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:ec61617354a292c5da975848f2418944d7b94ce08c7a22f1ff5b43e03190456e
+oid sha256:8a0ca05cbf37f6d59e4e85bff985be816b6edcf278c5642cd8ea89c70fdec3a4
 size 2436967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f03857430b6e9f5f89505b94bbc9494a2ad7ad603093928681f0264edb6593eb
+oid sha256:7786932a736761d66e8e010fa289e5b8d4909fb7c5e40dab2dcb9e13d0e101f5
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9f0761595d066037c2ae9ad82c6eccf286dbfdd9788a8103cd45a1a2e55d19e
+oid sha256:2670892202706f3c366e9c22f04d59513c2e3e52151669fda82c03146b98010f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0794f47fb4f98f83d7ef77dd5377b18c25e41000c65a03ebff31a82101236b9
+oid sha256:28d733e45c38afdeec0123ed2d75ad97977deb99070bafb40d0b1a57fa6df366
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb931128c5e0b61efa0fce1c8447b3a602766b778a3bfece90137a37b22913e
+oid sha256:fcfb75b1fa9fad441bae349ffc51dd7a47f5ad5098410ad94b45ddefc7b7bdb3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c52840d1e749d25cdf876af3b63190c309f0f68f8e5088b261a10e3898d2ff
+oid sha256:bc2b769bfbeef367ae4b51b28d8d3f407c87ae48240eb23ef9282582cd762827
 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": 4.0869059562683105,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0648403306856865,
+  "best_metric": 3.968430519104004,
+  "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": 13.151,
       "eval_steps_per_second": 3.419,
       "step": 25
+    },
+    {
+      "epoch": 0.06743394391311396,
+      "grad_norm": 3.166818141937256,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.9683,
+      "step": 26
+    },
+    {
+      "epoch": 0.07002755714054142,
+      "grad_norm": 3.9245522022247314,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.0797,
+      "step": 27
+    },
+    {
+      "epoch": 0.07262117036796888,
+      "grad_norm": 4.480504512786865,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.0345,
+      "step": 28
+    },
+    {
+      "epoch": 0.07521478359539634,
+      "grad_norm": 4.088141918182373,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.1171,
+      "step": 29
+    },
+    {
+      "epoch": 0.0778083968228238,
+      "grad_norm": 3.5814590454101562,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.9815,
+      "step": 30
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 2.991044282913208,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.9307,
+      "step": 31
+    },
+    {
+      "epoch": 0.08299562327767872,
+      "grad_norm": 2.4383318424224854,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.9331,
+      "step": 32
+    },
+    {
+      "epoch": 0.08558923650510618,
+      "grad_norm": 2.0898032188415527,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.9062,
+      "step": 33
+    },
+    {
+      "epoch": 0.08818284973253364,
+      "grad_norm": 1.9938257932662964,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.9457,
+      "step": 34
+    },
+    {
+      "epoch": 0.0907764629599611,
+      "grad_norm": 1.678131341934204,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.9616,
+      "step": 35
+    },
+    {
+      "epoch": 0.09337007618738856,
+      "grad_norm": 2.003936767578125,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.1226,
+      "step": 36
+    },
+    {
+      "epoch": 0.09596368941481602,
+      "grad_norm": 2.3786985874176025,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.9693,
+      "step": 37
+    },
+    {
+      "epoch": 0.09855730264224348,
+      "grad_norm": 1.0126866102218628,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.7566,
+      "step": 38
+    },
+    {
+      "epoch": 0.10115091586967094,
+      "grad_norm": 1.0450958013534546,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.7173,
+      "step": 39
+    },
+    {
+      "epoch": 0.1037445290970984,
+      "grad_norm": 0.9659586548805237,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.7651,
+      "step": 40
+    },
+    {
+      "epoch": 0.10633814232452586,
+      "grad_norm": 0.9066281914710999,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.6723,
+      "step": 41
+    },
+    {
+      "epoch": 0.10893175555195332,
+      "grad_norm": 0.8197788000106812,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.7228,
+      "step": 42
+    },
+    {
+      "epoch": 0.11152536877938077,
+      "grad_norm": 0.8055732250213623,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.8006,
+      "step": 43
+    },
+    {
+      "epoch": 0.11411898200680823,
+      "grad_norm": 0.9053921699523926,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.9203,
+      "step": 44
+    },
+    {
+      "epoch": 0.11671259523423569,
+      "grad_norm": 1.1126152276992798,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.8764,
+      "step": 45
+    },
+    {
+      "epoch": 0.11930620846166315,
+      "grad_norm": 1.1534708738327026,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.872,
+      "step": 46
+    },
+    {
+      "epoch": 0.12189982168909061,
+      "grad_norm": 1.4054807424545288,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.0488,
+      "step": 47
+    },
+    {
+      "epoch": 0.12449343491651807,
+      "grad_norm": 1.6983075141906738,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.9535,
+      "step": 48
+    },
+    {
+      "epoch": 0.12708704814394553,
+      "grad_norm": 2.652462959289551,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.0065,
+      "step": 49
+    },
+    {
+      "epoch": 0.129680661371373,
+      "grad_norm": 6.116709232330322,
+      "learning_rate": 1e-05,
+      "loss": 4.2401,
+      "step": 50
+    },
+    {
+      "epoch": 0.129680661371373,
+      "eval_loss": 3.968430519104004,
+      "eval_runtime": 3.7754,
+      "eval_samples_per_second": 13.244,
+      "eval_steps_per_second": 3.443,
+      "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