Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ae8c7ea340ddcdefbf0bdf2ef0b0bbefc2f967ee90496ab8f811414130fd656
+oid sha256:4fa05723dde4dc9dca4f6a0c08a424f39cacd57447d9d14737804b4088bc33df
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e82b63e567d59fcb4891decf202542d88d780563ffbb97acc49ca370987c040f
+oid sha256:4378fe3501dd3fd67195945223e4b4d8c30fa2b5422fb75be13d1096090a1cc6
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:352dc3e973c8c20ee5c66608badf857dcd49b109b503c6aa1a3ac429a13136fb
+oid sha256:546c1f560eab29dbbd8ad3a58f22f38b3f6d7d8801698e62d84517cda04688f4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ddb9588ea654e56e83effcf81a2bc03480954babcf6415cb44d41d3bfb8039f
+oid sha256:d8ce05761f46e7cf72fb17a02e3a0ca15c9d25ce3babf590eeb40568923b8bac
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1644848585128784,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.005768426517456701,
+  "best_metric": 1.139582872390747,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.00865263977618505,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -262,6 +262,133 @@
       "eval_samples_per_second": 58.947,
       "eval_steps_per_second": 14.738,
       "step": 100
+    },
+    {
+      "epoch": 0.005883795047805835,
+      "grad_norm": 0.46381473541259766,
+      "learning_rate": 5.247918773366112e-05,
+      "loss": 1.1083,
+      "step": 102
+    },
+    {
+      "epoch": 0.006056847843329536,
+      "grad_norm": 0.5000247955322266,
+      "learning_rate": 5e-05,
+      "loss": 1.0165,
+      "step": 105
+    },
+    {
+      "epoch": 0.006229900638853237,
+      "grad_norm": 0.38582298159599304,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 1.059,
+      "step": 108
+    },
+    {
+      "epoch": 0.0064029534343769375,
+      "grad_norm": 0.40634816884994507,
+      "learning_rate": 4.504772348747687e-05,
+      "loss": 1.021,
+      "step": 111
+    },
+    {
+      "epoch": 0.006576006229900639,
+      "grad_norm": 0.32036200165748596,
+      "learning_rate": 4.2586817614407895e-05,
+      "loss": 0.9665,
+      "step": 114
+    },
+    {
+      "epoch": 0.00674905902542434,
+      "grad_norm": 0.3690759241580963,
+      "learning_rate": 4.0144148627425993e-05,
+      "loss": 1.1389,
+      "step": 117
+    },
+    {
+      "epoch": 0.006922111820948041,
+      "grad_norm": 0.3883983790874481,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 1.1566,
+      "step": 120
+    },
+    {
+      "epoch": 0.007095164616471742,
+      "grad_norm": 0.4271601438522339,
+      "learning_rate": 3.533749813077677e-05,
+      "loss": 1.1872,
+      "step": 123
+    },
+    {
+      "epoch": 0.0072682174119954425,
+      "grad_norm": 0.358237087726593,
+      "learning_rate": 3.298534127791785e-05,
+      "loss": 1.1692,
+      "step": 126
+    },
+    {
+      "epoch": 0.007441270207519144,
+      "grad_norm": 0.365348219871521,
+      "learning_rate": 3.0675041535377405e-05,
+      "loss": 1.1708,
+      "step": 129
+    },
+    {
+      "epoch": 0.007614323003042845,
+      "grad_norm": 0.41103696823120117,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 1.2572,
+      "step": 132
+    },
+    {
+      "epoch": 0.007787375798566546,
+      "grad_norm": 0.41762009263038635,
+      "learning_rate": 2.6202630348146324e-05,
+      "loss": 1.1534,
+      "step": 135
+    },
+    {
+      "epoch": 0.007960428594090248,
+      "grad_norm": 0.39923688769340515,
+      "learning_rate": 2.405152131093926e-05,
+      "loss": 1.3375,
+      "step": 138
+    },
+    {
+      "epoch": 0.008133481389613948,
+      "grad_norm": 0.47532254457473755,
+      "learning_rate": 2.196424713241637e-05,
+      "loss": 1.3354,
+      "step": 141
+    },
+    {
+      "epoch": 0.008306534185137649,
+      "grad_norm": 0.3896162211894989,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 1.3604,
+      "step": 144
+    },
+    {
+      "epoch": 0.00847958698066135,
+      "grad_norm": 0.4989997446537018,
+      "learning_rate": 1.800157297483417e-05,
+      "loss": 1.3699,
+      "step": 147
+    },
+    {
+      "epoch": 0.00865263977618505,
+      "grad_norm": 0.7773590087890625,
+      "learning_rate": 1.6135921418712956e-05,
+      "loss": 1.333,
+      "step": 150
+    },
+    {
+      "epoch": 0.00865263977618505,
+      "eval_loss": 1.139582872390747,
+      "eval_runtime": 496.6517,
+      "eval_samples_per_second": 58.788,
+      "eval_steps_per_second": 14.698,
+      "step": 150
     }
   ],
   "logging_steps": 3,
@@ -290,7 +417,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6868879540224000.0,
+  "total_flos": 1.0303319310336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null