Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e34d008a2e970546fd84a45e8e769367b68849bc5b6d2f9c4797f79081c4576
+oid sha256:5143cbd0136f19832706f152840b82830433e3e0a2d06788f16de78443601ef2
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4f166a56b06966776a0607a6446deac1ca333d1910ffe37e0b3be541ca9ce54
+oid sha256:c56e6fdf1b1d7c7d67ceb767a9f08bbdd0524e393fec906aa0c043430751f381
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4329764fc299dd85a84b7a55661e86fcab9bb1b815145a2c18430ce0fa85af0f
+oid sha256:e04d45842b4f57f7bc47c4b705d580a46ba323787f21a23ed4c2131d727599bb
 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": 1.8047796487808228,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007357674974707992,
+  "best_metric": 1.7796204090118408,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.00919709371838499,
   "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": 5.46,
       "eval_steps_per_second": 2.732,
       "step": 20
+    },
+    {
+      "epoch": 0.0077255587234433916,
+      "grad_norm": 2.1431124210357666,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 7.2359,
+      "step": 21
+    },
+    {
+      "epoch": 0.008093442472178792,
+      "grad_norm": 2.209244728088379,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 7.4443,
+      "step": 22
+    },
+    {
+      "epoch": 0.008461326220914191,
+      "grad_norm": 2.184297561645508,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 6.9939,
+      "step": 23
+    },
+    {
+      "epoch": 0.00882920996964959,
+      "grad_norm": 2.2830893993377686,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 7.4885,
+      "step": 24
+    },
+    {
+      "epoch": 0.00919709371838499,
+      "grad_norm": 2.161515951156616,
+      "learning_rate": 0.0,
+      "loss": 7.587,
+      "step": 25
+    },
+    {
+      "epoch": 0.00919709371838499,
+      "eval_loss": 1.7796204090118408,
+      "eval_runtime": 209.7706,
+      "eval_samples_per_second": 5.458,
+      "eval_steps_per_second": 2.732,
+      "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": 3257498484080640.0,
+  "total_flos": 4071873105100800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null