Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d78b333f55b1d7da2f1214f74c41dc9e2a9e504caa94fe3347fce5386f185b1
+oid sha256:a5cb0fbb33bff12e14f33029d7308beddfc3d1fa9f169a4c70434a29dc5451da
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1bd2b88c0bd4002d85fbc3e11895aa2f5668ad8d8d93eaf48b802d31f9e7b8f
+oid sha256:c5a9420ea59acf78aa3743332592cceb74e79e70973fe46de8d1ffbc4496458d
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334d877cb53b63f40feaf798ed2d27d51fa607b0b40673b82657ea0addb7517c
+oid sha256:8a9dc045b9bc5a565e6dfde3fdb06b0d620422165417c90d17c180980214fd9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.37324193120002747,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01886080724254998,
+  "best_metric": 0.3447200655937195,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03772161448509996,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 109.792,
       "eval_steps_per_second": 13.767,
       "step": 25
+    },
+    {
+      "epoch": 0.01961523953225198,
+      "grad_norm": 0.7944580316543579,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.3518,
+      "step": 26
+    },
+    {
+      "epoch": 0.02036967182195398,
+      "grad_norm": 0.8035205006599426,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2861,
+      "step": 27
+    },
+    {
+      "epoch": 0.021124104111655977,
+      "grad_norm": 0.8863422870635986,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.3642,
+      "step": 28
+    },
+    {
+      "epoch": 0.02187853640135798,
+      "grad_norm": 0.9828726649284363,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.3992,
+      "step": 29
+    },
+    {
+      "epoch": 0.022632968691059976,
+      "grad_norm": 0.8663574457168579,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.2985,
+      "step": 30
+    },
+    {
+      "epoch": 0.023387400980761978,
+      "grad_norm": 0.7883567214012146,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.3014,
+      "step": 31
+    },
+    {
+      "epoch": 0.024141833270463976,
+      "grad_norm": 0.6813034415245056,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2094,
+      "step": 32
+    },
+    {
+      "epoch": 0.024896265560165973,
+      "grad_norm": 0.9920178055763245,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.3045,
+      "step": 33
+    },
+    {
+      "epoch": 0.025650697849867975,
+      "grad_norm": 0.7917585968971252,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.3264,
+      "step": 34
+    },
+    {
+      "epoch": 0.026405130139569973,
+      "grad_norm": 0.7119764089584351,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2033,
+      "step": 35
+    },
+    {
+      "epoch": 0.027159562429271974,
+      "grad_norm": 0.8375765681266785,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.3211,
+      "step": 36
+    },
+    {
+      "epoch": 0.02791399471897397,
+      "grad_norm": 0.8587736487388611,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.2886,
+      "step": 37
+    },
+    {
+      "epoch": 0.028668427008675973,
+      "grad_norm": 1.0836652517318726,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4182,
+      "step": 38
+    },
+    {
+      "epoch": 0.02942285929837797,
+      "grad_norm": 0.9219658374786377,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.2996,
+      "step": 39
+    },
+    {
+      "epoch": 0.03017729158807997,
+      "grad_norm": 0.8775100708007812,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3153,
+      "step": 40
+    },
+    {
+      "epoch": 0.03093172387778197,
+      "grad_norm": 0.8956629633903503,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.298,
+      "step": 41
+    },
+    {
+      "epoch": 0.03168615616748397,
+      "grad_norm": 1.0980639457702637,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3067,
+      "step": 42
+    },
+    {
+      "epoch": 0.03244058845718597,
+      "grad_norm": 0.944616973400116,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.3261,
+      "step": 43
+    },
+    {
+      "epoch": 0.03319502074688797,
+      "grad_norm": 1.178214192390442,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.3682,
+      "step": 44
+    },
+    {
+      "epoch": 0.033949453036589965,
+      "grad_norm": 0.9967607855796814,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2924,
+      "step": 45
+    },
+    {
+      "epoch": 0.03470388532629196,
+      "grad_norm": 1.1236211061477661,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.3553,
+      "step": 46
+    },
+    {
+      "epoch": 0.03545831761599397,
+      "grad_norm": 1.3691303730010986,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.4054,
+      "step": 47
+    },
+    {
+      "epoch": 0.036212749905695965,
+      "grad_norm": 1.5612680912017822,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4232,
+      "step": 48
+    },
+    {
+      "epoch": 0.03696718219539796,
+      "grad_norm": 1.8830749988555908,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.3219,
+      "step": 49
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "grad_norm": 3.1717007160186768,
+      "learning_rate": 0.0,
+      "loss": 0.5892,
+      "step": 50
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "eval_loss": 0.3447200655937195,
+      "eval_runtime": 20.3319,
+      "eval_samples_per_second": 109.828,
+      "eval_steps_per_second": 13.771,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1033684525252608.0,
+  "total_flos": 1999744829227008.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null