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:c5acd1345dcdeaee098f2fe149565bf11770aa79114f5aa4178d469c2353c3e6
+oid sha256:f511adb0f30619b6f3f3e72e75fbefc8a024387c146290f9298ae6e4c92e01a5
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b0b3ea07eafbe0418cb6c20c153909d08a4f158523e4d4aa9c7b8d4c18f4895
+oid sha256:24f2d0141b44e6bbd257e26a3687d92a33a32dcd355bef54353fbbf25bdad5cb
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424bbee88b71119b8b822764a7241f778767585adc92bb9d9774ed0b0318129d
+oid sha256:a42a28bae49361ff8b728d0ff06ae05404a85e064ad9ea87dca959c6b013bf1c
 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": 1.116862416267395,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06006006006006006,
+  "best_metric": 0.9848859906196594,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12012012012012012,
   "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": 14.069,
       "eval_steps_per_second": 1.766,
       "step": 25
+    },
+    {
+      "epoch": 0.06246246246246246,
+      "grad_norm": 0.35601821541786194,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.7875,
+      "step": 26
+    },
+    {
+      "epoch": 0.06486486486486487,
+      "grad_norm": 0.4093438684940338,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.962,
+      "step": 27
+    },
+    {
+      "epoch": 0.06726726726726727,
+      "grad_norm": 0.4381888508796692,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.0355,
+      "step": 28
+    },
+    {
+      "epoch": 0.06966966966966967,
+      "grad_norm": 0.394925594329834,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.8719,
+      "step": 29
+    },
+    {
+      "epoch": 0.07207207207207207,
+      "grad_norm": 0.39502450823783875,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.973,
+      "step": 30
+    },
+    {
+      "epoch": 0.07447447447447447,
+      "grad_norm": 0.41608545184135437,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.7986,
+      "step": 31
+    },
+    {
+      "epoch": 0.07687687687687687,
+      "grad_norm": 0.4361729919910431,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.9382,
+      "step": 32
+    },
+    {
+      "epoch": 0.07927927927927927,
+      "grad_norm": 0.42400476336479187,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.0115,
+      "step": 33
+    },
+    {
+      "epoch": 0.08168168168168168,
+      "grad_norm": 0.39441099762916565,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.8631,
+      "step": 34
+    },
+    {
+      "epoch": 0.08408408408408409,
+      "grad_norm": 0.42576584219932556,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0433,
+      "step": 35
+    },
+    {
+      "epoch": 0.08648648648648649,
+      "grad_norm": 0.3904152512550354,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.0188,
+      "step": 36
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.5034300088882446,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.1074,
+      "step": 37
+    },
+    {
+      "epoch": 0.0912912912912913,
+      "grad_norm": 0.6272788643836975,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.1985,
+      "step": 38
+    },
+    {
+      "epoch": 0.0936936936936937,
+      "grad_norm": 0.5937858819961548,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.3471,
+      "step": 39
+    },
+    {
+      "epoch": 0.0960960960960961,
+      "grad_norm": 0.646436333656311,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.353,
+      "step": 40
+    },
+    {
+      "epoch": 0.0984984984984985,
+      "grad_norm": 0.5500105023384094,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.1414,
+      "step": 41
+    },
+    {
+      "epoch": 0.1009009009009009,
+      "grad_norm": 0.6234367489814758,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.3546,
+      "step": 42
+    },
+    {
+      "epoch": 0.1033033033033033,
+      "grad_norm": 0.5408471822738647,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.9866,
+      "step": 43
+    },
+    {
+      "epoch": 0.1057057057057057,
+      "grad_norm": 0.8120220303535461,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4077,
+      "step": 44
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 0.654384195804596,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.7303,
+      "step": 45
+    },
+    {
+      "epoch": 0.11051051051051052,
+      "grad_norm": 0.6135900616645813,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.4114,
+      "step": 46
+    },
+    {
+      "epoch": 0.11291291291291292,
+      "grad_norm": 0.5442359447479248,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.22,
+      "step": 47
+    },
+    {
+      "epoch": 0.11531531531531532,
+      "grad_norm": 0.5599455237388611,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.5017,
+      "step": 48
+    },
+    {
+      "epoch": 0.11771771771771772,
+      "grad_norm": 0.6104506254196167,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4995,
+      "step": 49
+    },
+    {
+      "epoch": 0.12012012012012012,
+      "grad_norm": 0.44341933727264404,
+      "learning_rate": 0.0,
+      "loss": 0.8638,
+      "step": 50
+    },
+    {
+      "epoch": 0.12012012012012012,
+      "eval_loss": 0.9848859906196594,
+      "eval_runtime": 49.8489,
+      "eval_samples_per_second": 14.063,
+      "eval_steps_per_second": 1.765,
+      "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": 3.5547217133568e+16,
+  "total_flos": 7.1094434267136e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null