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:c6bd4f2f1df4e2e110bea60050850f0c12e0d2e8a1c51d5ce37c27922a6c6259
+oid sha256:9bc369638755a57eed0141fd6401f5bb4d975ea899b2158aea92e03707f6847f
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2359a8a8895c3744de118806c103e49f2ace50bd53c5108c727e93183987b1b3
+oid sha256:b22ad760c79407e6459d8fbc93e2b7595309431feb186cda658171f159a63867
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2260f349f40e1bcce8d7e3c5970ebcf5897f75df868070c784e602269518ae84
+oid sha256:6c574d8e30f2e864e475983c48bb1a9c31a25076b753f0104a850af3cf991200
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d4ae3842d5f151f968dca77e1398d806e7ccbbb71022d80233230f6c7d83bcb
+oid sha256:9567f2f3182e832808fd621212e0dd5e8f1a88bd24ddda3ea0d289496073738c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7120001316070557,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.036603221083455345,
+  "best_metric": 0.6729180812835693,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07320644216691069,
   "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": 3.716,
       "eval_steps_per_second": 1.858,
       "step": 25
+    },
+    {
+      "epoch": 0.03806734992679356,
+      "grad_norm": 0.9075884819030762,
+      "learning_rate": 0.00017684011108568592,
+      "loss": 0.7545,
+      "step": 26
+    },
+    {
+      "epoch": 0.03953147877013177,
+      "grad_norm": 0.8508671522140503,
+      "learning_rate": 0.0001746821476984154,
+      "loss": 0.6666,
+      "step": 27
+    },
+    {
+      "epoch": 0.040995607613469986,
+      "grad_norm": 0.830573558807373,
+      "learning_rate": 0.00017244252047910892,
+      "loss": 0.696,
+      "step": 28
+    },
+    {
+      "epoch": 0.0424597364568082,
+      "grad_norm": 0.816193163394928,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.7688,
+      "step": 29
+    },
+    {
+      "epoch": 0.043923865300146414,
+      "grad_norm": 0.9093814492225647,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.6717,
+      "step": 30
+    },
+    {
+      "epoch": 0.04538799414348463,
+      "grad_norm": 0.8094978332519531,
+      "learning_rate": 0.00016525857615241687,
+      "loss": 0.588,
+      "step": 31
+    },
+    {
+      "epoch": 0.04685212298682284,
+      "grad_norm": 0.8796850442886353,
+      "learning_rate": 0.0001627176358473537,
+      "loss": 0.7133,
+      "step": 32
+    },
+    {
+      "epoch": 0.048316251830161056,
+      "grad_norm": 0.9510671496391296,
+      "learning_rate": 0.00016010811472830252,
+      "loss": 0.6754,
+      "step": 33
+    },
+    {
+      "epoch": 0.04978038067349927,
+      "grad_norm": 0.9171980023384094,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 0.665,
+      "step": 34
+    },
+    {
+      "epoch": 0.05124450951683748,
+      "grad_norm": 0.9319704174995422,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.6215,
+      "step": 35
+    },
+    {
+      "epoch": 0.0527086383601757,
+      "grad_norm": 0.9619579911231995,
+      "learning_rate": 0.00015189695737812152,
+      "loss": 0.7145,
+      "step": 36
+    },
+    {
+      "epoch": 0.05417276720351391,
+      "grad_norm": 0.8880752921104431,
+      "learning_rate": 0.00014904235038305083,
+      "loss": 0.6216,
+      "step": 37
+    },
+    {
+      "epoch": 0.055636896046852125,
+      "grad_norm": 0.9341321587562561,
+      "learning_rate": 0.0001461341162978688,
+      "loss": 0.7046,
+      "step": 38
+    },
+    {
+      "epoch": 0.05710102489019034,
+      "grad_norm": 0.8551350235939026,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 0.6551,
+      "step": 39
+    },
+    {
+      "epoch": 0.05856515373352855,
+      "grad_norm": 0.9286485314369202,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.6471,
+      "step": 40
+    },
+    {
+      "epoch": 0.060029282576866766,
+      "grad_norm": 0.8776522278785706,
+      "learning_rate": 0.00013711972489182208,
+      "loss": 0.6324,
+      "step": 41
+    },
+    {
+      "epoch": 0.06149341142020498,
+      "grad_norm": 0.859512984752655,
+      "learning_rate": 0.00013402931744416433,
+      "loss": 0.6475,
+      "step": 42
+    },
+    {
+      "epoch": 0.0629575402635432,
+      "grad_norm": 0.8624581694602966,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6477,
+      "step": 43
+    },
+    {
+      "epoch": 0.06442166910688141,
+      "grad_norm": 0.8696426749229431,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 0.6571,
+      "step": 44
+    },
+    {
+      "epoch": 0.06588579795021962,
+      "grad_norm": 0.8606180548667908,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.6489,
+      "step": 45
+    },
+    {
+      "epoch": 0.06734992679355783,
+      "grad_norm": 0.8928582668304443,
+      "learning_rate": 0.0001213299630743747,
+      "loss": 0.6775,
+      "step": 46
+    },
+    {
+      "epoch": 0.06881405563689605,
+      "grad_norm": 0.9211382865905762,
+      "learning_rate": 0.000118088053433211,
+      "loss": 0.5962,
+      "step": 47
+    },
+    {
+      "epoch": 0.07027818448023426,
+      "grad_norm": 0.9554921388626099,
+      "learning_rate": 0.0001148263647711842,
+      "loss": 0.6437,
+      "step": 48
+    },
+    {
+      "epoch": 0.07174231332357248,
+      "grad_norm": 0.9748461842536926,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 0.6481,
+      "step": 49
+    },
+    {
+      "epoch": 0.07320644216691069,
+      "grad_norm": 1.0362958908081055,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.6812,
+      "step": 50
+    },
+    {
+      "epoch": 0.07320644216691069,
+      "eval_loss": 0.6729180812835693,
+      "eval_runtime": 77.5069,
+      "eval_samples_per_second": 3.716,
+      "eval_steps_per_second": 1.858,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.00529829052416e+16,
+  "total_flos": 2.01059658104832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null