Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:230343fa0753b22a28c2853983a74e79b3872e11b0db0e8eb058190b85fb32a8
+oid sha256:30cbced57fd6204f81250f21d906eebc4df65623f7a7354c1dc3cd41d275918d
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f157649d93cb49c525d1a7efd9ca2628e45921de1c93b072468da442b4c1373
+oid sha256:3c310cac8924aa5b49511787ae17ae930aeb263a1548e53dc7eae42be3e41320
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:399fe60659d7689d6eea08021aaf7665d24667c7d040316f63914bf5a73c14ef
+oid sha256:aed5aa11f5eb72daaedfd300e32c8ee8aed1f9249521c9fc611cfd846a162364
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc98bbd0f638f96fd3c3fe610f1cea1c5e7860d14e56c22b8dafd6f1e6543002
+oid sha256:f52a0c03b2efbf17939e961851ad73317567fa4df7d972bb3717528b68a5f6b0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1d36cb0320a322b1b2cb7b82dd560268d1abe44dcba5e08be2ec5c6ad173fc
+oid sha256:a8dc5141a3c5abc85a2e8010778542f7bd1fb967a2adee4ec0d5c524b5005333
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c42a6854513bb02e28361a8e096e5206cc7fc3a6d9a02766d3e8a288892b5d0
+oid sha256:126c95dc98a0761077a490543fcd1d0938c367db8fbc32548d97b0fbbb4bd2c4
 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": 6.946163177490234,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08822232024702249,
+  "best_metric": 6.818531036376953,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.17644464049404499,
   "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": 216.475,
       "eval_steps_per_second": 27.102,
       "step": 25
+    },
+    {
+      "epoch": 0.0917512130569034,
+      "grad_norm": 1.1054739952087402,
+      "learning_rate": 5e-05,
+      "loss": 7.2183,
+      "step": 26
+    },
+    {
+      "epoch": 0.0952801058667843,
+      "grad_norm": 0.9908803105354309,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 6.958,
+      "step": 27
+    },
+    {
+      "epoch": 0.09880899867666519,
+      "grad_norm": 1.0078890323638916,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 7.0784,
+      "step": 28
+    },
+    {
+      "epoch": 0.1023378914865461,
+      "grad_norm": 1.0495905876159668,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 6.9738,
+      "step": 29
+    },
+    {
+      "epoch": 0.105866784296427,
+      "grad_norm": 1.1118749380111694,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 6.8487,
+      "step": 30
+    },
+    {
+      "epoch": 0.10939567710630789,
+      "grad_norm": 1.258945345878601,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 6.8057,
+      "step": 31
+    },
+    {
+      "epoch": 0.1129245699161888,
+      "grad_norm": 1.2230989933013916,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 6.9796,
+      "step": 32
+    },
+    {
+      "epoch": 0.1164534627260697,
+      "grad_norm": 1.4328244924545288,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 6.7772,
+      "step": 33
+    },
+    {
+      "epoch": 0.1199823555359506,
+      "grad_norm": 1.7075251340866089,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.9079,
+      "step": 34
+    },
+    {
+      "epoch": 0.12351124834583149,
+      "grad_norm": 2.2108325958251953,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 6.6871,
+      "step": 35
+    },
+    {
+      "epoch": 0.12704014115571238,
+      "grad_norm": 2.8738584518432617,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 6.7338,
+      "step": 36
+    },
+    {
+      "epoch": 0.1305690339655933,
+      "grad_norm": 4.4806036949157715,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 6.7032,
+      "step": 37
+    },
+    {
+      "epoch": 0.1340979267754742,
+      "grad_norm": 1.2014843225479126,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.2215,
+      "step": 38
+    },
+    {
+      "epoch": 0.13762681958535508,
+      "grad_norm": 0.9526251554489136,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 7.0711,
+      "step": 39
+    },
+    {
+      "epoch": 0.141155712395236,
+      "grad_norm": 0.9825794696807861,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 7.0598,
+      "step": 40
+    },
+    {
+      "epoch": 0.1446846052051169,
+      "grad_norm": 0.9970250129699707,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 6.7972,
+      "step": 41
+    },
+    {
+      "epoch": 0.1482134980149978,
+      "grad_norm": 1.0425372123718262,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 6.8431,
+      "step": 42
+    },
+    {
+      "epoch": 0.1517423908248787,
+      "grad_norm": 1.1232349872589111,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 6.8156,
+      "step": 43
+    },
+    {
+      "epoch": 0.1552712836347596,
+      "grad_norm": 1.303544282913208,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.6732,
+      "step": 44
+    },
+    {
+      "epoch": 0.1588001764446405,
+      "grad_norm": 1.401859998703003,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 6.696,
+      "step": 45
+    },
+    {
+      "epoch": 0.1623290692545214,
+      "grad_norm": 1.6703929901123047,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 6.8849,
+      "step": 46
+    },
+    {
+      "epoch": 0.1658579620644023,
+      "grad_norm": 1.9721368551254272,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 6.7516,
+      "step": 47
+    },
+    {
+      "epoch": 0.1693868548742832,
+      "grad_norm": 2.599738359451294,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 6.8387,
+      "step": 48
+    },
+    {
+      "epoch": 0.1729157476841641,
+      "grad_norm": 3.7143712043762207,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 6.7818,
+      "step": 49
+    },
+    {
+      "epoch": 0.17644464049404499,
+      "grad_norm": 5.192096710205078,
+      "learning_rate": 0.0,
+      "loss": 6.617,
+      "step": 50
+    },
+    {
+      "epoch": 0.17644464049404499,
+      "eval_loss": 6.818531036376953,
+      "eval_runtime": 8.8921,
+      "eval_samples_per_second": 214.685,
+      "eval_steps_per_second": 26.878,
+      "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": 116006898892800.0,
+  "total_flos": 232013797785600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null