Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:780b05cc10479ec9565fbc76b50ea2e6f683c9e16be26080953ff65b4fe7985b
+oid sha256:fbb5c971b0f6a3451e86d8dc45848e12141980b4be738aee5711a75f6d8464b6
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ee5572139352354373f9784124225acd851d13510b441b8c75d5b63c35f8c50
+oid sha256:98314d84e827331a32663706cc5773dc115933bd86000f2093f5a572a99d2dd3
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:728b0cc058128f77eb7b109028a2a46b9de64cd9caf4b09a58a17cdc981839fe
+oid sha256:57aaf749f63e59dbbf6959705d9dd339e73fa06bbb2911a152b8ea162285f468
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c409614fe7c4294c30c517ac4a1097721f51ec5d3456b5de1ee4e4e2aed9ba
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.755621910095215,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.01685878658883527,
+  "epoch": 0.025288179883252902,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,181 @@
       "eval_samples_per_second": 110.501,
       "eval_steps_per_second": 27.631,
       "step": 50
+    },
+    {
+      "epoch": 0.017195962320611973,
+      "grad_norm": 0.070088692009449,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 11.7571,
+      "step": 51
+    },
+    {
+      "epoch": 0.01753313805238868,
+      "grad_norm": 0.06235595792531967,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 11.7546,
+      "step": 52
+    },
+    {
+      "epoch": 0.017870313784165384,
+      "grad_norm": 0.059733107686042786,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.756,
+      "step": 53
+    },
+    {
+      "epoch": 0.01820748951594209,
+      "grad_norm": 0.05899588763713837,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 11.7558,
+      "step": 54
+    },
+    {
+      "epoch": 0.018544665247718795,
+      "grad_norm": 0.06057891994714737,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 11.7538,
+      "step": 55
+    },
+    {
+      "epoch": 0.018881840979495502,
+      "grad_norm": 0.06534547358751297,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 11.7541,
+      "step": 56
+    },
+    {
+      "epoch": 0.019219016711272206,
+      "grad_norm": 0.06708380579948425,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 11.7548,
+      "step": 57
+    },
+    {
+      "epoch": 0.01955619244304891,
+      "grad_norm": 0.0493924543261528,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 11.7566,
+      "step": 58
+    },
+    {
+      "epoch": 0.019893368174825617,
+      "grad_norm": 0.05886533483862877,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 11.7567,
+      "step": 59
+    },
+    {
+      "epoch": 0.02023054390660232,
+      "grad_norm": 0.05675411969423294,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 11.7544,
+      "step": 60
+    },
+    {
+      "epoch": 0.02056771963837903,
+      "grad_norm": 0.0635736808180809,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 11.7544,
+      "step": 61
+    },
+    {
+      "epoch": 0.020904895370155732,
+      "grad_norm": 0.06321845203638077,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 11.7532,
+      "step": 62
+    },
+    {
+      "epoch": 0.02124207110193244,
+      "grad_norm": 0.056579649448394775,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 11.7571,
+      "step": 63
+    },
+    {
+      "epoch": 0.021579246833709143,
+      "grad_norm": 0.052547961473464966,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.7533,
+      "step": 64
+    },
+    {
+      "epoch": 0.02191642256548585,
+      "grad_norm": 0.049376729875802994,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 11.7545,
+      "step": 65
+    },
+    {
+      "epoch": 0.022253598297262554,
+      "grad_norm": 0.08245162665843964,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 11.757,
+      "step": 66
+    },
+    {
+      "epoch": 0.02259077402903926,
+      "grad_norm": 0.05794164538383484,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 11.7554,
+      "step": 67
+    },
+    {
+      "epoch": 0.022927949760815965,
+      "grad_norm": 0.04932315647602081,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 11.7546,
+      "step": 68
+    },
+    {
+      "epoch": 0.02326512549259267,
+      "grad_norm": 0.05570968613028526,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 11.7549,
+      "step": 69
+    },
+    {
+      "epoch": 0.023602301224369376,
+      "grad_norm": 0.042931802570819855,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 11.7553,
+      "step": 70
+    },
+    {
+      "epoch": 0.02393947695614608,
+      "grad_norm": 0.05428018793463707,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 11.754,
+      "step": 71
+    },
+    {
+      "epoch": 0.024276652687922787,
+      "grad_norm": 0.048408687114715576,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 11.7557,
+      "step": 72
+    },
+    {
+      "epoch": 0.02461382841969949,
+      "grad_norm": 0.05267668515443802,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 11.754,
+      "step": 73
+    },
+    {
+      "epoch": 0.0249510041514762,
+      "grad_norm": 0.05194791406393051,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 11.7525,
+      "step": 74
+    },
+    {
+      "epoch": 0.025288179883252902,
+      "grad_norm": 0.05502924695611,
+      "learning_rate": 0.0,
+      "loss": 11.7538,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -396,12 +571,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 84215795023872.0,
+  "total_flos": 126479072231424.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null