Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dbb4ff32b34e09178b4e950d8379ab3edcf829a3e615605d02b5e532c4fbb5f
+oid sha256:6835213552c3129524831ed6ef9892b2263f0ea5d41e24298fa7e589d02885e7
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0607fefcde41656769b02de8740bd6e7a7f72268f3b8dae74a9217dc2b72bf
+oid sha256:bffd4df5f63aec4d8cd6f8b5148a49788a657ec5703271379192d37b1ec96d69
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d539fe4d67d4d8fda2e72f75d140391a0aaf6f7ce2131b7b9f8701adbd03b4
+oid sha256:4329764fc299dd85a84b7a55661e86fcab9bb1b815145a2c18430ce0fa85af0f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c971b41fe7521762372f4d846fdb25f7ae6aeaf0776fa4aa30da6edd7f567bf
+oid sha256:e6da9db9fb6671f70d2a4e7001f6523f325b24520bef80a5a7ba3fc8703a924b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5595622062683105,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0007620934707641893,
+  "best_metric": 1.4337732791900635,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0015241869415283786,
   "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": 9.532,
       "eval_steps_per_second": 4.767,
       "step": 10
+    },
+    {
+      "epoch": 0.0009145121649170271,
+      "grad_norm": 2.1917099952697754,
+      "learning_rate": 4.093559974371725e-05,
+      "loss": 6.4835,
+      "step": 12
+    },
+    {
+      "epoch": 0.0011431402061462838,
+      "grad_norm": 1.7847143411636353,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 5.2452,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011431402061462838,
+      "eval_loss": 1.472966194152832,
+      "eval_runtime": 576.322,
+      "eval_samples_per_second": 9.587,
+      "eval_steps_per_second": 4.794,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013717682473755406,
+      "grad_norm": 1.906245470046997,
+      "learning_rate": 2.3430237011767167e-05,
+      "loss": 5.4955,
+      "step": 18
+    },
+    {
+      "epoch": 0.0015241869415283786,
+      "eval_loss": 1.4337732791900635,
+      "eval_runtime": 576.6791,
+      "eval_samples_per_second": 9.581,
+      "eval_steps_per_second": 4.791,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1842091508367360.0,
+  "total_flos": 3684183016734720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null