Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2be8f4cc537c2944247fdee3b385f4ff799d6f9aecc13736d2eea491cad53ea4
+oid sha256:ff1064a8903ce48850e95407dafa7e6f6da729cd13e10a14ffa38bdca0a977b7
 size 104902272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3a6aa31b5177a36b596ac65bd9d398dd8b38167d944f4e2ecd73d01343d55d3
+oid sha256:4766d77086676fe95c3e2fe7399f637cbec2257c225f2b584e75852b21bff008
 size 53622996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acca732549f543f7618d07961e2446fe20bc44f03c11629a1d6784169a308b9b
+oid sha256:8e0725fa5caf597200cd17099fbc09a252940f0a1b10f615aa778a871d49448c
 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": 1.4339179992675781,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.021592442645074223,
+  "best_metric": 1.426554560661316,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02699055330634278,
   "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": 4.786,
       "eval_steps_per_second": 2.393,
       "step": 20
+    },
+    {
+      "epoch": 0.022672064777327937,
+      "grad_norm": 1.5035929679870605,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 5.4438,
+      "step": 21
+    },
+    {
+      "epoch": 0.023751686909581647,
+      "grad_norm": 1.3411996364593506,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.0783,
+      "step": 22
+    },
+    {
+      "epoch": 0.024831309041835357,
+      "grad_norm": 1.7389713525772095,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 5.9207,
+      "step": 23
+    },
+    {
+      "epoch": 0.025910931174089068,
+      "grad_norm": 1.6175214052200317,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 6.0236,
+      "step": 24
+    },
+    {
+      "epoch": 0.02699055330634278,
+      "grad_norm": 1.2862156629562378,
+      "learning_rate": 0.0,
+      "loss": 5.6139,
+      "step": 25
+    },
+    {
+      "epoch": 0.02699055330634278,
+      "eval_loss": 1.426554560661316,
+      "eval_runtime": 81.5554,
+      "eval_samples_per_second": 4.782,
+      "eval_steps_per_second": 2.391,
+      "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": 9804141035520000.0,
+  "total_flos": 1.207870175576064e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null