Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07274795946a624dce9de8e01fea007766299eaf12b142cc6666c24783e3d52e
+oid sha256:c0298eeda0548eea281cfea3c8c3075c0d05db4649782c41ca44eaa086e0748a
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4970ed6a01d1dd8dc5336322170385f5fed45098c5a32b45866b81f263708cf2
+oid sha256:e48a0f9093f4f0bb05a856f2803b9c2c4037f28b1f783854e348e7aed58a6f2f
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e121c9aff9ad65f34924278511c609e470e97e96c34ce4594a18e80db212ae82
+oid sha256:774bbb6f5e19fdaacb870e4fda89c4f21487ef83d435974c414bf1a2e23564cb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f88bc0faeb4b9a7b67d92c85713098b52c49e06daf848f5ffd5627b3badff05b
+oid sha256:0cc94d33882e7cb16e88c2fc198780d8ef0c58a4fb26696464ebc42958a319f0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:300383c63c14da0e90c5829e8840301d1b6b61947c7334b6c5594ddcf9c12b58
+oid sha256:0486b51353b445f96170329d0fa6e3f1f56fdecaa676ffb862c6d2e97bacd494
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c36338eabc7e98868eb6036beb50d63c13e54b0ec66d823ef3635c2c29c9d1f
+oid sha256:4232480544fe015087d1e6db4b0a1a69d9e37096dcffae52701223b93c1859a9
 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": 11.716475486755371,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009897315353210442,
+  "best_metric": 11.688956260681152,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.019794630706420884,
   "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": 313.955,
       "eval_steps_per_second": 81.628,
       "step": 25
+    },
+    {
+      "epoch": 0.010293207967338859,
+      "grad_norm": 0.9336376786231995,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.7377,
+      "step": 26
+    },
+    {
+      "epoch": 0.010689100581467277,
+      "grad_norm": 0.9597164988517761,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.7309,
+      "step": 27
+    },
+    {
+      "epoch": 0.011084993195595695,
+      "grad_norm": 0.9862052798271179,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7275,
+      "step": 28
+    },
+    {
+      "epoch": 0.011480885809724112,
+      "grad_norm": 0.9398750066757202,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.7179,
+      "step": 29
+    },
+    {
+      "epoch": 0.01187677842385253,
+      "grad_norm": 0.9106470346450806,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.7238,
+      "step": 30
+    },
+    {
+      "epoch": 0.012272671037980947,
+      "grad_norm": 0.9347615242004395,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.7057,
+      "step": 31
+    },
+    {
+      "epoch": 0.012668563652109366,
+      "grad_norm": 0.8774538636207581,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.6895,
+      "step": 32
+    },
+    {
+      "epoch": 0.013064456266237782,
+      "grad_norm": 0.9370536208152771,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.6945,
+      "step": 33
+    },
+    {
+      "epoch": 0.0134603488803662,
+      "grad_norm": 0.9235231876373291,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.6921,
+      "step": 34
+    },
+    {
+      "epoch": 0.013856241494494619,
+      "grad_norm": 0.9303660988807678,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.6912,
+      "step": 35
+    },
+    {
+      "epoch": 0.014252134108623036,
+      "grad_norm": 0.8900956511497498,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.6827,
+      "step": 36
+    },
+    {
+      "epoch": 0.014648026722751454,
+      "grad_norm": 1.000619649887085,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.6509,
+      "step": 37
+    },
+    {
+      "epoch": 0.01504391933687987,
+      "grad_norm": 0.9968812465667725,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.6788,
+      "step": 38
+    },
+    {
+      "epoch": 0.015439811951008289,
+      "grad_norm": 0.9819913506507874,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.7155,
+      "step": 39
+    },
+    {
+      "epoch": 0.015835704565136707,
+      "grad_norm": 1.0137593746185303,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.7058,
+      "step": 40
+    },
+    {
+      "epoch": 0.016231597179265124,
+      "grad_norm": 0.9970508813858032,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.6978,
+      "step": 41
+    },
+    {
+      "epoch": 0.01662748979339354,
+      "grad_norm": 1.027045726776123,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.7046,
+      "step": 42
+    },
+    {
+      "epoch": 0.01702338240752196,
+      "grad_norm": 0.8774479627609253,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.6764,
+      "step": 43
+    },
+    {
+      "epoch": 0.017419275021650377,
+      "grad_norm": 0.9244899153709412,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.6821,
+      "step": 44
+    },
+    {
+      "epoch": 0.017815167635778794,
+      "grad_norm": 0.9668672680854797,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.6844,
+      "step": 45
+    },
+    {
+      "epoch": 0.018211060249907214,
+      "grad_norm": 0.9782124161720276,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.6838,
+      "step": 46
+    },
+    {
+      "epoch": 0.01860695286403563,
+      "grad_norm": 0.9850881099700928,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.6841,
+      "step": 47
+    },
+    {
+      "epoch": 0.019002845478164047,
+      "grad_norm": 0.9748925566673279,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.6842,
+      "step": 48
+    },
+    {
+      "epoch": 0.019398738092292464,
+      "grad_norm": 0.9819056987762451,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.6558,
+      "step": 49
+    },
+    {
+      "epoch": 0.019794630706420884,
+      "grad_norm": 1.0381964445114136,
+      "learning_rate": 1e-05,
+      "loss": 11.6251,
+      "step": 50
+    },
+    {
+      "epoch": 0.019794630706420884,
+      "eval_loss": 11.688956260681152,
+      "eval_runtime": 0.1594,
+      "eval_samples_per_second": 313.714,
+      "eval_steps_per_second": 81.566,
+      "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": 81943068672000.0,
+  "total_flos": 163886137344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null