Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d07f94ec1743689c37895a3a238c2cf89a822eca9a616e94c9f799c6a92b4ec
+oid sha256:6b550c820509f16e2b3c493399810c938f1167615c76da83ca4f3ebec549b9f9
 size 28348936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552f67eefd47c920de1fab775dda0c50eecd9f65d188d75dc41521ef95ec9b0c
+oid sha256:9706f1c81cab528b08d442e6efbc19fabdf6498589189a297d61dc997799c5bf
 size 14714068

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8375041b515f2472c1f51546dc0672fee7801d61bb5b291d5da88eddea1097c
+oid sha256:02fb893e2cbc9f7f86c75f624c996a81a234c82f63bfed48d4d33a25173cc2b0
 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": 1.2417117357254028,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004129884879458985,
+  "best_metric": 1.2390294075012207,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.005162356099323731,
   "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": 9.092,
       "eval_steps_per_second": 4.546,
       "step": 20
+    },
+    {
+      "epoch": 0.004336379123431934,
+      "grad_norm": 0.24532422423362732,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.2764,
+      "step": 21
+    },
+    {
+      "epoch": 0.004542873367404884,
+      "grad_norm": 0.22703120112419128,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3281,
+      "step": 22
+    },
+    {
+      "epoch": 0.004749367611377833,
+      "grad_norm": 0.2032739222049713,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.1221,
+      "step": 23
+    },
+    {
+      "epoch": 0.004955861855350782,
+      "grad_norm": 0.23146522045135498,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.1992,
+      "step": 24
+    },
+    {
+      "epoch": 0.005162356099323731,
+      "grad_norm": 0.23780851066112518,
+      "learning_rate": 0.0,
+      "loss": 1.4991,
+      "step": 25
+    },
+    {
+      "epoch": 0.005162356099323731,
+      "eval_loss": 1.2390294075012207,
+      "eval_runtime": 226.8424,
+      "eval_samples_per_second": 8.993,
+      "eval_steps_per_second": 4.497,
+      "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": 1298095480504320.0,
+  "total_flos": 1622619350630400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null