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:a4701c754c8739efaede54d1c4293272f5d623375ef19940c0615888d3aeeedc
+oid sha256:e0882b03481e8798c80992ec491be3db32cde612950d3d2ac3104a128dd3cc8d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea2d4c3e9a5f5823f0c47ddedc958795af715f2311467df928f136db0725468
+oid sha256:a340dbaeb0ef87e03a944bb13ea77345fdbc41691409d59a03ec60c4889ce4ee
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:817931efad9f290099676a90ea933db1f9f8de07a0915d1c71b4a6677cdad515
+oid sha256:69840105536fe0a1015af896335d8d7348244e9cde47f1c1e97facd075fb1016
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4367bf62aa3fb9d7268bf5b527ebc1a9a019cfa7a6543c8efe42be467b67b6ba
+oid sha256:1b8eee0e5e46ccc6b54faeb9228b5bad2bded0fc69fb853f788165f16952f8be
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00da0f763556c9d6c474ec1472c1abf2cc5a52a73eedfefcdecd01abc4554fa5
+oid sha256:00fdee056f12a420727962f590ab1cdfc7410d9548566e2c40e6d1a14cbcf25a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f557f19a6fb5546d2c6afe3e506c6cb906cfc9ed901beafb5f3a4da15adfb4f
+oid sha256:8c48eda64ae4bf36b07c0212af4b9e4ce821548e538b85258e4f634115a121e7
 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": 3.398573398590088,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03415300546448088,
+  "best_metric": 3.2531516551971436,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06830601092896176,
   "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": 14.431,
       "eval_steps_per_second": 3.752,
       "step": 25
+    },
+    {
+      "epoch": 0.03551912568306011,
+      "grad_norm": 1.455446720123291,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.3439,
+      "step": 26
+    },
+    {
+      "epoch": 0.036885245901639344,
+      "grad_norm": 2.329031467437744,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.9435,
+      "step": 27
+    },
+    {
+      "epoch": 0.03825136612021858,
+      "grad_norm": 2.5059032440185547,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.9663,
+      "step": 28
+    },
+    {
+      "epoch": 0.03961748633879782,
+      "grad_norm": 1.9605844020843506,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.1745,
+      "step": 29
+    },
+    {
+      "epoch": 0.040983606557377046,
+      "grad_norm": 1.597434163093567,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.3009,
+      "step": 30
+    },
+    {
+      "epoch": 0.04234972677595628,
+      "grad_norm": 1.3100905418395996,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.3497,
+      "step": 31
+    },
+    {
+      "epoch": 0.04371584699453552,
+      "grad_norm": 1.4777722358703613,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.3907,
+      "step": 32
+    },
+    {
+      "epoch": 0.045081967213114756,
+      "grad_norm": 1.580230712890625,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.6009,
+      "step": 33
+    },
+    {
+      "epoch": 0.04644808743169399,
+      "grad_norm": 1.8173338174819946,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.4578,
+      "step": 34
+    },
+    {
+      "epoch": 0.04781420765027322,
+      "grad_norm": 2.1014060974121094,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.507,
+      "step": 35
+    },
+    {
+      "epoch": 0.04918032786885246,
+      "grad_norm": 2.4913907051086426,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.7169,
+      "step": 36
+    },
+    {
+      "epoch": 0.050546448087431695,
+      "grad_norm": 2.769925594329834,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.0094,
+      "step": 37
+    },
+    {
+      "epoch": 0.05191256830601093,
+      "grad_norm": 0.6865216493606567,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.4872,
+      "step": 38
+    },
+    {
+      "epoch": 0.05327868852459016,
+      "grad_norm": 0.6267939805984497,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.6732,
+      "step": 39
+    },
+    {
+      "epoch": 0.0546448087431694,
+      "grad_norm": 0.74587482213974,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.8649,
+      "step": 40
+    },
+    {
+      "epoch": 0.056010928961748634,
+      "grad_norm": 0.9323634505271912,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.1053,
+      "step": 41
+    },
+    {
+      "epoch": 0.05737704918032787,
+      "grad_norm": 0.9466826915740967,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.1002,
+      "step": 42
+    },
+    {
+      "epoch": 0.05874316939890711,
+      "grad_norm": 0.9597004652023315,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.0931,
+      "step": 43
+    },
+    {
+      "epoch": 0.060109289617486336,
+      "grad_norm": 1.058807134628296,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.2562,
+      "step": 44
+    },
+    {
+      "epoch": 0.06147540983606557,
+      "grad_norm": 1.2648183107376099,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.4148,
+      "step": 45
+    },
+    {
+      "epoch": 0.06284153005464481,
+      "grad_norm": 1.4772535562515259,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.44,
+      "step": 46
+    },
+    {
+      "epoch": 0.06420765027322405,
+      "grad_norm": 1.4803715944290161,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.658,
+      "step": 47
+    },
+    {
+      "epoch": 0.06557377049180328,
+      "grad_norm": 1.6075665950775146,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.5905,
+      "step": 48
+    },
+    {
+      "epoch": 0.06693989071038252,
+      "grad_norm": 1.932875156402588,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.6877,
+      "step": 49
+    },
+    {
+      "epoch": 0.06830601092896176,
+      "grad_norm": 3.3861000537872314,
+      "learning_rate": 1e-05,
+      "loss": 4.0972,
+      "step": 50
+    },
+    {
+      "epoch": 0.06830601092896176,
+      "eval_loss": 3.2531516551971436,
+      "eval_runtime": 3.4586,
+      "eval_samples_per_second": 14.457,
+      "eval_steps_per_second": 3.759,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.971813667564421e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null