Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c6578c3e058749e6b509cd906c2b26486dcff6335e354ce05e053e210ca302f
+oid sha256:113e04bbfbc35eb620e63b885898c9d33b653dd53c2bc0ab1e96e0367a6f2848
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:456398cfd81708a92eec9b2d29fb13bc51885582d9b8e2de58ae244525543010
+oid sha256:ef9685d40e03ad4733c113500a8b31d4e613e4b8e34739df0ead9e9950461b29
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:471fd9cace8c99cd422e841ef6c2f27ac31bdc167a7afff42a774033143986ab
+oid sha256:e84ac23b6fe95f5e8146180db1089fe59bc459b01a299fd90a32b32865823f09
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:605206fdf722c59250949bb7b28f17581d50a97979b9d9c9dafbc1374317a8a0
+oid sha256:22b316c90c06f326a16a8fec40f7309e92b0d5fcd0b08a2f03ce35051a0b4814
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b759af88f8d6ce1f9ce1201d87f2fee5e2100ab28ddfd6b2d205c0ad2ed5740
+oid sha256:cc2fb260d319d15d0d562e2984501a4daec76cedafeffe8a3caf740925b62f25
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d04576e82d1c294601f014dcb823e38bda147ace7afe51e574c9d81654f20ad
+oid sha256:004da3107113de1e9dea0d1823cd91f4612a94e6f21cc862e2481640f60d8fcc
 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": 6.922355651855469,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.0810810810810811,
+  "best_metric": 6.917191028594971,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.1621621621621623,
   "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": 1190.662,
       "eval_steps_per_second": 152.649,
       "step": 25
+    },
+    {
+      "epoch": 1.1243243243243244,
+      "grad_norm": 0.14169707894325256,
+      "learning_rate": 5e-05,
+      "loss": 6.9437,
+      "step": 26
+    },
+    {
+      "epoch": 1.1675675675675676,
+      "grad_norm": 0.15641377866268158,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 6.9905,
+      "step": 27
+    },
+    {
+      "epoch": 1.2108108108108109,
+      "grad_norm": 0.1642267405986786,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 6.8949,
+      "step": 28
+    },
+    {
+      "epoch": 1.2540540540540541,
+      "grad_norm": 0.1128983348608017,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 5.5863,
+      "step": 29
+    },
+    {
+      "epoch": 1.2972972972972974,
+      "grad_norm": 0.16381703317165375,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 8.229,
+      "step": 30
+    },
+    {
+      "epoch": 1.3405405405405406,
+      "grad_norm": 0.14603477716445923,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 6.893,
+      "step": 31
+    },
+    {
+      "epoch": 1.3837837837837839,
+      "grad_norm": 0.16026656329631805,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 6.9852,
+      "step": 32
+    },
+    {
+      "epoch": 1.427027027027027,
+      "grad_norm": 0.1536598801612854,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 6.9091,
+      "step": 33
+    },
+    {
+      "epoch": 1.4702702702702704,
+      "grad_norm": 0.15081219375133514,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.9582,
+      "step": 34
+    },
+    {
+      "epoch": 1.5135135135135136,
+      "grad_norm": 0.1353471279144287,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 6.4464,
+      "step": 35
+    },
+    {
+      "epoch": 1.5567567567567568,
+      "grad_norm": 0.1591843217611313,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 7.344,
+      "step": 36
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.15149177610874176,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 6.8545,
+      "step": 37
+    },
+    {
+      "epoch": 1.6432432432432433,
+      "grad_norm": 0.15297028422355652,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 6.97,
+      "step": 38
+    },
+    {
+      "epoch": 1.6864864864864866,
+      "grad_norm": 0.1657475382089615,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 6.996,
+      "step": 39
+    },
+    {
+      "epoch": 1.7297297297297298,
+      "grad_norm": 0.16660283505916595,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 6.991,
+      "step": 40
+    },
+    {
+      "epoch": 1.772972972972973,
+      "grad_norm": 0.16040071845054626,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 6.5794,
+      "step": 41
+    },
+    {
+      "epoch": 1.8162162162162163,
+      "grad_norm": 0.15271268784999847,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 7.0738,
+      "step": 42
+    },
+    {
+      "epoch": 1.8594594594594596,
+      "grad_norm": 0.14652898907661438,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 6.9184,
+      "step": 43
+    },
+    {
+      "epoch": 1.9027027027027028,
+      "grad_norm": 0.16251295804977417,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.9841,
+      "step": 44
+    },
+    {
+      "epoch": 1.945945945945946,
+      "grad_norm": 0.15599997341632843,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 6.9053,
+      "step": 45
+    },
+    {
+      "epoch": 1.9891891891891893,
+      "grad_norm": 0.17976956069469452,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 7.2866,
+      "step": 46
+    },
+    {
+      "epoch": 2.0324324324324325,
+      "grad_norm": 0.3074623942375183,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 12.6789,
+      "step": 47
+    },
+    {
+      "epoch": 2.075675675675676,
+      "grad_norm": 0.14891654253005981,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 6.8518,
+      "step": 48
+    },
+    {
+      "epoch": 2.118918918918919,
+      "grad_norm": 0.15843117237091064,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 6.8739,
+      "step": 49
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.1670803725719452,
+      "learning_rate": 0.0,
+      "loss": 7.058,
+      "step": 50
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "eval_loss": 6.917191028594971,
+      "eval_runtime": 0.1313,
+      "eval_samples_per_second": 1188.467,
+      "eval_steps_per_second": 152.368,
+      "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": 2879725363200.0,
+  "total_flos": 5755884503040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null