Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6252aa8926f44fb67314af27b275aaec8cc0868e7294822ea2a2529710ed1d50
+oid sha256:9a69e69df1c215c9fbd45805f864ee3ac4c779dc496d6f4a5065ef792e21302a
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03d8111879456358dc5ce38f5793e07dc5cd6ba31d8f8aea213fd39c704b233d
+oid sha256:aa69e17bdeb510add6d20eb825063a8f124666a15f04da1625db2aa0e4664d82
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a850cc6eda316843b981d8bd2fc891e4769877ed1461a31c08af31fbf0c075d3
+oid sha256:e31e0fdb3869a241061ca27b64da9fbd0a58f71586f852b6544558cc627e89db
 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": 1.317594051361084,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.008451299387280795,
+  "best_metric": 1.1583677530288696,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.01690259877456159,
   "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": 6.633,
       "eval_steps_per_second": 3.323,
       "step": 10
+    },
+    {
+      "epoch": 0.010141559264736952,
+      "grad_norm": 2.6403181552886963,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.2473,
+      "step": 12
+    },
+    {
+      "epoch": 0.012676949080921191,
+      "grad_norm": 1.7580329179763794,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2577,
+      "step": 15
+    },
+    {
+      "epoch": 0.012676949080921191,
+      "eval_loss": 1.1970915794372559,
+      "eval_runtime": 75.3571,
+      "eval_samples_per_second": 6.622,
+      "eval_steps_per_second": 3.318,
+      "step": 15
+    },
+    {
+      "epoch": 0.01521233889710543,
+      "grad_norm": 1.215514063835144,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.1374,
+      "step": 18
+    },
+    {
+      "epoch": 0.01690259877456159,
+      "eval_loss": 1.1583677530288696,
+      "eval_runtime": 75.4072,
+      "eval_samples_per_second": 6.617,
+      "eval_steps_per_second": 3.315,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3834471807713280.0,
+  "total_flos": 7668943615426560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null