Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1078cb85a0f469d4ba3d10e751c6044e23ce27b5556f0954af6601462deb2eec
+oid sha256:8bf8fbacf15b0f6581427170661b0453f23cd1762fef3ad413b6cdd7f5f49150
 size 2436967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eab91ef8102c0d692e2c01df5511b610a008414c64a0f0393492901460e17b7
+oid sha256:5dd7cdb9fd62e58c62a40b256c81a497aaf3df3d6502d7ddaa2c13ab8fa1cc63
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2780fe85f0d0574cda938e12a493f5e0ef79b9161e81f812178dc5aa242a24a
+oid sha256:5306bec7e4ed725fe7ce44761ff835d1ff3dffcc86bc7a6c129b0a4e7563b5c3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de12f3707159b46b04cf6db45bee5391047993e2f839108995ab0ead4d74eb9e
+oid sha256:1a40e81596ee843c610a19d87cc96bea2d3ee9f2b65cc025f00c521fcaa625f1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f8239b22106d88f90ddab75b9370c265c6c82145cd24140facafd2f7147bbc6
+oid sha256:8cb7257fac9e2ff4bd972e7ed6ac4a95a04337aac5971d908674aa126f371fbd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f30cfddcac4a641c12f25010b1dc657f46d5d743766d03120c3cc4322fe7e25d
+oid sha256:2f0eb798428a03b17136d0b073b1ff22469bdb6f4f00f82f72a96b8b0d8dd56e
 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": 4.011327743530273,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06817794443497528,
+  "best_metric": 3.913165807723999,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.13635588886995056,
   "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": 30.106,
       "eval_steps_per_second": 3.766,
       "step": 25
+    },
+    {
+      "epoch": 0.0709050622123743,
+      "grad_norm": 2.2828495502471924,
+      "learning_rate": 5e-05,
+      "loss": 3.9172,
+      "step": 26
+    },
+    {
+      "epoch": 0.07363217998977331,
+      "grad_norm": 2.7300260066986084,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 4.0181,
+      "step": 27
+    },
+    {
+      "epoch": 0.07635929776717232,
+      "grad_norm": 2.9719653129577637,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 4.0165,
+      "step": 28
+    },
+    {
+      "epoch": 0.07908641554457133,
+      "grad_norm": 2.9800491333007812,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.8962,
+      "step": 29
+    },
+    {
+      "epoch": 0.08181353332197035,
+      "grad_norm": 2.593806266784668,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.9558,
+      "step": 30
+    },
+    {
+      "epoch": 0.08454065109936935,
+      "grad_norm": 2.301185131072998,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.9558,
+      "step": 31
+    },
+    {
+      "epoch": 0.08726776887676836,
+      "grad_norm": 2.195345878601074,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.897,
+      "step": 32
+    },
+    {
+      "epoch": 0.08999488665416738,
+      "grad_norm": 1.9010220766067505,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.9487,
+      "step": 33
+    },
+    {
+      "epoch": 0.09272200443156639,
+      "grad_norm": 2.0472588539123535,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.121,
+      "step": 34
+    },
+    {
+      "epoch": 0.0954491222089654,
+      "grad_norm": 2.0967180728912354,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.9512,
+      "step": 35
+    },
+    {
+      "epoch": 0.0981762399863644,
+      "grad_norm": 2.0463292598724365,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.0246,
+      "step": 36
+    },
+    {
+      "epoch": 0.10090335776376343,
+      "grad_norm": 2.5716755390167236,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.1409,
+      "step": 37
+    },
+    {
+      "epoch": 0.10363047554116243,
+      "grad_norm": 1.0110124349594116,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.745,
+      "step": 38
+    },
+    {
+      "epoch": 0.10635759331856144,
+      "grad_norm": 1.0488909482955933,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.7371,
+      "step": 39
+    },
+    {
+      "epoch": 0.10908471109596046,
+      "grad_norm": 0.9047977328300476,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.8171,
+      "step": 40
+    },
+    {
+      "epoch": 0.11181182887335947,
+      "grad_norm": 0.9148534536361694,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.7319,
+      "step": 41
+    },
+    {
+      "epoch": 0.11453894665075848,
+      "grad_norm": 1.192430853843689,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.8528,
+      "step": 42
+    },
+    {
+      "epoch": 0.11726606442815748,
+      "grad_norm": 1.1312968730926514,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.8156,
+      "step": 43
+    },
+    {
+      "epoch": 0.1199931822055565,
+      "grad_norm": 0.9511891603469849,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.894,
+      "step": 44
+    },
+    {
+      "epoch": 0.12272029998295551,
+      "grad_norm": 1.1418358087539673,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.7971,
+      "step": 45
+    },
+    {
+      "epoch": 0.12544741776035453,
+      "grad_norm": 1.1028140783309937,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.8487,
+      "step": 46
+    },
+    {
+      "epoch": 0.12817453553775354,
+      "grad_norm": 1.3050944805145264,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.8828,
+      "step": 47
+    },
+    {
+      "epoch": 0.13090165331515255,
+      "grad_norm": 1.4526429176330566,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.8323,
+      "step": 48
+    },
+    {
+      "epoch": 0.13362877109255156,
+      "grad_norm": 1.9823384284973145,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.9885,
+      "step": 49
+    },
+    {
+      "epoch": 0.13635588886995056,
+      "grad_norm": 4.876001834869385,
+      "learning_rate": 0.0,
+      "loss": 4.1589,
+      "step": 50
+    },
+    {
+      "epoch": 0.13635588886995056,
+      "eval_loss": 3.913165807723999,
+      "eval_runtime": 82.0402,
+      "eval_samples_per_second": 30.107,
+      "eval_steps_per_second": 3.766,
+      "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": 2.984043419271168e+17,
+  "total_flos": 5.968086838542336e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null