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:e54bc9dc3362f8f5580bf78337985c522f0af0c6ddcde6a26e85c68beee93b6f
+oid sha256:0e0b11a979d278cd185e38fd06a1c4bcc5b9d2be8f9c57b4838af5d2b55c702b
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27a2e2df24ed77f254797f02f69ab213f814b1d05b109edfb66c6f6d282cc40c
+oid sha256:5b22809f3d97c508a1b402ca9edd85270c1ba52bd9da6a1e000959afb3ba09ba
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b11a9b8b5e49a15428b17603d656692fa62c99109f993518c15db14cb753609
+oid sha256:d694e21b6cc85047400680dffd2aae59e81bc693a406d97374cd034ded33506b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e611eadac6469da9fec173147518c8c798a8c6a89a6bf22ec269b0fef2889384
+oid sha256:f3fbda9c3d5a48c1412117b19424b3371348fef42c2f9af57cf16d942b4bd7b5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8338465b5fc9b7dab643fa71608845f79269ebbf697b94ba40c5dbea72dc24f7
+oid sha256:aec668fa8fd5177a84abfd6543642c1c754636a362a6a739684f5f8904a05ef5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1f6a8c2417f8dbea4464b636e3b7cbb2716ba1a46261c10bcf8a75ff4f1a404
+oid sha256:6c38248b28313f524c1184bd58846d0bf9c602d1a475d0107ae1f7e944748c4e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.197417736053467,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0594000594000594,
+  "best_metric": 3.993185520172119,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1188001188001188,
   "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": 107.934,
       "eval_steps_per_second": 28.063,
       "step": 25
+    },
+    {
+      "epoch": 0.06177606177606178,
+      "grad_norm": 5.812683582305908,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 3.9788,
+      "step": 26
+    },
+    {
+      "epoch": 0.06415206415206415,
+      "grad_norm": 5.340697288513184,
+      "learning_rate": 7.75e-05,
+      "loss": 4.1852,
+      "step": 27
+    },
+    {
+      "epoch": 0.06652806652806653,
+      "grad_norm": 5.233508586883545,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 4.0927,
+      "step": 28
+    },
+    {
+      "epoch": 0.0689040689040689,
+      "grad_norm": 4.724637985229492,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 4.184,
+      "step": 29
+    },
+    {
+      "epoch": 0.07128007128007129,
+      "grad_norm": 3.7798030376434326,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 3.9799,
+      "step": 30
+    },
+    {
+      "epoch": 0.07365607365607366,
+      "grad_norm": 3.1549389362335205,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 4.0357,
+      "step": 31
+    },
+    {
+      "epoch": 0.07603207603207603,
+      "grad_norm": 2.810375213623047,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 4.2323,
+      "step": 32
+    },
+    {
+      "epoch": 0.07840807840807841,
+      "grad_norm": 2.2946324348449707,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 4.1228,
+      "step": 33
+    },
+    {
+      "epoch": 0.08078408078408078,
+      "grad_norm": 2.794386386871338,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 4.3795,
+      "step": 34
+    },
+    {
+      "epoch": 0.08316008316008316,
+      "grad_norm": 2.846055507659912,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 4.338,
+      "step": 35
+    },
+    {
+      "epoch": 0.08553608553608553,
+      "grad_norm": 3.5053131580352783,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 4.6534,
+      "step": 36
+    },
+    {
+      "epoch": 0.08791208791208792,
+      "grad_norm": 4.065090179443359,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 4.7563,
+      "step": 37
+    },
+    {
+      "epoch": 0.09028809028809029,
+      "grad_norm": 2.289839744567871,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 4.1748,
+      "step": 38
+    },
+    {
+      "epoch": 0.09266409266409266,
+      "grad_norm": 2.2016358375549316,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.8301,
+      "step": 39
+    },
+    {
+      "epoch": 0.09504009504009504,
+      "grad_norm": 2.1572742462158203,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 3.8959,
+      "step": 40
+    },
+    {
+      "epoch": 0.09741609741609741,
+      "grad_norm": 2.1548614501953125,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 4.0368,
+      "step": 41
+    },
+    {
+      "epoch": 0.0997920997920998,
+      "grad_norm": 1.97099769115448,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.8731,
+      "step": 42
+    },
+    {
+      "epoch": 0.10216810216810217,
+      "grad_norm": 1.972032904624939,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 4.0455,
+      "step": 43
+    },
+    {
+      "epoch": 0.10454410454410454,
+      "grad_norm": 2.277165412902832,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 4.0799,
+      "step": 44
+    },
+    {
+      "epoch": 0.10692010692010692,
+      "grad_norm": 2.229562997817993,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.2358,
+      "step": 45
+    },
+    {
+      "epoch": 0.10929610929610929,
+      "grad_norm": 2.1845741271972656,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 4.1261,
+      "step": 46
+    },
+    {
+      "epoch": 0.11167211167211168,
+      "grad_norm": 2.513690948486328,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 4.249,
+      "step": 47
+    },
+    {
+      "epoch": 0.11404811404811405,
+      "grad_norm": 2.7216529846191406,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.3592,
+      "step": 48
+    },
+    {
+      "epoch": 0.11642411642411643,
+      "grad_norm": 2.8171885013580322,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 4.59,
+      "step": 49
+    },
+    {
+      "epoch": 0.1188001188001188,
+      "grad_norm": 4.377580165863037,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 5.0176,
+      "step": 50
+    },
+    {
+      "epoch": 0.1188001188001188,
+      "eval_loss": 3.993185520172119,
+      "eval_runtime": 0.463,
+      "eval_samples_per_second": 107.981,
+      "eval_steps_per_second": 28.075,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null