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:dbf3483eda57b30652a76ebf48ffd13c86facaef0fe4b04464b576f9e93e6868
+oid sha256:fc275ecc4fe7b2dae430a6db60bcd949b192921388b25d10652879021e6c98c4
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1faf480b1986137072d06483c87a6aec0ab1f50bcf4421ec5fef5fcec7f115e9
+oid sha256:5f33a9b2274d381bf315443aea39945f1c67ff64d951f0e0044151c154581fd9
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f9f7ef70996e84f7dc6811ec752eea202da535749f2ac49923b4322384b4a8b
+oid sha256:d210cfe60d092a76a87a264de273a75aa804d79a27c1e05b02ad1643265dd256
 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": 3.8484609127044678,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003361627027481301,
+  "best_metric": 3.831801176071167,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.004202033784351626,
   "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": 11.943,
       "eval_steps_per_second": 5.974,
       "step": 20
+    },
+    {
+      "epoch": 0.003529708378855366,
+      "grad_norm": 0.9038202166557312,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.2658,
+      "step": 21
+    },
+    {
+      "epoch": 0.003697789730229431,
+      "grad_norm": 0.7761992812156677,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.4303,
+      "step": 22
+    },
+    {
+      "epoch": 0.003865871081603496,
+      "grad_norm": 0.9693357348442078,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 4.1018,
+      "step": 23
+    },
+    {
+      "epoch": 0.004033952432977561,
+      "grad_norm": 0.9627821445465088,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.7486,
+      "step": 24
+    },
+    {
+      "epoch": 0.004202033784351626,
+      "grad_norm": 1.1465263366699219,
+      "learning_rate": 0.0,
+      "loss": 4.3581,
+      "step": 25
+    },
+    {
+      "epoch": 0.004202033784351626,
+      "eval_loss": 3.831801176071167,
+      "eval_runtime": 211.2104,
+      "eval_samples_per_second": 11.86,
+      "eval_steps_per_second": 5.932,
+      "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": 511583956500480.0,
+  "total_flos": 645874745081856.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null