Training in progress, step 47, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9510038dc30b4708017a12a9f0807a139ba81c7520288422f114a93f4f322bbf
+oid sha256:c421bbbcbb41962db194338c8b68919e59fc58cc3d095708e52fa945c06b558e
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78be1ffdf5a8b5fe48aac526eb7846fbdbe96a5eecbf5437c48bc75966e371ba
+oid sha256:c4f023da92d3fb2b5bbaed59f615cdcc0887ec1902f7585b73c74d40e325b9b5
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3920d42eff2e3f81ad57b76f1ab51b8b6805abb7aaff0a465761c32eaf43e751
+oid sha256:82328c46f52fb686be64f8caa69b14ff923f4d070165b2d092119c82f45806fd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f8b3a1736e564a4b137739bad0216b115210f6249caaa3cc1297f0a2de1098
+oid sha256:91d2ac2b7eabf057fe3a35c0bbc4681bb9253f386e25e6e7cbf956cd50e43d02
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:970a46bb7467d976a43f0beb9e7c74dbeb8f4ff725d368f66e8bfebd5270fe4d
+oid sha256:7dfbe37ee33752ada5cb964d53b19a0358e420903b7ebbd188f18e5b9e51658c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ffb34c2329cff24c81267ba92e305440f5541296091d810f80fdc7a8f09d8f
+oid sha256:1c0449131b67708924f0d9f9675c17daaa11a086eb1e024cfcd64d74452c62ef
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:698599bc6a23f90bcfa6fe6477fe271a75dd69b61906d06e949f339ef005f13a
+oid sha256:35151b95c3cc502d9e4fc6d9dc99d112a424ad3624e33428ecbe517e837a6fc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.07034969329834,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.6,
+  "epoch": 3.008,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 47,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,160 @@
       "eval_samples_per_second": 1005.981,
       "eval_steps_per_second": 132.865,
       "step": 25
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 4.830604553222656,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 11.0723,
+      "step": 26
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 5.275437831878662,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 11.0776,
+      "step": 27
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 3.4468271732330322,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 11.0769,
+      "step": 28
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 4.286435604095459,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.0735,
+      "step": 29
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 4.553131580352783,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 11.0687,
+      "step": 30
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 4.932947158813477,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 11.0769,
+      "step": 31
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 4.311124801635742,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.0789,
+      "step": 32
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 4.4758620262146,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 11.0791,
+      "step": 33
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 4.808510780334473,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 11.0723,
+      "step": 34
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 6.5858964920043945,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 11.0734,
+      "step": 35
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 3.916059732437134,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 11.079,
+      "step": 36
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 4.540916919708252,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 11.0698,
+      "step": 37
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 5.163912296295166,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.0768,
+      "step": 38
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 5.536440849304199,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 11.0735,
+      "step": 39
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 3.9795005321502686,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 11.0733,
+      "step": 40
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 4.769349098205566,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 11.0765,
+      "step": 41
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 5.8106465339660645,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 11.0647,
+      "step": 42
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 5.031451225280762,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 11.0743,
+      "step": 43
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 4.750061988830566,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 11.07,
+      "step": 44
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.097783088684082,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 11.0777,
+      "step": 45
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 6.31856632232666,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 11.0714,
+      "step": 46
+    },
+    {
+      "epoch": 3.008,
+      "grad_norm": 3.7459287643432617,
+      "learning_rate": 0.0,
+      "loss": 11.0713,
+      "step": 47
     }
   ],
   "logging_steps": 1,
@@ -221,12 +375,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2101346304000.0,
+  "total_flos": 3950531051520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null