Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a1637beaeb297228aad5756d9b3c0b7525eb469a0bdb0dc409053719af09e5
+oid sha256:6479b323807a9b929cd0f3477ea446072b23a693ee1b5a761f7bf3ad80c5ab1e
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61b480a3afc650bf4c66c9a7602e6bd8cf76beb92ec2b002374acebaaff475f
+oid sha256:b1449c0d7b1127e5a597ca9b2b9aaf4e2ed3b2879298a9f08404b96ce2414933
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfc0724a64e9a729c8733b7fa44b0c5b89c1d1acceb2f1f92af71f32032c5874
+oid sha256:b376455dff954dd91fc47b901fe4e1d8bbc5ae2d00a94b8e80155fea4f0ce3b4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2873783111572266,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.001978552490997586,
+  "best_metric": 2.272261142730713,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.003957104981995172,
   "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": 3.671,
       "eval_steps_per_second": 1.836,
       "step": 25
+    },
+    {
+      "epoch": 0.0020576945906374895,
+      "grad_norm": 0.42730939388275146,
+      "learning_rate": 0.0001,
+      "loss": 2.0884,
+      "step": 26
+    },
+    {
+      "epoch": 0.002136836690277393,
+      "grad_norm": 0.9263526797294617,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 2.3938,
+      "step": 27
+    },
+    {
+      "epoch": 0.0022159787899172965,
+      "grad_norm": 0.3488403856754303,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 2.3595,
+      "step": 28
+    },
+    {
+      "epoch": 0.0022951208895572,
+      "grad_norm": 0.37862449884414673,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 2.1439,
+      "step": 29
+    },
+    {
+      "epoch": 0.0023742629891971034,
+      "grad_norm": 0.3307685852050781,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 2.2033,
+      "step": 30
+    },
+    {
+      "epoch": 0.002453405088837007,
+      "grad_norm": 0.3769107162952423,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 2.4333,
+      "step": 31
+    },
+    {
+      "epoch": 0.0025325471884769103,
+      "grad_norm": 0.38113144040107727,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 2.1927,
+      "step": 32
+    },
+    {
+      "epoch": 0.0026116892881168138,
+      "grad_norm": 0.33478325605392456,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 2.3015,
+      "step": 33
+    },
+    {
+      "epoch": 0.0026908313877567172,
+      "grad_norm": 0.29439330101013184,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.2517,
+      "step": 34
+    },
+    {
+      "epoch": 0.0027699734873966207,
+      "grad_norm": 0.3198701739311218,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 2.3491,
+      "step": 35
+    },
+    {
+      "epoch": 0.002849115587036524,
+      "grad_norm": 0.4098028838634491,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 2.4146,
+      "step": 36
+    },
+    {
+      "epoch": 0.0029282576866764276,
+      "grad_norm": 0.39363518357276917,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 2.4595,
+      "step": 37
+    },
+    {
+      "epoch": 0.003007399786316331,
+      "grad_norm": 0.37463560700416565,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.4214,
+      "step": 38
+    },
+    {
+      "epoch": 0.0030865418859562345,
+      "grad_norm": 0.35873377323150635,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 2.2987,
+      "step": 39
+    },
+    {
+      "epoch": 0.003165683985596138,
+      "grad_norm": 0.35473981499671936,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 2.3872,
+      "step": 40
+    },
+    {
+      "epoch": 0.0032448260852360414,
+      "grad_norm": 0.38532593846321106,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 2.2592,
+      "step": 41
+    },
+    {
+      "epoch": 0.003323968184875945,
+      "grad_norm": 0.4655337333679199,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 2.4574,
+      "step": 42
+    },
+    {
+      "epoch": 0.0034031102845158484,
+      "grad_norm": 0.4277578294277191,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 2.3818,
+      "step": 43
+    },
+    {
+      "epoch": 0.003482252384155752,
+      "grad_norm": 0.5126660466194153,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 2.4937,
+      "step": 44
+    },
+    {
+      "epoch": 0.0035613944837956553,
+      "grad_norm": 0.47781333327293396,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 2.5162,
+      "step": 45
+    },
+    {
+      "epoch": 0.0036405365834355588,
+      "grad_norm": 0.525256335735321,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 2.275,
+      "step": 46
+    },
+    {
+      "epoch": 0.0037196786830754618,
+      "grad_norm": 0.6399112939834595,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 2.5581,
+      "step": 47
+    },
+    {
+      "epoch": 0.0037988207827153652,
+      "grad_norm": 0.5539636015892029,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 2.5673,
+      "step": 48
+    },
+    {
+      "epoch": 0.0038779628823552687,
+      "grad_norm": 0.6108574271202087,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 2.4309,
+      "step": 49
+    },
+    {
+      "epoch": 0.003957104981995172,
+      "grad_norm": 0.9037721753120422,
+      "learning_rate": 0.0,
+      "loss": 2.5523,
+      "step": 50
+    },
+    {
+      "epoch": 0.003957104981995172,
+      "eval_loss": 2.272261142730713,
+      "eval_runtime": 1449.1424,
+      "eval_samples_per_second": 3.672,
+      "eval_steps_per_second": 1.836,
+      "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": 3.29615318974464e+16,
+  "total_flos": 6.59230637948928e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null