Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f236a5753f3b146f5cbb02a356b4850c115ae3730b7e14d3ad976d595603377
+oid sha256:0dba366f84c698cf2d5922f6fea069761bd41d10c84c6ad893af3e266c5d6d7f
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b89a20513f9aa60dd038007fe01402821b36bd37b343685e092b517bd7bb390b
+oid sha256:3e673327f3d4558d1d0f66667a0540629a31926fa7a4f09da66ce0dddd9dda78
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:848c0abae9d83cab8e0f976d40f82bd0f3d7bad5fe48b190a8d002ce37cace52
+oid sha256:ce8d8cd060ddb0ca49b00c4f5c236c0c76ea758ba4b4ae7330a4b2e0b86b6556
 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": 10.357394218444824,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.011327594019030359,
+  "best_metric": 10.35035228729248,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.022655188038060717,
   "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": 606.693,
       "eval_steps_per_second": 75.898,
       "step": 25
+    },
+    {
+      "epoch": 0.011780697779791573,
+      "grad_norm": 0.1885799765586853,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 10.3603,
+      "step": 26
+    },
+    {
+      "epoch": 0.012233801540552787,
+      "grad_norm": 0.16406424343585968,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 10.3557,
+      "step": 27
+    },
+    {
+      "epoch": 0.012686905301314002,
+      "grad_norm": 0.17430010437965393,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 10.3564,
+      "step": 28
+    },
+    {
+      "epoch": 0.013140009062075216,
+      "grad_norm": 0.1869587004184723,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 10.3561,
+      "step": 29
+    },
+    {
+      "epoch": 0.01359311282283643,
+      "grad_norm": 0.16364026069641113,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 10.3571,
+      "step": 30
+    },
+    {
+      "epoch": 0.014046216583597644,
+      "grad_norm": 0.13922007381916046,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 10.357,
+      "step": 31
+    },
+    {
+      "epoch": 0.014499320344358859,
+      "grad_norm": 0.1661142110824585,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 10.3528,
+      "step": 32
+    },
+    {
+      "epoch": 0.014952424105120073,
+      "grad_norm": 0.17683999240398407,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 10.3551,
+      "step": 33
+    },
+    {
+      "epoch": 0.015405527865881287,
+      "grad_norm": 0.15338218212127686,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 10.3499,
+      "step": 34
+    },
+    {
+      "epoch": 0.0158586316266425,
+      "grad_norm": 0.17775611579418182,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.351,
+      "step": 35
+    },
+    {
+      "epoch": 0.016311735387403714,
+      "grad_norm": 0.17701967060565948,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 10.3541,
+      "step": 36
+    },
+    {
+      "epoch": 0.01676483914816493,
+      "grad_norm": 0.15589460730552673,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 10.3524,
+      "step": 37
+    },
+    {
+      "epoch": 0.017217942908926143,
+      "grad_norm": 0.14376643300056458,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 10.3524,
+      "step": 38
+    },
+    {
+      "epoch": 0.017671046669687357,
+      "grad_norm": 0.17480316758155823,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 10.3501,
+      "step": 39
+    },
+    {
+      "epoch": 0.01812415043044857,
+      "grad_norm": 0.17131978273391724,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3545,
+      "step": 40
+    },
+    {
+      "epoch": 0.018577254191209785,
+      "grad_norm": 0.14923687279224396,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 10.3502,
+      "step": 41
+    },
+    {
+      "epoch": 0.019030357951971,
+      "grad_norm": 0.1653790920972824,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 10.3535,
+      "step": 42
+    },
+    {
+      "epoch": 0.019483461712732214,
+      "grad_norm": 0.14821237325668335,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 10.3546,
+      "step": 43
+    },
+    {
+      "epoch": 0.01993656547349343,
+      "grad_norm": 0.1650238186120987,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 10.3489,
+      "step": 44
+    },
+    {
+      "epoch": 0.020389669234254643,
+      "grad_norm": 0.13781306147575378,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3507,
+      "step": 45
+    },
+    {
+      "epoch": 0.02084277299501586,
+      "grad_norm": 0.16543304920196533,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 10.3499,
+      "step": 46
+    },
+    {
+      "epoch": 0.021295876755777075,
+      "grad_norm": 0.15752767026424408,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 10.3518,
+      "step": 47
+    },
+    {
+      "epoch": 0.02174898051653829,
+      "grad_norm": 0.1764352172613144,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 10.3515,
+      "step": 48
+    },
+    {
+      "epoch": 0.022202084277299503,
+      "grad_norm": 0.15777145326137543,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 10.3515,
+      "step": 49
+    },
+    {
+      "epoch": 0.022655188038060717,
+      "grad_norm": 0.1509462594985962,
+      "learning_rate": 0.0,
+      "loss": 10.35,
+      "step": 50
+    },
+    {
+      "epoch": 0.022655188038060717,
+      "eval_loss": 10.35035228729248,
+      "eval_runtime": 6.129,
+      "eval_samples_per_second": 606.456,
+      "eval_steps_per_second": 75.868,
+      "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": 2705103519744.0,
+  "total_flos": 4099486777344.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null