Training in progress, step 47, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8919b7e782d1c2443ad66ca535b4a4af3e464654c2ca832d1f58cc6bf9aede84
+oid sha256:b3a466b9f1ccfb57b29855eb8f50e6de7c9e0e9e10c39928b8d478bd2533a028
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b014331bddf69a90069c01eca0c250f24c6225b57f51a04f7e7124c27d999e54
+oid sha256:977af5186bcb5246476c6fbc1a6a5081bb3b83b1f244499888dcb58420fba1b1
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319d6b8fda060d0294fd97158033c18d9c48822021690e34a7cd8af00ab53617
+oid sha256:33227ebdc5d770ec0ff71c6f47b6abcdc96ce349fa2484b414d214f5542ba1e6
 size 14960

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": 11.071593284606934,
   "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": 1047.442,
       "eval_steps_per_second": 138.341,
       "step": 25
+    },
+    {
+      "epoch": 1.6640000000000001,
+      "grad_norm": 4.809144020080566,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 11.0729,
+      "step": 26
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 5.203744888305664,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 11.078,
+      "step": 27
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 3.483856678009033,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 11.0775,
+      "step": 28
+    },
+    {
+      "epoch": 1.8559999999999999,
+      "grad_norm": 4.308492660522461,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.0724,
+      "step": 29
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 4.462175369262695,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 11.0692,
+      "step": 30
+    },
+    {
+      "epoch": 1.984,
+      "grad_norm": 4.674779891967773,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 11.0758,
+      "step": 31
+    },
+    {
+      "epoch": 2.048,
+      "grad_norm": 4.3319244384765625,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.0778,
+      "step": 32
+    },
+    {
+      "epoch": 2.112,
+      "grad_norm": 4.53694486618042,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 11.078,
+      "step": 33
+    },
+    {
+      "epoch": 2.176,
+      "grad_norm": 4.895163536071777,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 11.0718,
+      "step": 34
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 6.260696887969971,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 11.0733,
+      "step": 35
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 3.851774215698242,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 11.0782,
+      "step": 36
+    },
+    {
+      "epoch": 2.368,
+      "grad_norm": 4.45391845703125,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 11.0703,
+      "step": 37
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 5.240525722503662,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.0769,
+      "step": 38
+    },
+    {
+      "epoch": 2.496,
+      "grad_norm": 5.4221577644348145,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 11.0718,
+      "step": 39
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 4.008364200592041,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 11.0728,
+      "step": 40
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 4.672859191894531,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 11.0769,
+      "step": 41
+    },
+    {
+      "epoch": 2.6879999999999997,
+      "grad_norm": 5.85573148727417,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 11.0651,
+      "step": 42
+    },
+    {
+      "epoch": 2.752,
+      "grad_norm": 5.035050868988037,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 11.0731,
+      "step": 43
+    },
+    {
+      "epoch": 2.816,
+      "grad_norm": 4.608683109283447,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 11.0689,
+      "step": 44
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 5.071901321411133,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 11.0771,
+      "step": 45
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 6.193559169769287,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 11.0724,
+      "step": 46
+    },
+    {
+      "epoch": 3.008,
+      "grad_norm": 3.6927578449249268,
+      "learning_rate": 0.0,
+      "loss": 11.0724,
+      "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