Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:934798911214172b84002a4c7ee43e583f2c89bd9e5b974626226d5f681cc05f
+oid sha256:da70edcc5fefc3e407e8a0e8cb4b21b165582f20619db8cb63d96e62a034c33b
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1765e24a2122b86748c3ce5cb2e031a03c061e51efbd8bf1fbce1c967fa3ed0
-size 328468404
+oid sha256:7719af313e750fc3e0063ae70c0df58eb04ae561b79f1b3bd5f70dafcb78fc25
+size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7401ac442d77066992141eb9ea0b57d1e4f23fcc2f023e93ec7db7d6e814c0bf
+oid sha256:6e277839274dcede1dc9ad7c8ffffd9d5f234fc5c992789b16d54bd3f1aa7383
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f1d977e4f2f95229581bcd1ac0533ad10dd1745468aa05c633db009acac158
+oid sha256:72d70c30fbe5ceae156e7f3a6e726bcff1fd25730d73db981e0853ab0e72ab09
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4170724153518677,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.09196247930844216,
+  "best_metric": 1.3866181373596191,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.11035497517013058,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 17.394,
       "eval_steps_per_second": 4.36,
       "step": 250
+    },
+    {
+      "epoch": 0.09564097848077985,
+      "grad_norm": 0.7596132755279541,
+      "learning_rate": 0.00011155737479003301,
+      "loss": 1.5365,
+      "step": 260
+    },
+    {
+      "epoch": 0.09931947765311752,
+      "grad_norm": 0.8383329510688782,
+      "learning_rate": 0.00010452484916695262,
+      "loss": 1.4248,
+      "step": 270
+    },
+    {
+      "epoch": 0.10299797682545521,
+      "grad_norm": 0.8279966711997986,
+      "learning_rate": 9.747515083304742e-05,
+      "loss": 1.3758,
+      "step": 280
+    },
+    {
+      "epoch": 0.1066764759977929,
+      "grad_norm": 0.9013005495071411,
+      "learning_rate": 9.044262520996702e-05,
+      "loss": 1.3529,
+      "step": 290
+    },
+    {
+      "epoch": 0.11035497517013058,
+      "grad_norm": 1.153868317604065,
+      "learning_rate": 8.346153405564004e-05,
+      "loss": 1.2002,
+      "step": 300
+    },
+    {
+      "epoch": 0.11035497517013058,
+      "eval_loss": 1.3866181373596191,
+      "eval_runtime": 65.7201,
+      "eval_samples_per_second": 17.422,
+      "eval_steps_per_second": 4.367,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.443402141696e+16,
+  "total_flos": 5.3320825700352e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null