Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6951d8cde221c2954b5f24b41e0e3ecd17d1f41fcd81308bafab5a071e473b
+oid sha256:aed30a90e5c25563c2d54ab583218b0c846dc7243485eed822e4a931ee5ac7d8
 size 864368280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d79fc4e72ca42fa694d3bdd1ea537560f4f8ca8c15f4d3f96846bea4f711acc
+oid sha256:d9c78941a695394f38db8cc399e65215c0ceb9791c5d23d0284b35b2f80902cb
 size 439588164

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a28fbc658c3e3be6a1c018f4a984a4d34c53f61a9b1441e6388ef98d5351008
+oid sha256:67372f1a770dd7b82fec7245884e4b2585e25bef8d5f2f82ab2d735f4bc5b246
 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": 0.45177578926086426,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.005236698785085882,
+  "best_metric": 0.433734267950058,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.010473397570171765,
   "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": 9.15,
       "eval_steps_per_second": 1.145,
       "step": 25
+    },
+    {
+      "epoch": 0.005446166736489317,
+      "grad_norm": 0.433027982711792,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.432,
+      "step": 26
+    },
+    {
+      "epoch": 0.005655634687892753,
+      "grad_norm": 0.6095757484436035,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.4492,
+      "step": 27
+    },
+    {
+      "epoch": 0.005865102639296188,
+      "grad_norm": 0.35056862235069275,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.4748,
+      "step": 28
+    },
+    {
+      "epoch": 0.006074570590699623,
+      "grad_norm": 0.40742507576942444,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.4191,
+      "step": 29
+    },
+    {
+      "epoch": 0.006284038542103058,
+      "grad_norm": 0.3521018624305725,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.4234,
+      "step": 30
+    },
+    {
+      "epoch": 0.006493506493506494,
+      "grad_norm": 0.37851810455322266,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.445,
+      "step": 31
+    },
+    {
+      "epoch": 0.006702974444909929,
+      "grad_norm": 0.32674071192741394,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.3601,
+      "step": 32
+    },
+    {
+      "epoch": 0.0069124423963133645,
+      "grad_norm": 0.32310712337493896,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.3583,
+      "step": 33
+    },
+    {
+      "epoch": 0.007121910347716799,
+      "grad_norm": 0.3961349129676819,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.4433,
+      "step": 34
+    },
+    {
+      "epoch": 0.007331378299120235,
+      "grad_norm": 0.33904099464416504,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3749,
+      "step": 35
+    },
+    {
+      "epoch": 0.00754084625052367,
+      "grad_norm": 0.3657974898815155,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.4653,
+      "step": 36
+    },
+    {
+      "epoch": 0.007750314201927106,
+      "grad_norm": 0.37978294491767883,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.4818,
+      "step": 37
+    },
+    {
+      "epoch": 0.007959782153330541,
+      "grad_norm": 0.43654364347457886,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4463,
+      "step": 38
+    },
+    {
+      "epoch": 0.008169250104733976,
+      "grad_norm": 0.3577118515968323,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.414,
+      "step": 39
+    },
+    {
+      "epoch": 0.008378718056137411,
+      "grad_norm": 0.3934151828289032,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.5138,
+      "step": 40
+    },
+    {
+      "epoch": 0.008588186007540846,
+      "grad_norm": 0.3723115026950836,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4938,
+      "step": 41
+    },
+    {
+      "epoch": 0.008797653958944282,
+      "grad_norm": 0.37193042039871216,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.459,
+      "step": 42
+    },
+    {
+      "epoch": 0.009007121910347717,
+      "grad_norm": 0.43767815828323364,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.606,
+      "step": 43
+    },
+    {
+      "epoch": 0.009216589861751152,
+      "grad_norm": 0.4332287013530731,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.5161,
+      "step": 44
+    },
+    {
+      "epoch": 0.009426057813154587,
+      "grad_norm": 0.36227110028266907,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.4897,
+      "step": 45
+    },
+    {
+      "epoch": 0.009635525764558023,
+      "grad_norm": 0.42358869314193726,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.5444,
+      "step": 46
+    },
+    {
+      "epoch": 0.009844993715961458,
+      "grad_norm": 0.36963951587677,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.4438,
+      "step": 47
+    },
+    {
+      "epoch": 0.010054461667364893,
+      "grad_norm": 0.40725886821746826,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4948,
+      "step": 48
+    },
+    {
+      "epoch": 0.010263929618768328,
+      "grad_norm": 0.407678484916687,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.4942,
+      "step": 49
+    },
+    {
+      "epoch": 0.010473397570171765,
+      "grad_norm": 0.5885221362113953,
+      "learning_rate": 0.0,
+      "loss": 0.597,
+      "step": 50
+    },
+    {
+      "epoch": 0.010473397570171765,
+      "eval_loss": 0.433734267950058,
+      "eval_runtime": 878.5022,
+      "eval_samples_per_second": 9.153,
+      "eval_steps_per_second": 1.145,
+      "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": 4.19771556298752e+16,
+  "total_flos": 8.39543112597504e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null