Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:459746dd8f961bf23e8d89d9beab5adb4892ad055a67a8615c397563a1c31a03
+oid sha256:9552b46fb198b3e5fb66e327079c791dfc359dfc1ca19e0ee91c270fa56582e9
 size 95402480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dff6ba6d2a2fc2964fe0237b6b8fea3645f84a9bdc11d5a01aa5526cf34b5677
+oid sha256:c1af3f1e166becf947cbb29d50f73ec408a731cfb2e9142cded4dd7ad0f0982a
 size 191012170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241accf5083677e360fec7fce75a0a782e034ba8a707503c48ef17f395ca86ba
+oid sha256:1c03c2c8bb3e85ada00c06d8f15634a504338d250319d9c7fed88bd8a3614be6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.053781270980835,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004253056884635832,
+  "best_metric": 1.0213980674743652,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.008506113769271665,
   "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": 8.139,
       "eval_steps_per_second": 4.069,
       "step": 10
+    },
+    {
+      "epoch": 0.005103668261562998,
+      "grad_norm": 15.459342956542969,
+      "learning_rate": 0.000163742398974869,
+      "loss": 9.1011,
+      "step": 12
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": 21.93683433532715,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.692,
+      "step": 15
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "eval_loss": 1.0534517765045166,
+      "eval_runtime": 121.3238,
+      "eval_samples_per_second": 8.16,
+      "eval_steps_per_second": 4.08,
+      "step": 15
+    },
+    {
+      "epoch": 0.007655502392344498,
+      "grad_norm": 9.392662048339844,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 8.0363,
+      "step": 18
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "eval_loss": 1.0213980674743652,
+      "eval_runtime": 121.3264,
+      "eval_samples_per_second": 8.16,
+      "eval_steps_per_second": 4.08,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1569687116709888.0,
+  "total_flos": 2996675404627968.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null