Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f1b0643be8562be910d169975142bdeff515de188402eb2a4c0bff627786abd
+oid sha256:131387fc3a4bd8eb037b6f0b290e27ac4a798ccb50d50d1ff5c0c5c0bc5dbdb1
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0cdcfb2dc2d43fca6e70ad10521393af2e24b1281a974d4409e5ae6934e29ad
+oid sha256:212f99a27d4e3f01058e85ba86629d693100f463952641958e74745c9698a400
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dbaa96bf7278ecbefad4fe38c5db9d553c3754d433af7837889caa38b8fcb17
+oid sha256:19591a304aac7d7535112192df1b4c5e4867287fbe3c20b6fecc3da3829533ad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00e81896bf9d01601a3815cbc63d03bc32d99aaca916684b7f901b5e1baa823f
+oid sha256:030a317538443820a14c10695860ece0e18a9a3ddabf1a9b3f34a7d74a7be704
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e5da4e2a861828eb1d469335e9830692edc493406bdc6756a074a1b7504ef7
+oid sha256:b36bd23e5994bdff5b78c96b245e0356fb6c5babdd62fbd59eaefc94fb1ea331
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a8de1b9947f50c950738459585478fe17cee95f5e696fa085559a324c1a711d
+oid sha256:93b01fad80336293ef5000c6f654625366cf22f8693f4f942b9bc5cb7e49da7c
 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": 4.893651008605957,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05375621556242441,
+  "best_metric": 4.476396560668945,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10751243112484882,
   "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": 34.615,
       "eval_steps_per_second": 9.0,
       "step": 25
+    },
+    {
+      "epoch": 0.05590646418492138,
+      "grad_norm": 6.720362186431885,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.8796,
+      "step": 26
+    },
+    {
+      "epoch": 0.05805671280741836,
+      "grad_norm": 6.6319499015808105,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.8505,
+      "step": 27
+    },
+    {
+      "epoch": 0.060206961429915336,
+      "grad_norm": 6.37089729309082,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.8001,
+      "step": 28
+    },
+    {
+      "epoch": 0.06235721005241231,
+      "grad_norm": 5.236145496368408,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.7555,
+      "step": 29
+    },
+    {
+      "epoch": 0.06450745867490928,
+      "grad_norm": 4.066835403442383,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.5387,
+      "step": 30
+    },
+    {
+      "epoch": 0.06665770729740626,
+      "grad_norm": 2.819272041320801,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.6675,
+      "step": 31
+    },
+    {
+      "epoch": 0.06880795591990324,
+      "grad_norm": 1.8012014627456665,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.5881,
+      "step": 32
+    },
+    {
+      "epoch": 0.07095820454240022,
+      "grad_norm": 1.616188645362854,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.4681,
+      "step": 33
+    },
+    {
+      "epoch": 0.0731084531648972,
+      "grad_norm": 1.6810884475708008,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.4601,
+      "step": 34
+    },
+    {
+      "epoch": 0.07525870178739416,
+      "grad_norm": 2.0555830001831055,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.5417,
+      "step": 35
+    },
+    {
+      "epoch": 0.07740895040989114,
+      "grad_norm": 2.8344008922576904,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.7851,
+      "step": 36
+    },
+    {
+      "epoch": 0.07955919903238812,
+      "grad_norm": 3.864741325378418,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.9669,
+      "step": 37
+    },
+    {
+      "epoch": 0.0817094476548851,
+      "grad_norm": 1.7793840169906616,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.6599,
+      "step": 38
+    },
+    {
+      "epoch": 0.08385969627738207,
+      "grad_norm": 1.3759382963180542,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.2021,
+      "step": 39
+    },
+    {
+      "epoch": 0.08600994489987905,
+      "grad_norm": 1.3663908243179321,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.4005,
+      "step": 40
+    },
+    {
+      "epoch": 0.08816019352237603,
+      "grad_norm": 1.2785991430282593,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 4.2243,
+      "step": 41
+    },
+    {
+      "epoch": 0.09031044214487301,
+      "grad_norm": 1.2903536558151245,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 4.4202,
+      "step": 42
+    },
+    {
+      "epoch": 0.09246069076736997,
+      "grad_norm": 1.398136019706726,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.377,
+      "step": 43
+    },
+    {
+      "epoch": 0.09461093938986695,
+      "grad_norm": 1.6057686805725098,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.4098,
+      "step": 44
+    },
+    {
+      "epoch": 0.09676118801236393,
+      "grad_norm": 1.499598503112793,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.4333,
+      "step": 45
+    },
+    {
+      "epoch": 0.0989114366348609,
+      "grad_norm": 1.7191181182861328,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.3681,
+      "step": 46
+    },
+    {
+      "epoch": 0.10106168525735788,
+      "grad_norm": 1.7606230974197388,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.3406,
+      "step": 47
+    },
+    {
+      "epoch": 0.10321193387985486,
+      "grad_norm": 2.182579755783081,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.4751,
+      "step": 48
+    },
+    {
+      "epoch": 0.10536218250235184,
+      "grad_norm": 2.8871469497680664,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.6591,
+      "step": 49
+    },
+    {
+      "epoch": 0.10751243112484882,
+      "grad_norm": 4.577729225158691,
+      "learning_rate": 1e-05,
+      "loss": 5.0534,
+      "step": 50
+    },
+    {
+      "epoch": 0.10751243112484882,
+      "eval_loss": 4.476396560668945,
+      "eval_runtime": 1.4456,
+      "eval_samples_per_second": 34.589,
+      "eval_steps_per_second": 8.993,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null