Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd5f5dc328c26b02bc9f97ee7ee6780d210fdc74bfd45724d3049d73d058491
+oid sha256:e49f57a5f88e34beb3163545ed6a2476ba4d3b578e28dc0301e5abe6c0aace8b
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f793f14384983e5f5176a844ff7e2a410b560ab352e82d7dcc61395cb715113f
+oid sha256:be6f511faedbeca7818dd92a07a03845a5a5d7f544b2cb6918f8d83c83ce4fe9
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e5ace1042d41cf9168006df6516b80b44b6fd6adf6e13be2bd607b91877d4f
+oid sha256:94637d7ffb0cb5cc7c96d0f33995c199e60857dabed8c474a12aeaabfd646aec
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66731505eb47a42c0b4141f8171ffd9e396692055f8aea4be68499110e3cc241
+oid sha256:acea86e425703e89a9bf2ec1a99c93375ca76a49e4a34897f904c216a07455bc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4746845796bbde32e548d4bf44afaf71c0d5e7972adfd26a66c299477cd10e5f
+oid sha256:5fb0569ad3e17bd511677cd75543a410d517996e4bf978f101a0f19bef16a668
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93112f446dbb3e35559fe9b13ba24f030d1e2ce8d48b12b0c654e602f42619a1
+oid sha256:9dfdbb93df0393a9bffa400395ec263f550ffa8c03324e4bae0150cdd867c8b5
 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": 2.083423137664795,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.17286084701815038,
+  "best_metric": 2.044828414916992,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.34572169403630076,
   "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": 143.994,
       "eval_steps_per_second": 18.018,
       "step": 25
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "grad_norm": 0.5990504026412964,
+      "learning_rate": 5e-05,
+      "loss": 2.161,
+      "step": 26
+    },
+    {
+      "epoch": 0.18668971477960242,
+      "grad_norm": 0.6129897832870483,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0514,
+      "step": 27
+    },
+    {
+      "epoch": 0.19360414866032843,
+      "grad_norm": 0.5701473355293274,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.0373,
+      "step": 28
+    },
+    {
+      "epoch": 0.20051858254105445,
+      "grad_norm": 0.5828129053115845,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.9951,
+      "step": 29
+    },
+    {
+      "epoch": 0.20743301642178047,
+      "grad_norm": 0.5781091451644897,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.0095,
+      "step": 30
+    },
+    {
+      "epoch": 0.2143474503025065,
+      "grad_norm": 0.5957980751991272,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.0276,
+      "step": 31
+    },
+    {
+      "epoch": 0.2212618841832325,
+      "grad_norm": 0.5550655126571655,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.0665,
+      "step": 32
+    },
+    {
+      "epoch": 0.22817631806395852,
+      "grad_norm": 0.5569533705711365,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.0486,
+      "step": 33
+    },
+    {
+      "epoch": 0.23509075194468454,
+      "grad_norm": 0.587203323841095,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0427,
+      "step": 34
+    },
+    {
+      "epoch": 0.24200518582541056,
+      "grad_norm": 0.628190815448761,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.1194,
+      "step": 35
+    },
+    {
+      "epoch": 0.24891961970613655,
+      "grad_norm": 0.6483805775642395,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.1284,
+      "step": 36
+    },
+    {
+      "epoch": 0.25583405358686256,
+      "grad_norm": 0.9295467138290405,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.2859,
+      "step": 37
+    },
+    {
+      "epoch": 0.2627484874675886,
+      "grad_norm": 0.3905627727508545,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.1243,
+      "step": 38
+    },
+    {
+      "epoch": 0.2696629213483146,
+      "grad_norm": 0.4461933672428131,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.0737,
+      "step": 39
+    },
+    {
+      "epoch": 0.27657735522904064,
+      "grad_norm": 0.484654039144516,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0199,
+      "step": 40
+    },
+    {
+      "epoch": 0.28349178910976663,
+      "grad_norm": 0.4882582128047943,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.0215,
+      "step": 41
+    },
+    {
+      "epoch": 0.2904062229904927,
+      "grad_norm": 0.4536379873752594,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.0383,
+      "step": 42
+    },
+    {
+      "epoch": 0.29732065687121867,
+      "grad_norm": 0.45317670702934265,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.9894,
+      "step": 43
+    },
+    {
+      "epoch": 0.30423509075194466,
+      "grad_norm": 0.4442202150821686,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9552,
+      "step": 44
+    },
+    {
+      "epoch": 0.3111495246326707,
+      "grad_norm": 0.43366938829421997,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.9832,
+      "step": 45
+    },
+    {
+      "epoch": 0.3180639585133967,
+      "grad_norm": 0.4810980558395386,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.988,
+      "step": 46
+    },
+    {
+      "epoch": 0.32497839239412274,
+      "grad_norm": 0.4820277988910675,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.0303,
+      "step": 47
+    },
+    {
+      "epoch": 0.33189282627484873,
+      "grad_norm": 0.5481479167938232,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.0748,
+      "step": 48
+    },
+    {
+      "epoch": 0.3388072601555748,
+      "grad_norm": 0.6438647508621216,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.1891,
+      "step": 49
+    },
+    {
+      "epoch": 0.34572169403630076,
+      "grad_norm": 1.0699537992477417,
+      "learning_rate": 0.0,
+      "loss": 2.3742,
+      "step": 50
+    },
+    {
+      "epoch": 0.34572169403630076,
+      "eval_loss": 2.044828414916992,
+      "eval_runtime": 6.7873,
+      "eval_samples_per_second": 143.652,
+      "eval_steps_per_second": 17.975,
+      "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": 1.4774273839202304e+16,
+  "total_flos": 2.954854767840461e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null