Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22b96cedeed92cd602432f1a68bb7ec166fe0edc4ca2248a0858d8fa0dcd0c35
+oid sha256:4bb13233ed4b1bad2a544c76be13c829d504e8a654ed44b451778ab1a69a3e93
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbe34bb336108b632381e1e86d3bf265ffb3bfd57add45079a9e544d37bf56da
+oid sha256:5818a8104e86471848c2935015d45ceb0cf4e07a5b3bd90a378c22b4099d4ca0
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77105301d7bd3e0c485399b32e9db462b80cc2c045c27a413e1e87a10aaa3b7
+oid sha256:800cd6381775c04667f5929a3cc01183a00855045f4fd80e5816d6d369a4d89b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c9abd6ebc4968158db608544b3314fa7bf896cf9c473464f326766d992eb1ab
+oid sha256:173c72cfb3534a4523764d9d89fafab6f146c5cfb4ce3ccab4de6306964c01e1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5648385907a88d24cf1fdfd7fc7f25b1252cc2e0af320d3e11259da8a8a9971
+oid sha256:af0de59b797c2a4e6dc6961fb8d484cc0623da08c2d74acb818203bdc9fe4ccb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33c5607b8314316db0b5d3973e1526b2c0e60666fb71503e8db1602dab4e1ff8
+oid sha256:5214c4144fe725cdc5a3831d121239b55f5946c3664ca6aa279b1ae78a0780d1
 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": 6.922487258911133,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.63441712926249,
+  "best_metric": 6.91412353515625,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.26883425852498,
   "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": 429.492,
       "eval_steps_per_second": 111.668,
       "step": 25
+    },
+    {
+      "epoch": 0.6597938144329897,
+      "grad_norm": 0.2449556142091751,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.9239,
+      "step": 26
+    },
+    {
+      "epoch": 0.6851704996034893,
+      "grad_norm": 0.30131685733795166,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 6.9162,
+      "step": 27
+    },
+    {
+      "epoch": 0.7105471847739889,
+      "grad_norm": 0.32581567764282227,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.914,
+      "step": 28
+    },
+    {
+      "epoch": 0.7359238699444886,
+      "grad_norm": 0.32971295714378357,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.9164,
+      "step": 29
+    },
+    {
+      "epoch": 0.7613005551149881,
+      "grad_norm": 0.617648720741272,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.877,
+      "step": 30
+    },
+    {
+      "epoch": 0.7866772402854877,
+      "grad_norm": 0.6868042349815369,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 6.8734,
+      "step": 31
+    },
+    {
+      "epoch": 0.8120539254559873,
+      "grad_norm": 0.3134247362613678,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 6.9059,
+      "step": 32
+    },
+    {
+      "epoch": 0.8374306106264869,
+      "grad_norm": 0.2802397608757019,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.9128,
+      "step": 33
+    },
+    {
+      "epoch": 0.8628072957969866,
+      "grad_norm": 0.2617209851741791,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.9152,
+      "step": 34
+    },
+    {
+      "epoch": 0.8881839809674861,
+      "grad_norm": 0.23401491343975067,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.9297,
+      "step": 35
+    },
+    {
+      "epoch": 0.9135606661379857,
+      "grad_norm": 0.3026781976222992,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.9084,
+      "step": 36
+    },
+    {
+      "epoch": 0.9389373513084853,
+      "grad_norm": 0.29526880383491516,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.9079,
+      "step": 37
+    },
+    {
+      "epoch": 0.964314036478985,
+      "grad_norm": 0.34165528416633606,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 6.9084,
+      "step": 38
+    },
+    {
+      "epoch": 0.9896907216494846,
+      "grad_norm": 0.31630247831344604,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.9171,
+      "step": 39
+    },
+    {
+      "epoch": 1.015067406819984,
+      "grad_norm": 0.6814719438552856,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.9955,
+      "step": 40
+    },
+    {
+      "epoch": 1.0404440919904838,
+      "grad_norm": 0.6847633123397827,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.8728,
+      "step": 41
+    },
+    {
+      "epoch": 1.0658207771609833,
+      "grad_norm": 0.4051920473575592,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.7039,
+      "step": 42
+    },
+    {
+      "epoch": 1.0911974623314828,
+      "grad_norm": 0.3018025755882263,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 7.3555,
+      "step": 43
+    },
+    {
+      "epoch": 1.1165741475019826,
+      "grad_norm": 0.2783207595348358,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.7517,
+      "step": 44
+    },
+    {
+      "epoch": 1.141950832672482,
+      "grad_norm": 0.21331705152988434,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 6.6381,
+      "step": 45
+    },
+    {
+      "epoch": 1.1673275178429818,
+      "grad_norm": 0.2783212661743164,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 7.109,
+      "step": 46
+    },
+    {
+      "epoch": 1.1927042030134813,
+      "grad_norm": 0.2744676172733307,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.6019,
+      "step": 47
+    },
+    {
+      "epoch": 1.218080888183981,
+      "grad_norm": 0.3599938750267029,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 7.6122,
+      "step": 48
+    },
+    {
+      "epoch": 1.2434575733544806,
+      "grad_norm": 0.2515687644481659,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 5.8057,
+      "step": 49
+    },
+    {
+      "epoch": 1.26883425852498,
+      "grad_norm": 0.7015694975852966,
+      "learning_rate": 1e-05,
+      "loss": 7.5716,
+      "step": 50
+    },
+    {
+      "epoch": 1.26883425852498,
+      "eval_loss": 6.91412353515625,
+      "eval_runtime": 0.1195,
+      "eval_samples_per_second": 418.264,
+      "eval_steps_per_second": 108.749,
+      "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": 2852978688000.0,
+  "total_flos": 5705957376000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null