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:aad6de7a247cb79896c9ae51048d2d6fe7445679cbe2cc1bdf79a4876491cd61
+oid sha256:1845f1144bbe8e5ed1cddf70abd1df6fef5148b1a2c87611f564f23b64e86ff3
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d3f81b08d1bc948e0f4c188eb4de90a6abdcfb59248231f503ea3ba6784567f
+oid sha256:186c68a8f7c83374e396e26491347e4e70b9ef1f0fdea0c0b606f8caa9f8cb7a
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85a343c50b5474118c70ed4d0e43377639b1abf39eba9c3d5e53523d331bb555
+oid sha256:b53e97a9b5d7a02f9bdf6804203b1ec7c3d0ec59bf7e09245bab653f77a80ddc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:734f7a3888628100b572d51325707a0de7773ecfedc6050d8a3104b4820ab9cb
+oid sha256:f1edc1f327ec20ac57d978bff78e378b8bc92154f141026200ed8c59a5547184
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28bcea9d7fbf60a1f0d7a6f0b954a8c79fd8299b99e3e647fb7080ff14a9b7fa
+oid sha256:833e8619bb9e7b4a3e58a5b4e3b610b2f559ea59215de822347ecb865f1c44b3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a00f268d86e415ae5571a600fe5e36df85c76e10b216dec1a66a76c96a577e6
+oid sha256:ab9cafefb1d534d2c0c8adb48cf3154941feaa0a4bb7b073e8892ee10492f2ed
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.007557204458862543,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01678345151680443,
+  "best_metric": 0.005274961236864328,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03356690303360886,
   "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": 48.184,
       "eval_steps_per_second": 6.026,
       "step": 25
+    },
+    {
+      "epoch": 0.017454789577476607,
+      "grad_norm": 0.05196339637041092,
+      "learning_rate": 5e-05,
+      "loss": 0.0026,
+      "step": 26
+    },
+    {
+      "epoch": 0.018126127638148786,
+      "grad_norm": 0.05076891928911209,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0036,
+      "step": 27
+    },
+    {
+      "epoch": 0.018797465698820962,
+      "grad_norm": 0.05824902653694153,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0039,
+      "step": 28
+    },
+    {
+      "epoch": 0.01946880375949314,
+      "grad_norm": 0.05391624569892883,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.004,
+      "step": 29
+    },
+    {
+      "epoch": 0.020140141820165318,
+      "grad_norm": 0.09434299916028976,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0046,
+      "step": 30
+    },
+    {
+      "epoch": 0.020811479880837494,
+      "grad_norm": 0.08576031774282455,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0062,
+      "step": 31
+    },
+    {
+      "epoch": 0.02148281794150967,
+      "grad_norm": 0.06679359078407288,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0039,
+      "step": 32
+    },
+    {
+      "epoch": 0.02215415600218185,
+      "grad_norm": 0.08394492417573929,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0077,
+      "step": 33
+    },
+    {
+      "epoch": 0.022825494062854026,
+      "grad_norm": 0.07740284502506256,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.007,
+      "step": 34
+    },
+    {
+      "epoch": 0.023496832123526202,
+      "grad_norm": 0.07654044032096863,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0088,
+      "step": 35
+    },
+    {
+      "epoch": 0.02416817018419838,
+      "grad_norm": 0.07540926337242126,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.006,
+      "step": 36
+    },
+    {
+      "epoch": 0.024839508244870558,
+      "grad_norm": 0.13866406679153442,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0108,
+      "step": 37
+    },
+    {
+      "epoch": 0.025510846305542734,
+      "grad_norm": 0.029844947159290314,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.003,
+      "step": 38
+    },
+    {
+      "epoch": 0.026182184366214913,
+      "grad_norm": 0.02928406558930874,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0016,
+      "step": 39
+    },
+    {
+      "epoch": 0.02685352242688709,
+      "grad_norm": 0.03697742521762848,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0025,
+      "step": 40
+    },
+    {
+      "epoch": 0.027524860487559265,
+      "grad_norm": 0.028026431798934937,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0033,
+      "step": 41
+    },
+    {
+      "epoch": 0.028196198548231445,
+      "grad_norm": 0.034609757363796234,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.002,
+      "step": 42
+    },
+    {
+      "epoch": 0.02886753660890362,
+      "grad_norm": 0.037386205047369,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0036,
+      "step": 43
+    },
+    {
+      "epoch": 0.029538874669575797,
+      "grad_norm": 0.04624997451901436,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0041,
+      "step": 44
+    },
+    {
+      "epoch": 0.030210212730247977,
+      "grad_norm": 0.04912189394235611,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0037,
+      "step": 45
+    },
+    {
+      "epoch": 0.030881550790920153,
+      "grad_norm": 0.05287240073084831,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0044,
+      "step": 46
+    },
+    {
+      "epoch": 0.03155288885159233,
+      "grad_norm": 0.05969248712062836,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0054,
+      "step": 47
+    },
+    {
+      "epoch": 0.03222422691226451,
+      "grad_norm": 0.08090845495462418,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0065,
+      "step": 48
+    },
+    {
+      "epoch": 0.032895564972936685,
+      "grad_norm": 0.10718454420566559,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.011,
+      "step": 49
+    },
+    {
+      "epoch": 0.03356690303360886,
+      "grad_norm": 0.1893693208694458,
+      "learning_rate": 0.0,
+      "loss": 0.016,
+      "step": 50
+    },
+    {
+      "epoch": 0.03356690303360886,
+      "eval_loss": 0.005274961236864328,
+      "eval_runtime": 208.0854,
+      "eval_samples_per_second": 48.225,
+      "eval_steps_per_second": 6.031,
+      "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": 5.310925972176896e+16,
+  "total_flos": 1.062516298832937e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null