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:fbb6eac7c5b17d5fce7ed66c5c08dc66201fdf652fe9c701596cd9ab2d3dc763
+oid sha256:377b1fbbfaa25f282314c83ce463792127bdee488761b595c7c8cb1c167b4223
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759815889ca50fbaf35666c86356a21ca718c345c275edc85a814d2e82f125bc
+oid sha256:1488dbac244a862581d2cee8f8478ce87f7110d56387d0047c0d4d56eea47381
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9731b3dd62edc8cea23640953ecd34462aa59304fd31a2c490f01467c52517b3
+oid sha256:789af1fadd7325e21a1f339c2907c07e6520d027501803b6300ea0bbd7cdf5ed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c5f3882c3117be254d04ef783d04874159fba4211f2558cf16ef830e3b94f9b
+oid sha256:f918aba8194691e1c1fdb5da97ac40c28ae1e349544108a5c636fbd6be88b041
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b417426e7db42c89957ed8d514b7614ad02822933582f53261292b00c77796f
+oid sha256:d5f7f07ddddd17b9cc6eb581fba52145e0b02c3c2c7c57169be90b3b20d990a0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb8d9a881d74d66c77a7a0e6aba59fbded6f3e6b7cc8e60b4964b543974c4d66
+oid sha256:815a6d51d8e4d88e3f5fc96b6fedab9f70c2a72541ad348e4618ccdab25d4917
 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": 1.8553268909454346,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.29673590504451036,
+  "best_metric": 1.8252456188201904,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5934718100890207,
   "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": 87.461,
       "eval_steps_per_second": 10.933,
       "step": 25
+    },
+    {
+      "epoch": 0.3086053412462908,
+      "grad_norm": 0.6685218811035156,
+      "learning_rate": 5e-05,
+      "loss": 1.8927,
+      "step": 26
+    },
+    {
+      "epoch": 0.32047477744807124,
+      "grad_norm": 0.6507945656776428,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.8866,
+      "step": 27
+    },
+    {
+      "epoch": 0.3323442136498516,
+      "grad_norm": 0.637917697429657,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.8561,
+      "step": 28
+    },
+    {
+      "epoch": 0.34421364985163205,
+      "grad_norm": 0.5948305130004883,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.7897,
+      "step": 29
+    },
+    {
+      "epoch": 0.3560830860534125,
+      "grad_norm": 0.49185270071029663,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.8109,
+      "step": 30
+    },
+    {
+      "epoch": 0.36795252225519287,
+      "grad_norm": 0.43624943494796753,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.8639,
+      "step": 31
+    },
+    {
+      "epoch": 0.3798219584569733,
+      "grad_norm": 0.38713496923446655,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8508,
+      "step": 32
+    },
+    {
+      "epoch": 0.3916913946587537,
+      "grad_norm": 0.38741055130958557,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.8357,
+      "step": 33
+    },
+    {
+      "epoch": 0.4035608308605341,
+      "grad_norm": 0.40148451924324036,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.7832,
+      "step": 34
+    },
+    {
+      "epoch": 0.41543026706231456,
+      "grad_norm": 0.4694264531135559,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8257,
+      "step": 35
+    },
+    {
+      "epoch": 0.42729970326409494,
+      "grad_norm": 0.49596676230430603,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8726,
+      "step": 36
+    },
+    {
+      "epoch": 0.4391691394658754,
+      "grad_norm": 0.6188309192657471,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.826,
+      "step": 37
+    },
+    {
+      "epoch": 0.45103857566765576,
+      "grad_norm": 0.3719251751899719,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8437,
+      "step": 38
+    },
+    {
+      "epoch": 0.4629080118694362,
+      "grad_norm": 0.3250787556171417,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.8298,
+      "step": 39
+    },
+    {
+      "epoch": 0.47477744807121663,
+      "grad_norm": 0.3276398181915283,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.7952,
+      "step": 40
+    },
+    {
+      "epoch": 0.486646884272997,
+      "grad_norm": 0.33880218863487244,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.7894,
+      "step": 41
+    },
+    {
+      "epoch": 0.49851632047477745,
+      "grad_norm": 0.3426777720451355,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.8094,
+      "step": 42
+    },
+    {
+      "epoch": 0.5103857566765578,
+      "grad_norm": 0.3449629843235016,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.8138,
+      "step": 43
+    },
+    {
+      "epoch": 0.5222551928783383,
+      "grad_norm": 0.3571850061416626,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7878,
+      "step": 44
+    },
+    {
+      "epoch": 0.5341246290801187,
+      "grad_norm": 0.38788995146751404,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.7721,
+      "step": 45
+    },
+    {
+      "epoch": 0.5459940652818991,
+      "grad_norm": 0.3872774541378021,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.7995,
+      "step": 46
+    },
+    {
+      "epoch": 0.5578635014836796,
+      "grad_norm": 0.42015138268470764,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.8377,
+      "step": 47
+    },
+    {
+      "epoch": 0.56973293768546,
+      "grad_norm": 0.4835258424282074,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8335,
+      "step": 48
+    },
+    {
+      "epoch": 0.5816023738872403,
+      "grad_norm": 0.5363931059837341,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.8543,
+      "step": 49
+    },
+    {
+      "epoch": 0.5934718100890207,
+      "grad_norm": 0.6558699011802673,
+      "learning_rate": 0.0,
+      "loss": 1.8785,
+      "step": 50
+    },
+    {
+      "epoch": 0.5934718100890207,
+      "eval_loss": 1.8252456188201904,
+      "eval_runtime": 6.4997,
+      "eval_samples_per_second": 87.388,
+      "eval_steps_per_second": 10.924,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null