Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b22f925e28f061b18ce81f988602b67432b5828f76ac0c6fad5c250ddece38a
+oid sha256:515b1a691fdb3d8c2d5d67f0a2cf1afd4b2bc5ae91d9fd08c2c6fad438aff200
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:940eabd94c39598fcc0aef35cf6b902dcd24872ca9cb11754ef4d568ab062bad
+oid sha256:3525e41308de61c63cc2798e0edee9a2adacb5be31a4ba27df42e5d927fd99db
 size 166349050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6efbabefda7734d07483d10bcb6bd298685a7f25416c66603623fef766b919fc
+oid sha256:a17be098e82a90601c192aafd4c95c92acb7efc804e41a1222461f862a5e60a7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2095636129379272,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0199203187250996,
+  "best_metric": 1.150830864906311,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0398406374501992,
   "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": 12.386,
       "eval_steps_per_second": 6.193,
       "step": 10
+    },
+    {
+      "epoch": 0.02390438247011952,
+      "grad_norm": 0.6812877058982849,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.0985,
+      "step": 12
+    },
+    {
+      "epoch": 0.029880478087649404,
+      "grad_norm": 0.5477489829063416,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.1426,
+      "step": 15
+    },
+    {
+      "epoch": 0.029880478087649404,
+      "eval_loss": 1.1750253438949585,
+      "eval_runtime": 17.1311,
+      "eval_samples_per_second": 12.375,
+      "eval_steps_per_second": 6.188,
+      "step": 15
+    },
+    {
+      "epoch": 0.035856573705179286,
+      "grad_norm": 0.7969092726707458,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.2434,
+      "step": 18
+    },
+    {
+      "epoch": 0.0398406374501992,
+      "eval_loss": 1.150830864906311,
+      "eval_runtime": 17.1711,
+      "eval_samples_per_second": 12.346,
+      "eval_steps_per_second": 6.173,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1281755320418304.0,
+  "total_flos": 2387583439994880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null