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:fd8b3a9f68428d4817a0611506395d4d73cb549e0d5774fe44b16d9a57119a4e
+oid sha256:219347134e9bdd74a1472ab189770b8743a7714a552d2e9139ec488d1a2c8935
 size 2436967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0e21db34542e99e6c0dbefb2d5358e555396b6c2cc47fbaa06e18e7d60783f9
+oid sha256:d34c9fcca82afd4e85fe1cede95d9b32d038cac8cef5de3ae12983edbe43e7bc
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:250fac0481afeca9564cc785af64705a1a0073025c50afffac2ba138110fa5cb
+oid sha256:2c2572a8a03e5d689f02af1451d1c5ca7c60301095af061a82420a7f5aeb9f20
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf1eac1c56706269cbaf420bc150d99af3d7c59e4465a24cc03a08356d6ccd1b
+oid sha256:1096d6c92360329110b3330409e7ab40ea40fc787fea5f920f5e1c27ef617e20
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9c3ee880c60d81b45bcf3798558d68637dc71377bae9be667e736c9753956de
+oid sha256:b47fb0ef0b76b0ec55148efb904951b04e98ae0b59ed21d9df2314e12208331e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb14c8e901ec85d3a53c149e66ef6c281bdd2dba4ca1cfbe62fa319f866eb16f
+oid sha256:a6497a5322d8fbaaefe3155f9ca4e7469c110fd5be9e9e0e4a5e32b91b540778
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.085999011993408,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0648403306856865,
+  "best_metric": 3.9628827571868896,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.129680661371373,
   "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": 21.478,
       "eval_steps_per_second": 5.584,
       "step": 25
+    },
+    {
+      "epoch": 0.06743394391311396,
+      "grad_norm": 2.760413408279419,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.963,
+      "step": 26
+    },
+    {
+      "epoch": 0.07002755714054142,
+      "grad_norm": 3.3028481006622314,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.0512,
+      "step": 27
+    },
+    {
+      "epoch": 0.07262117036796888,
+      "grad_norm": 3.695802927017212,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.9918,
+      "step": 28
+    },
+    {
+      "epoch": 0.07521478359539634,
+      "grad_norm": 3.3420543670654297,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.0709,
+      "step": 29
+    },
+    {
+      "epoch": 0.0778083968228238,
+      "grad_norm": 2.8132102489471436,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.936,
+      "step": 30
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 2.410557270050049,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.8944,
+      "step": 31
+    },
+    {
+      "epoch": 0.08299562327767872,
+      "grad_norm": 1.9881235361099243,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.9089,
+      "step": 32
+    },
+    {
+      "epoch": 0.08558923650510618,
+      "grad_norm": 1.8629140853881836,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.8896,
+      "step": 33
+    },
+    {
+      "epoch": 0.08818284973253364,
+      "grad_norm": 1.81000554561615,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.9437,
+      "step": 34
+    },
+    {
+      "epoch": 0.0907764629599611,
+      "grad_norm": 1.6936609745025635,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.9741,
+      "step": 35
+    },
+    {
+      "epoch": 0.09337007618738856,
+      "grad_norm": 2.0665626525878906,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.1504,
+      "step": 36
+    },
+    {
+      "epoch": 0.09596368941481602,
+      "grad_norm": 2.5222113132476807,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.0006,
+      "step": 37
+    },
+    {
+      "epoch": 0.09855730264224348,
+      "grad_norm": 1.097839593887329,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.7587,
+      "step": 38
+    },
+    {
+      "epoch": 0.10115091586967094,
+      "grad_norm": 0.9856619238853455,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.7098,
+      "step": 39
+    },
+    {
+      "epoch": 0.1037445290970984,
+      "grad_norm": 0.9252366423606873,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.7605,
+      "step": 40
+    },
+    {
+      "epoch": 0.10633814232452586,
+      "grad_norm": 0.8420267105102539,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.6713,
+      "step": 41
+    },
+    {
+      "epoch": 0.10893175555195332,
+      "grad_norm": 0.8332710862159729,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.7245,
+      "step": 42
+    },
+    {
+      "epoch": 0.11152536877938077,
+      "grad_norm": 0.8014082312583923,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.8029,
+      "step": 43
+    },
+    {
+      "epoch": 0.11411898200680823,
+      "grad_norm": 0.8639490008354187,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.9165,
+      "step": 44
+    },
+    {
+      "epoch": 0.11671259523423569,
+      "grad_norm": 0.9951760172843933,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.8803,
+      "step": 45
+    },
+    {
+      "epoch": 0.11930620846166315,
+      "grad_norm": 1.2074276208877563,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.8738,
+      "step": 46
+    },
+    {
+      "epoch": 0.12189982168909061,
+      "grad_norm": 1.2788665294647217,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.0534,
+      "step": 47
+    },
+    {
+      "epoch": 0.12449343491651807,
+      "grad_norm": 1.6001139879226685,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.9496,
+      "step": 48
+    },
+    {
+      "epoch": 0.12708704814394553,
+      "grad_norm": 2.474669933319092,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.0053,
+      "step": 49
+    },
+    {
+      "epoch": 0.129680661371373,
+      "grad_norm": 5.6437201499938965,
+      "learning_rate": 1e-05,
+      "loss": 4.2376,
+      "step": 50
+    },
+    {
+      "epoch": 0.129680661371373,
+      "eval_loss": 3.9628827571868896,
+      "eval_runtime": 2.3228,
+      "eval_samples_per_second": 21.526,
+      "eval_steps_per_second": 5.597,
+      "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": 2.984043419271168e+17,
+  "total_flos": 5.968086838542336e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null