Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5cddbf6767a69b72226e33fb8db58fca7e3533e0fa4f9de4c7a438045236138
+oid sha256:6fad623b459919d03fc84523bf80ee8aa9973675b81a6c99c030857aab130f21
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a682b558cde10b9239bd36ffb99c81c9247660cb94fd2afff6a1553349e48f6
+oid sha256:01a7f042ea48eda7a06ab001fd30c3a8ce6028792d742dc1e6b5379e8bcc0994
 size 68874

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.933143615722656,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.000732305664384314,
+  "best_metric": 11.93295669555664,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.001464611328768628,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 60.9,
       "eval_steps_per_second": 30.45,
       "step": 10
+    },
+    {
+      "epoch": 0.0008787667972611768,
+      "grad_norm": 0.0106218745931983,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 11.9332,
+      "step": 12
+    },
+    {
+      "epoch": 0.001098458496576471,
+      "grad_norm": 0.00903626624494791,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 11.9314,
+      "step": 15
+    },
+    {
+      "epoch": 0.001098458496576471,
+      "eval_loss": 11.933040618896484,
+      "eval_runtime": 94.0048,
+      "eval_samples_per_second": 61.167,
+      "eval_steps_per_second": 30.584,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013181501958917652,
+      "grad_norm": 0.016062667593359947,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9332,
+      "step": 18
+    },
+    {
+      "epoch": 0.001464611328768628,
+      "eval_loss": 11.93295669555664,
+      "eval_runtime": 94.3686,
+      "eval_samples_per_second": 60.931,
+      "eval_steps_per_second": 30.466,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3934715904.0,
+  "total_flos": 7682064384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null