072850514,
+  "best_metric": 4.602868556976318,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.002138259884106314,
   "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": 15.7,
       "eval_steps_per_second": 7.852,
       "step": 20
+    },
+    {
+      "epoch": 0.001796138302649304,
+      "grad_norm": 6.339782238006592,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 18.6854,
+      "step": 21
+    },
+    {
+      "epoch": 0.0018816686980135566,
+      "grad_norm": 8.081241607666016,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 15.65,
+      "step": 22
+    },
+    {
+      "epoch": 0.001967199093377809,
+      "grad_norm": 5.962035179138184,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 19.2275,
+      "step": 23
+    },
+    {
+      "epoch": 0.0020527294887420617,
+      "grad_norm": 7.869252681732178,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 20.7399,
+      "step": 24
+    },
+    {
+      "epoch": 0.002138259884106314,
+      "grad_norm": 7.777577877044678,
+      "learning_rate": 0.0,
+      "loss": 19.8523,
+      "step": 25
+    },
+    {
+      "epoch": 0.002138259884106314,
+      "eval_loss": 4.602868556976318,
+      "eval_runtime": 309.311,
+      "eval_samples_per_second": 15.916,
+      "eval_steps_per_second": 7.96,
+      "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": 159523012608000.0,
+  "total_flos": 197057839104000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null