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:eaff1a43ce68534d1123c190f4350c9ec3f2d96b71c85e264511357b8450443b
+oid sha256:eaaec0b045149baaef6958f3f8cd09c7cd6a9ce67e23bc05617496813a71d18f
 size 121155320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c90b2f616a0776da92566ba6437afddd77f85b9575467a11a8d5e669a226222
+oid sha256:96ecd541e9109c23665f9fdd59c76a811328783ea2198fa80a44b7ebdcbd0c9e
 size 61896852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382fa05c7e8947d4b97b98a2156db3561da2915a2519aa8a8013e8eb1b7188c6
+oid sha256:8ac7a1d8d1498c3d02901557e82206bd870cc1e4bac420f90ef7164aa5a8433c
 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": 0.00023969815811142325,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.5869565217391304,
+  "epoch": 2.383399209486166,
   "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": 20.166,
       "eval_steps_per_second": 5.089,
       "step": 50
+    },
+    {
+      "epoch": 1.6185770750988142,
+      "grad_norm": 0.007441387511789799,
+      "learning_rate": 4.007047666771274e-05,
+      "loss": 0.0003,
+      "step": 51
+    },
+    {
+      "epoch": 1.650197628458498,
+      "grad_norm": 0.004175810143351555,
+      "learning_rate": 3.728908329032567e-05,
+      "loss": 0.0003,
+      "step": 52
+    },
+    {
+      "epoch": 1.6818181818181817,
+      "grad_norm": 0.025354648008942604,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.003,
+      "step": 53
+    },
+    {
+      "epoch": 1.7134387351778657,
+      "grad_norm": 0.0125960111618042,
+      "learning_rate": 3.1859614732467954e-05,
+      "loss": 0.0004,
+      "step": 54
+    },
+    {
+      "epoch": 1.7450592885375493,
+      "grad_norm": 0.004288897849619389,
+      "learning_rate": 2.9229249349905684e-05,
+      "loss": 0.0003,
+      "step": 55
+    },
+    {
+      "epoch": 1.7766798418972332,
+      "grad_norm": 0.13706451654434204,
+      "learning_rate": 2.6666633838716314e-05,
+      "loss": 0.0044,
+      "step": 56
+    },
+    {
+      "epoch": 1.808300395256917,
+      "grad_norm": 0.13290545344352722,
+      "learning_rate": 2.418012691805191e-05,
+      "loss": 0.0016,
+      "step": 57
+    },
+    {
+      "epoch": 1.8399209486166008,
+      "grad_norm": 0.004434171598404646,
+      "learning_rate": 2.1777839056661554e-05,
+      "loss": 0.0002,
+      "step": 58
+    },
+    {
+      "epoch": 1.8715415019762847,
+      "grad_norm": 0.004509397316724062,
+      "learning_rate": 1.946760601822809e-05,
+      "loss": 0.0003,
+      "step": 59
+    },
+    {
+      "epoch": 1.9031620553359683,
+      "grad_norm": 0.03684943914413452,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.0024,
+      "step": 60
+    },
+    {
+      "epoch": 1.9347826086956523,
+      "grad_norm": 0.004858649801462889,
+      "learning_rate": 1.5153121567235335e-05,
+      "loss": 0.0003,
+      "step": 61
+    },
+    {
+      "epoch": 1.966403162055336,
+      "grad_norm": 0.033181995153427124,
+      "learning_rate": 1.3162943106179749e-05,
+      "loss": 0.0036,
+      "step": 62
+    },
+    {
+      "epoch": 2.0039525691699605,
+      "grad_norm": 0.007152313366532326,
+      "learning_rate": 1.1292919468045877e-05,
+      "loss": 0.0004,
+      "step": 63
+    },
+    {
+      "epoch": 2.035573122529644,
+      "grad_norm": 0.053472116589546204,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0011,
+      "step": 64
+    },
+    {
+      "epoch": 2.067193675889328,
+      "grad_norm": 0.0040871379896998405,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.0003,
+      "step": 65
+    },
+    {
+      "epoch": 2.0988142292490117,
+      "grad_norm": 0.0035609269980341196,
+      "learning_rate": 6.462696144011149e-06,
+      "loss": 0.0002,
+      "step": 66
+    },
+    {
+      "epoch": 2.130434782608696,
+      "grad_norm": 0.02019282802939415,
+      "learning_rate": 5.13007856543209e-06,
+      "loss": 0.0013,
+      "step": 67
+    },
+    {
+      "epoch": 2.1620553359683794,
+      "grad_norm": 0.004724355414509773,
+      "learning_rate": 3.9438173442575e-06,
+      "loss": 0.0002,
+      "step": 68
+    },
+    {
+      "epoch": 2.1936758893280635,
+      "grad_norm": 0.0054779378697276115,
+      "learning_rate": 2.9077818180237693e-06,
+      "loss": 0.0003,
+      "step": 69
+    },
+    {
+      "epoch": 2.225296442687747,
+      "grad_norm": 0.004262240137904882,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.0002,
+      "step": 70
+    },
+    {
+      "epoch": 2.2569169960474307,
+      "grad_norm": 0.09871349483728409,
+      "learning_rate": 1.2994041528833266e-06,
+      "loss": 0.0012,
+      "step": 71
+    },
+    {
+      "epoch": 2.2885375494071147,
+      "grad_norm": 0.014313112944364548,
+      "learning_rate": 7.323082076153509e-07,
+      "loss": 0.0005,
+      "step": 72
+    },
+    {
+      "epoch": 2.3201581027667983,
+      "grad_norm": 0.03431084752082825,
+      "learning_rate": 3.2591323257248893e-07,
+      "loss": 0.0006,
+      "step": 73
+    },
+    {
+      "epoch": 2.3517786561264824,
+      "grad_norm": 0.004373958334326744,
+      "learning_rate": 8.15448036932176e-08,
+      "loss": 0.0003,
+      "step": 74
+    },
+    {
+      "epoch": 2.383399209486166,
+      "grad_norm": 0.05674320086836815,
+      "learning_rate": 0.0,
+      "loss": 0.0059,
+      "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": 2.077538226536448e+16,
+  "total_flos": 3.134618974814208e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null