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:ca29c5c7392deff997ec35896349d4c99deddbe9cd771dc703822b29933d8618
+oid sha256:29c953a91bf91a18c26e31f4dc03dff2405b81e3f3b07ad8ebdf6430874b18a3
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e42a6c4850d1e30c48b22b3cf966421b8640fd909a6a4ff5dbb6505061457e1
+oid sha256:d4867877e1a1aefea07f5765069cf5341bfd99449a2c70b8ec57fb651b55c407
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c10e2d53728a771186d6fda9768e46c47919b7ab630313acb560cb6162f649c
+oid sha256:11cc396d23cc0c797eef3b46c1c4ba411a5bf39be2d859cb355d8fb7cb1cc0ad
 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": 6.847862243652344,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.048520135856380396,
+  "best_metric": 6.828060150146484,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09704027171276079,
   "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": 783.548,
       "eval_steps_per_second": 98.395,
       "step": 25
+    },
+    {
+      "epoch": 0.050460941290635615,
+      "grad_norm": 0.3825906813144684,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 6.8667,
+      "step": 26
+    },
+    {
+      "epoch": 0.05240174672489083,
+      "grad_norm": 0.39277198910713196,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 6.8628,
+      "step": 27
+    },
+    {
+      "epoch": 0.054342552159146046,
+      "grad_norm": 0.39206662774086,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 6.8594,
+      "step": 28
+    },
+    {
+      "epoch": 0.056283357593401265,
+      "grad_norm": 0.3919509947299957,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 6.8515,
+      "step": 29
+    },
+    {
+      "epoch": 0.05822416302765648,
+      "grad_norm": 0.40495046973228455,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 6.8458,
+      "step": 30
+    },
+    {
+      "epoch": 0.060164968461911696,
+      "grad_norm": 0.4313710331916809,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 6.8364,
+      "step": 31
+    },
+    {
+      "epoch": 0.06210577389616691,
+      "grad_norm": 0.46062034368515015,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 6.8315,
+      "step": 32
+    },
+    {
+      "epoch": 0.06404657933042213,
+      "grad_norm": 0.47267451882362366,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 6.8277,
+      "step": 33
+    },
+    {
+      "epoch": 0.06598738476467735,
+      "grad_norm": 1.8254433870315552,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 6.8264,
+      "step": 34
+    },
+    {
+      "epoch": 0.06792819019893255,
+      "grad_norm": 1.8017712831497192,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.8216,
+      "step": 35
+    },
+    {
+      "epoch": 0.06986899563318777,
+      "grad_norm": 1.805820107460022,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 6.8203,
+      "step": 36
+    },
+    {
+      "epoch": 0.07180980106744299,
+      "grad_norm": 1.792947769165039,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 6.8177,
+      "step": 37
+    },
+    {
+      "epoch": 0.07375060650169821,
+      "grad_norm": 1.7828471660614014,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 6.8137,
+      "step": 38
+    },
+    {
+      "epoch": 0.07569141193595343,
+      "grad_norm": 1.78638756275177,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 6.8141,
+      "step": 39
+    },
+    {
+      "epoch": 0.07763221737020863,
+      "grad_norm": 1.765810489654541,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 6.8104,
+      "step": 40
+    },
+    {
+      "epoch": 0.07957302280446385,
+      "grad_norm": 1.7625008821487427,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 6.8077,
+      "step": 41
+    },
+    {
+      "epoch": 0.08151382823871907,
+      "grad_norm": 1.7558047771453857,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 6.8057,
+      "step": 42
+    },
+    {
+      "epoch": 0.08345463367297429,
+      "grad_norm": 1.758226990699768,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 6.8066,
+      "step": 43
+    },
+    {
+      "epoch": 0.0853954391072295,
+      "grad_norm": 1.747825264930725,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 6.8011,
+      "step": 44
+    },
+    {
+      "epoch": 0.08733624454148471,
+      "grad_norm": 1.7420827150344849,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 6.8014,
+      "step": 45
+    },
+    {
+      "epoch": 0.08927704997573993,
+      "grad_norm": 1.7530667781829834,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 6.8033,
+      "step": 46
+    },
+    {
+      "epoch": 0.09121785540999515,
+      "grad_norm": 1.7421718835830688,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 6.8006,
+      "step": 47
+    },
+    {
+      "epoch": 0.09315866084425037,
+      "grad_norm": 1.7380465269088745,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 6.7997,
+      "step": 48
+    },
+    {
+      "epoch": 0.09509946627850557,
+      "grad_norm": 1.743160605430603,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 6.7994,
+      "step": 49
+    },
+    {
+      "epoch": 0.09704027171276079,
+      "grad_norm": 1.7376538515090942,
+      "learning_rate": 0.0,
+      "loss": 6.7979,
+      "step": 50
+    },
+    {
+      "epoch": 0.09704027171276079,
+      "eval_loss": 6.828060150146484,
+      "eval_runtime": 1.1077,
+      "eval_samples_per_second": 783.584,
+      "eval_steps_per_second": 98.399,
+      "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": 480564019200.0,
+  "total_flos": 961128038400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null