Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cc793a228bafa992eb2996af80e0eccc6db12a7c441137829670994eb41633a
+oid sha256:11a10b084ec886e9d497dec268349595565820a69da6b3bc0f2157a26106f7f4
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:facd36a7a8c045976ffaedd33e97d9f2c252f66c11550db159d4c3a6b4971001
+oid sha256:df8c8a82f2ba9098f581ddd29074ad8d4180aced7f567cec4321b37dc733ebaf
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6822ffc8570fb511b5c4c757ad326229cfde5cc71b2a212e4a304fd58cf4fde5
+oid sha256:dda33db27aa0c877d9bd756f4675ef45dea6b8fb80ad23a4c6003c3d86e24885
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ed38589fa900f00061f2b2b1c3568cfd451b3d56d9884a66a9416b8e5ca1986
+oid sha256:83576a6e35db7c4740f01251705f98bc9f70d52a8d4704ed43c2fbd546a51a0b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05ea9e920ea0062f553c0b9db562336b611a85a1c2f05d19272e872cef7c0386
+oid sha256:d938cd3645531d99aef50f05b793ae6073b3b079520e94db6ed1f408bc5d844d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41a1abc766f0aba7667247e5cec910e5d08e3f995946090e456b3a70951d57a8
+oid sha256:3a7033a392b90eaacd77ba41dfe4e75bd2f1c68cb6e4f25e391293c272a3e7a6
 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": 0.22289028763771057,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5908419497784343,
+  "best_metric": 0.1706855595111847,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1816838995568686,
   "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": 49.479,
       "eval_steps_per_second": 6.228,
       "step": 25
+    },
+    {
+      "epoch": 0.6144756277695717,
+      "grad_norm": 1.3822792768478394,
+      "learning_rate": 5e-05,
+      "loss": 0.2117,
+      "step": 26
+    },
+    {
+      "epoch": 0.638109305760709,
+      "grad_norm": 0.7628507614135742,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1982,
+      "step": 27
+    },
+    {
+      "epoch": 0.6617429837518464,
+      "grad_norm": 0.6021902561187744,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1994,
+      "step": 28
+    },
+    {
+      "epoch": 0.6853766617429837,
+      "grad_norm": 0.9015952944755554,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2243,
+      "step": 29
+    },
+    {
+      "epoch": 0.7090103397341211,
+      "grad_norm": 1.0857808589935303,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2062,
+      "step": 30
+    },
+    {
+      "epoch": 0.7326440177252584,
+      "grad_norm": 0.8910597562789917,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1585,
+      "step": 31
+    },
+    {
+      "epoch": 0.7562776957163959,
+      "grad_norm": 2.153136730194092,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.1872,
+      "step": 32
+    },
+    {
+      "epoch": 0.7799113737075333,
+      "grad_norm": 2.040679693222046,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1527,
+      "step": 33
+    },
+    {
+      "epoch": 0.8035450516986706,
+      "grad_norm": 4.356012344360352,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2195,
+      "step": 34
+    },
+    {
+      "epoch": 0.827178729689808,
+      "grad_norm": 2.1332600116729736,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2126,
+      "step": 35
+    },
+    {
+      "epoch": 0.8508124076809453,
+      "grad_norm": 1.7389914989471436,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2404,
+      "step": 36
+    },
+    {
+      "epoch": 0.8744460856720827,
+      "grad_norm": 3.6628377437591553,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2148,
+      "step": 37
+    },
+    {
+      "epoch": 0.8980797636632201,
+      "grad_norm": 5.675159454345703,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2503,
+      "step": 38
+    },
+    {
+      "epoch": 0.9217134416543574,
+      "grad_norm": 5.330775260925293,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2351,
+      "step": 39
+    },
+    {
+      "epoch": 0.9453471196454948,
+      "grad_norm": 4.94797420501709,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2219,
+      "step": 40
+    },
+    {
+      "epoch": 0.9689807976366323,
+      "grad_norm": 3.37272047996521,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2225,
+      "step": 41
+    },
+    {
+      "epoch": 0.9926144756277696,
+      "grad_norm": 2.723189115524292,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.179,
+      "step": 42
+    },
+    {
+      "epoch": 1.016248153618907,
+      "grad_norm": 2.4876487255096436,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2768,
+      "step": 43
+    },
+    {
+      "epoch": 1.0398818316100442,
+      "grad_norm": 1.6984374523162842,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1719,
+      "step": 44
+    },
+    {
+      "epoch": 1.0635155096011817,
+      "grad_norm": 2.616401195526123,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1488,
+      "step": 45
+    },
+    {
+      "epoch": 1.0871491875923192,
+      "grad_norm": 1.1589338779449463,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1614,
+      "step": 46
+    },
+    {
+      "epoch": 1.1107828655834564,
+      "grad_norm": 2.8123533725738525,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1689,
+      "step": 47
+    },
+    {
+      "epoch": 1.1344165435745939,
+      "grad_norm": 0.8784838318824768,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2094,
+      "step": 48
+    },
+    {
+      "epoch": 1.1580502215657311,
+      "grad_norm": 2.1387734413146973,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1802,
+      "step": 49
+    },
+    {
+      "epoch": 1.1816838995568686,
+      "grad_norm": 3.335361957550049,
+      "learning_rate": 0.0,
+      "loss": 0.1699,
+      "step": 50
+    },
+    {
+      "epoch": 1.1816838995568686,
+      "eval_loss": 0.1706855595111847,
+      "eval_runtime": 5.7689,
+      "eval_samples_per_second": 49.576,
+      "eval_steps_per_second": 6.24,
+      "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": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null