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:e9235766a18e479f9a35c7611e83f422e41025626ccc6cb13c1fc03b78c0836b
+oid sha256:18270d208d8f61121396d8e5b25615637de45ddcddfcfc616d50944f6f270a13
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d570b8b1198be4e82722c07237a7960a959cb5852f64c827113479fce02d14ba
+oid sha256:ed513f23c7bae5797d2f01701e5b5eb5837352508f4cc09707c493a636f0953c
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2613a8f18853e4bc3fb1f6ba26e4f841daea64179af069a6be8168e3ef81242
+oid sha256:5d7da9f8eb0f74e4519942681a855a193aa78c4de8c952f53f1896e79be8ff6b
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50004b902a9563dfe9559870ba1766c496e7d547cdf381cd4792d6aeda1bb467
+oid sha256:a0f66d7bf4544c04d1e3485b54ee3402fd9ec98957330ab95dbbcacf6a1ac716
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce7966901b9c5e1966bd052e273642ff8b138baffd477a79b88c5d1f9cb9391
+oid sha256:8f3a083329c0ae3c035806e77888bbe0e664e4cdf0e4dc837ca7a307aeded52e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59d37fcf34a978fbfc00896a7c31d04bc803b06fd2d73e7daad4ec8f053d025f
+oid sha256:679251cddc48640ddefa9eb4b6db83a5c1bc213921c170fcc85fd57fdde74e2c
 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": 2.044109582901001,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.3114754098360657,
+  "best_metric": 2.0400946140289307,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.6229508196721314,
   "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": 10.556,
       "eval_steps_per_second": 2.744,
       "step": 25
+    },
+    {
+      "epoch": 1.3639344262295081,
+      "grad_norm": 7.692803859710693,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 30.9557,
+      "step": 26
+    },
+    {
+      "epoch": 1.4163934426229507,
+      "grad_norm": 7.772709369659424,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 31.432,
+      "step": 27
+    },
+    {
+      "epoch": 1.4688524590163934,
+      "grad_norm": 9.130861282348633,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 32.0877,
+      "step": 28
+    },
+    {
+      "epoch": 1.521311475409836,
+      "grad_norm": 10.832189559936523,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 31.0261,
+      "step": 29
+    },
+    {
+      "epoch": 1.5737704918032787,
+      "grad_norm": 8.154661178588867,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 30.5008,
+      "step": 30
+    },
+    {
+      "epoch": 1.6262295081967213,
+      "grad_norm": 8.400430679321289,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 31.3353,
+      "step": 31
+    },
+    {
+      "epoch": 1.678688524590164,
+      "grad_norm": 8.89877700805664,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 30.9697,
+      "step": 32
+    },
+    {
+      "epoch": 1.7311475409836066,
+      "grad_norm": 9.605426788330078,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 32.3451,
+      "step": 33
+    },
+    {
+      "epoch": 1.7836065573770492,
+      "grad_norm": 12.887454986572266,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 30.6939,
+      "step": 34
+    },
+    {
+      "epoch": 1.8360655737704918,
+      "grad_norm": 8.313308715820312,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 30.9625,
+      "step": 35
+    },
+    {
+      "epoch": 1.8885245901639345,
+      "grad_norm": 9.007829666137695,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 31.2103,
+      "step": 36
+    },
+    {
+      "epoch": 1.940983606557377,
+      "grad_norm": 8.962111473083496,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 31.4604,
+      "step": 37
+    },
+    {
+      "epoch": 1.9934426229508198,
+      "grad_norm": 11.267090797424316,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 32.3345,
+      "step": 38
+    },
+    {
+      "epoch": 2.045901639344262,
+      "grad_norm": 9.0362548828125,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 29.2781,
+      "step": 39
+    },
+    {
+      "epoch": 2.098360655737705,
+      "grad_norm": 7.795830249786377,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 29.9757,
+      "step": 40
+    },
+    {
+      "epoch": 2.1508196721311474,
+      "grad_norm": 8.447335243225098,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 30.0933,
+      "step": 41
+    },
+    {
+      "epoch": 2.2032786885245903,
+      "grad_norm": 9.279709815979004,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 29.6093,
+      "step": 42
+    },
+    {
+      "epoch": 2.2557377049180327,
+      "grad_norm": 11.038886070251465,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 30.4997,
+      "step": 43
+    },
+    {
+      "epoch": 2.3081967213114756,
+      "grad_norm": 8.14568042755127,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 29.6179,
+      "step": 44
+    },
+    {
+      "epoch": 2.360655737704918,
+      "grad_norm": 8.41407299041748,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 29.772,
+      "step": 45
+    },
+    {
+      "epoch": 2.413114754098361,
+      "grad_norm": 9.197470664978027,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 29.093,
+      "step": 46
+    },
+    {
+      "epoch": 2.4655737704918033,
+      "grad_norm": 10.19188404083252,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 30.6495,
+      "step": 47
+    },
+    {
+      "epoch": 2.5180327868852457,
+      "grad_norm": 13.069672584533691,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 30.3433,
+      "step": 48
+    },
+    {
+      "epoch": 2.5704918032786885,
+      "grad_norm": 8.42982006072998,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 29.7666,
+      "step": 49
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "grad_norm": 9.083083152770996,
+      "learning_rate": 1e-05,
+      "loss": 30.3737,
+      "step": 50
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "eval_loss": 2.0400946140289307,
+      "eval_runtime": 4.7581,
+      "eval_samples_per_second": 10.508,
+      "eval_steps_per_second": 2.732,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null