Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cec9bb00107f764534eab05d4b98a494b37ea44941b9679d7b34d388a6342e8
+oid sha256:e28a0969e0d12e5c82f2f9386cc5bfa4aadffff4210ed049daa68d9f0f9b6eb9
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7034b9ab685a3ec89bb8b327059f05be0cd230c107e0a834264efe3015eeaef6
+oid sha256:a840335b9b9afe60a3604be7778ac7251bed11b91667e56629bded1cb7947850
 size 36135892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e760cdcb4e65eec1b29da658da89867a7239ec0eadeccfa4c3bb7c20bb7657a
+oid sha256:e01dfd723622e9677c7b52a2436bae7b33f9b2cab0de4c18546921773d165195
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a95a99091545372a9108ea806f0fe10555cc9024eec57a651f3f4b2ee1bd7409
+oid sha256:504bbfdc996899ae0fed191469707d16864e324e1af3e19030b955ead524b577
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3450167179107666,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.008462921823759652,
+  "best_metric": 2.213444709777832,
+  "best_model_checkpoint": "miner_id_24/checkpoint-40",
+  "epoch": 0.016925843647519305,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,154 @@
       "eval_samples_per_second": 33.498,
       "eval_steps_per_second": 8.383,
       "step": 20
+    },
+    {
+      "epoch": 0.008886067914947636,
+      "grad_norm": 1.3622525930404663,
+      "learning_rate": 0.0001880595531856738,
+      "loss": 2.3444,
+      "step": 21
+    },
+    {
+      "epoch": 0.009309214006135618,
+      "grad_norm": 1.3455640077590942,
+      "learning_rate": 0.00018584487936018661,
+      "loss": 2.4493,
+      "step": 22
+    },
+    {
+      "epoch": 0.009732360097323601,
+      "grad_norm": 1.4010404348373413,
+      "learning_rate": 0.00018345732537213027,
+      "loss": 2.4324,
+      "step": 23
+    },
+    {
+      "epoch": 0.010155506188511583,
+      "grad_norm": 1.306706428527832,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.3131,
+      "step": 24
+    },
+    {
+      "epoch": 0.010578652279699566,
+      "grad_norm": 1.194472074508667,
+      "learning_rate": 0.000178183148246803,
+      "loss": 2.3262,
+      "step": 25
+    },
+    {
+      "epoch": 0.011001798370887548,
+      "grad_norm": 1.2795559167861938,
+      "learning_rate": 0.00017530714660036112,
+      "loss": 2.2353,
+      "step": 26
+    },
+    {
+      "epoch": 0.011424944462075532,
+      "grad_norm": 1.4027005434036255,
+      "learning_rate": 0.00017227948638273916,
+      "loss": 2.2406,
+      "step": 27
+    },
+    {
+      "epoch": 0.011848090553263513,
+      "grad_norm": 1.3928605318069458,
+      "learning_rate": 0.00016910626489868649,
+      "loss": 2.3127,
+      "step": 28
+    },
+    {
+      "epoch": 0.012271236644451497,
+      "grad_norm": 1.5246529579162598,
+      "learning_rate": 0.00016579387259397127,
+      "loss": 2.3343,
+      "step": 29
+    },
+    {
+      "epoch": 0.012694382735639479,
+      "grad_norm": 1.4026535749435425,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 2.3008,
+      "step": 30
+    },
+    {
+      "epoch": 0.013117528826827462,
+      "grad_norm": 1.375996708869934,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 2.26,
+      "step": 31
+    },
+    {
+      "epoch": 0.013540674918015444,
+      "grad_norm": 1.3354617357254028,
+      "learning_rate": 0.00015508969814521025,
+      "loss": 2.3904,
+      "step": 32
+    },
+    {
+      "epoch": 0.013963821009203427,
+      "grad_norm": 1.3204755783081055,
+      "learning_rate": 0.00015128992774059063,
+      "loss": 2.2757,
+      "step": 33
+    },
+    {
+      "epoch": 0.014386967100391411,
+      "grad_norm": 1.7939963340759277,
+      "learning_rate": 0.00014738686624729986,
+      "loss": 2.2381,
+      "step": 34
+    },
+    {
+      "epoch": 0.014810113191579393,
+      "grad_norm": 1.3174601793289185,
+      "learning_rate": 0.00014338837391175582,
+      "loss": 2.1787,
+      "step": 35
+    },
+    {
+      "epoch": 0.015233259282767376,
+      "grad_norm": 1.3664051294326782,
+      "learning_rate": 0.00013930250316539238,
+      "loss": 2.1824,
+      "step": 36
+    },
+    {
+      "epoch": 0.015656405373955358,
+      "grad_norm": 1.3687667846679688,
+      "learning_rate": 0.0001351374824081343,
+      "loss": 2.2669,
+      "step": 37
+    },
+    {
+      "epoch": 0.01607955146514334,
+      "grad_norm": 1.2880141735076904,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.2264,
+      "step": 38
+    },
+    {
+      "epoch": 0.016502697556331325,
+      "grad_norm": 1.4410102367401123,
+      "learning_rate": 0.00012660368455666752,
+      "loss": 2.217,
+      "step": 39
+    },
+    {
+      "epoch": 0.016925843647519305,
+      "grad_norm": 1.3260499238967896,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 2.1896,
+      "step": 40
+    },
+    {
+      "epoch": 0.016925843647519305,
+      "eval_loss": 2.213444709777832,
+      "eval_runtime": 76.1355,
+      "eval_samples_per_second": 26.138,
+      "eval_steps_per_second": 6.541,
+      "step": 40
     }
   ],
   "logging_steps": 1,
@@ -191,7 +339,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 369126140805120.0,
+  "total_flos": 738252281610240.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null