Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73d6956cdba0a96d8054b18e7639349be2fb15597d580f3cb67a31747b3f8d18
+oid sha256:46be7a31595c201454556404cb2db625c070b2fb49b0830deff3ae5d0ac4e4fa
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5391d0096ab0fd1e0fd19e8566f6d940749066f2c2af27a735ae42bc9466536
+oid sha256:3fb02ac8b29f945a86f4b84822b7853a006158a547a44b2dd5bf701944103325
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6141fc894019c9de557508d134249fd60d6bf4ba3890b968117c2f1835e64ca2
+oid sha256:6c8f2cd7bc52682dea58fb7482fcdc339d16e7a6adac224fb7d3f20f0b785e05
 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": 0.38313478231430054,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0005028890978672474,
+  "best_metric": 0.380575567483902,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0010057781957344947,
   "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": 3.507,
       "eval_steps_per_second": 1.753,
       "step": 25
+    },
+    {
+      "epoch": 0.0005230046617819373,
+      "grad_norm": 1.2087231874465942,
+      "learning_rate": 0.00017684011108568592,
+      "loss": 0.3541,
+      "step": 26
+    },
+    {
+      "epoch": 0.0005431202256966271,
+      "grad_norm": 0.7510756254196167,
+      "learning_rate": 0.0001746821476984154,
+      "loss": 0.2474,
+      "step": 27
+    },
+    {
+      "epoch": 0.000563235789611317,
+      "grad_norm": 0.9615175127983093,
+      "learning_rate": 0.00017244252047910892,
+      "loss": 0.4285,
+      "step": 28
+    },
+    {
+      "epoch": 0.0005833513535260069,
+      "grad_norm": 1.6521743535995483,
+      "learning_rate": 0.00017012367842724887,
+      "loss": 0.5122,
+      "step": 29
+    },
+    {
+      "epoch": 0.0006034669174406969,
+      "grad_norm": 1.0975160598754883,
+      "learning_rate": 0.00016772815716257412,
+      "loss": 0.4345,
+      "step": 30
+    },
+    {
+      "epoch": 0.0006235824813553867,
+      "grad_norm": 1.332993984222412,
+      "learning_rate": 0.00016525857615241687,
+      "loss": 0.1814,
+      "step": 31
+    },
+    {
+      "epoch": 0.0006436980452700766,
+      "grad_norm": 2.3052821159362793,
+      "learning_rate": 0.0001627176358473537,
+      "loss": 0.764,
+      "step": 32
+    },
+    {
+      "epoch": 0.0006638136091847665,
+      "grad_norm": 1.9049065113067627,
+      "learning_rate": 0.00016010811472830252,
+      "loss": 0.5676,
+      "step": 33
+    },
+    {
+      "epoch": 0.0006839291730994564,
+      "grad_norm": 1.4157077074050903,
+      "learning_rate": 0.00015743286626829437,
+      "loss": 0.2885,
+      "step": 34
+    },
+    {
+      "epoch": 0.0007040447370141462,
+      "grad_norm": 1.8599406480789185,
+      "learning_rate": 0.00015469481581224272,
+      "loss": 0.5417,
+      "step": 35
+    },
+    {
+      "epoch": 0.0007241603009288362,
+      "grad_norm": 0.757952094078064,
+      "learning_rate": 0.00015189695737812152,
+      "loss": 0.2253,
+      "step": 36
+    },
+    {
+      "epoch": 0.0007442758648435261,
+      "grad_norm": 1.1078306436538696,
+      "learning_rate": 0.00014904235038305083,
+      "loss": 0.1614,
+      "step": 37
+    },
+    {
+      "epoch": 0.000764391428758216,
+      "grad_norm": 1.2288084030151367,
+      "learning_rate": 0.0001461341162978688,
+      "loss": 0.2767,
+      "step": 38
+    },
+    {
+      "epoch": 0.0007845069926729058,
+      "grad_norm": 0.7424066066741943,
+      "learning_rate": 0.00014317543523384928,
+      "loss": 0.1715,
+      "step": 39
+    },
+    {
+      "epoch": 0.0008046225565875957,
+      "grad_norm": 1.009460210800171,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.2123,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008247381205022857,
+      "grad_norm": 1.8544470071792603,
+      "learning_rate": 0.00013711972489182208,
+      "loss": 0.7898,
+      "step": 41
+    },
+    {
+      "epoch": 0.0008448536844169756,
+      "grad_norm": 1.8500866889953613,
+      "learning_rate": 0.00013402931744416433,
+      "loss": 0.4095,
+      "step": 42
+    },
+    {
+      "epoch": 0.0008649692483316654,
+      "grad_norm": 2.287600517272949,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6513,
+      "step": 43
+    },
+    {
+      "epoch": 0.0008850848122463553,
+      "grad_norm": 0.6950022578239441,
+      "learning_rate": 0.00012774029087618446,
+      "loss": 0.098,
+      "step": 44
+    },
+    {
+      "epoch": 0.0009052003761610452,
+      "grad_norm": 1.1519097089767456,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.3887,
+      "step": 45
+    },
+    {
+      "epoch": 0.0009253159400757352,
+      "grad_norm": 1.9645311832427979,
+      "learning_rate": 0.0001213299630743747,
+      "loss": 0.5686,
+      "step": 46
+    },
+    {
+      "epoch": 0.000945431503990425,
+      "grad_norm": 2.0428481101989746,
+      "learning_rate": 0.000118088053433211,
+      "loss": 0.5198,
+      "step": 47
+    },
+    {
+      "epoch": 0.0009655470679051149,
+      "grad_norm": 1.8423922061920166,
+      "learning_rate": 0.0001148263647711842,
+      "loss": 0.528,
+      "step": 48
+    },
+    {
+      "epoch": 0.0009856626318198048,
+      "grad_norm": 3.1978683471679688,
+      "learning_rate": 0.00011154846369695863,
+      "loss": 0.4476,
+      "step": 49
+    },
+    {
+      "epoch": 0.0010057781957344947,
+      "grad_norm": 2.396751642227173,
+      "learning_rate": 0.00010825793454723325,
+      "loss": 0.6431,
+      "step": 50
+    },
+    {
+      "epoch": 0.0010057781957344947,
+      "eval_loss": 0.380575567483902,
+      "eval_runtime": 5967.1284,
+      "eval_samples_per_second": 3.508,
+      "eval_steps_per_second": 1.754,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.746530781980262e+16,
+  "total_flos": 7.455967199782502e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null