Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ff1e970806f8d5e26a9eff7663f06d7e498309443763ae6573e5362f7fbaefe
+oid sha256:b59fc64eed9de126ff9470a8c8475edd8079173c68f77929ff5e545c45fe6dbf
 size 209760536

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d0f3875b907fc3290d90a491468acd54a4d32e6bb680ad5ddb3c5e224ff812b
+oid sha256:1844487d8a444c6264ddac9015dbecd48cf6837c634be4188cb889193cec0546
 size 419620666

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83486417bdee3ce84342137be74ab276aaffbcb89513f06c08dd8cb1619fddab
+oid sha256:0dde818a0fb0fcda30af73e8e8fc599e1229a8d1c318a4e90d13938d315b1b4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5510300397872925,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0008699907563482138,
+  "best_metric": 1.5060062408447266,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0013049861345223207,
   "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": 5.534,
       "eval_steps_per_second": 2.767,
       "step": 20
+    },
+    {
+      "epoch": 0.0009134902941656245,
+      "grad_norm": 1.4493082761764526,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 6.3174,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010439889076178566,
+      "grad_norm": 2.05763578414917,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 5.9476,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010874884454352672,
+      "eval_loss": 1.5137639045715332,
+      "eval_runtime": 1749.268,
+      "eval_samples_per_second": 5.534,
+      "eval_steps_per_second": 2.767,
+      "step": 25
+    },
+    {
+      "epoch": 0.0011744875210700887,
+      "grad_norm": 1.5941640138626099,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 6.4491,
+      "step": 27
+    },
+    {
+      "epoch": 0.0013049861345223207,
+      "grad_norm": 1.5353425741195679,
+      "learning_rate": 0.0,
+      "loss": 6.2578,
+      "step": 30
+    },
+    {
+      "epoch": 0.0013049861345223207,
+      "eval_loss": 1.5060062408447266,
+      "eval_runtime": 1748.7018,
+      "eval_samples_per_second": 5.536,
+      "eval_steps_per_second": 2.768,
+      "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": 1.273225870835712e+16,
+  "total_flos": 1.933417063120896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null