Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:455e9ce0816a12f21c872d33b5b0b04552d2082b5e1070d69a2044fb229d98ad
+oid sha256:3755293a356d586c7b3717850c4a2c8225ee747e5ed84b98d4af670d5e4111cf
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1052feb073c4a5f2467d21109f3763a140eac414ba1694867a71ca2543867f8e
+oid sha256:3f1b2716466288a10f35613e7858819d3eebc8ef87711f89312348b0a48cd206
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f19095ce893b13ba667dc4a8cb6d3911a9d816620c263e1f0eedfa9f49bb839
+oid sha256:1457c3205c67368202f9e11315ab5b66da1ba854d305a975c0e59cd06ce9feca
 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": 1.8223572969436646,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.042034468263976464,
+  "best_metric": 1.764018177986145,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08406893652795293,
   "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": 18.607,
       "eval_steps_per_second": 2.34,
       "step": 25
+    },
+    {
+      "epoch": 0.04371584699453552,
+      "grad_norm": 5.934324741363525,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.0369,
+      "step": 26
+    },
+    {
+      "epoch": 0.04539722572509458,
+      "grad_norm": 4.599030017852783,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.6305,
+      "step": 27
+    },
+    {
+      "epoch": 0.047078604455653636,
+      "grad_norm": 4.753709316253662,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.9704,
+      "step": 28
+    },
+    {
+      "epoch": 0.0487599831862127,
+      "grad_norm": 3.938774585723877,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.4958,
+      "step": 29
+    },
+    {
+      "epoch": 0.05044136191677175,
+      "grad_norm": 4.442599773406982,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.7748,
+      "step": 30
+    },
+    {
+      "epoch": 0.052122740647330815,
+      "grad_norm": 4.685940742492676,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.8004,
+      "step": 31
+    },
+    {
+      "epoch": 0.05380411937788987,
+      "grad_norm": 4.308958530426025,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.5518,
+      "step": 32
+    },
+    {
+      "epoch": 0.05548549810844893,
+      "grad_norm": 4.3257737159729,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.7638,
+      "step": 33
+    },
+    {
+      "epoch": 0.057166876839007986,
+      "grad_norm": 4.2862324714660645,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.6903,
+      "step": 34
+    },
+    {
+      "epoch": 0.05884825556956705,
+      "grad_norm": 4.446920394897461,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5118,
+      "step": 35
+    },
+    {
+      "epoch": 0.0605296343001261,
+      "grad_norm": 4.1637468338012695,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.7835,
+      "step": 36
+    },
+    {
+      "epoch": 0.062211013030685165,
+      "grad_norm": 5.5191144943237305,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.7005,
+      "step": 37
+    },
+    {
+      "epoch": 0.06389239176124423,
+      "grad_norm": 4.147561073303223,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.5857,
+      "step": 38
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 4.230316638946533,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8089,
+      "step": 39
+    },
+    {
+      "epoch": 0.06725514922236234,
+      "grad_norm": 4.044164180755615,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.5085,
+      "step": 40
+    },
+    {
+      "epoch": 0.06893652795292139,
+      "grad_norm": 4.815402507781982,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6942,
+      "step": 41
+    },
+    {
+      "epoch": 0.07061790668348046,
+      "grad_norm": 4.001568794250488,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.473,
+      "step": 42
+    },
+    {
+      "epoch": 0.07229928541403952,
+      "grad_norm": 4.6987504959106445,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7146,
+      "step": 43
+    },
+    {
+      "epoch": 0.07398066414459857,
+      "grad_norm": 4.370215892791748,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.6669,
+      "step": 44
+    },
+    {
+      "epoch": 0.07566204287515763,
+      "grad_norm": 4.669373035430908,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.549,
+      "step": 45
+    },
+    {
+      "epoch": 0.0773434216057167,
+      "grad_norm": 3.481714963912964,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.246,
+      "step": 46
+    },
+    {
+      "epoch": 0.07902480033627575,
+      "grad_norm": 4.119218826293945,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5097,
+      "step": 47
+    },
+    {
+      "epoch": 0.0807061790668348,
+      "grad_norm": 4.261626243591309,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.262,
+      "step": 48
+    },
+    {
+      "epoch": 0.08238755779739386,
+      "grad_norm": 4.05534553527832,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.2714,
+      "step": 49
+    },
+    {
+      "epoch": 0.08406893652795293,
+      "grad_norm": 4.904563903808594,
+      "learning_rate": 0.0,
+      "loss": 1.3498,
+      "step": 50
+    },
+    {
+      "epoch": 0.08406893652795293,
+      "eval_loss": 1.764018177986145,
+      "eval_runtime": 53.8465,
+      "eval_samples_per_second": 18.608,
+      "eval_steps_per_second": 2.34,
+      "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": 3.02966221307904e+16,
+  "total_flos": 4.86582113009664e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null