Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019af15efb2dcbd976de76ac063f93b8121641556c8c1a1fc9db5ac14335dbda
+oid sha256:60711844fda55f8ee9b119c681f7ef5668003ce400920716b4bb13042c409aaa
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79c40a44e312ca9f85a9ba26925804d3014fbca93097ea247e5d7c2240f1bf61
+oid sha256:d57babde7f416e41a5695e0b5cbd096c2e083317fdf73456760bb5396b561e1a
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f49dc4275dd5e0db1ccb72022f8f7b8078a1c86f1b62fc7ca4965347c2e22bb9
+oid sha256:152cd0ddfdb900a1ee9db68f41a2f646c41e8a83f860127c58562c4ace833f6c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e01fb69481195d0ef54401939a32191b2ad4b493225264302e2cbd85f0360889
+oid sha256:f7a52893496e27877eca2230b05a3dd0ab796fe92cfa42aa54647534c270215b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d11e6c163dd1cfafedbb51fc22a5360783b72ea984d893ca03e050f105cd6900
+oid sha256:1ea7dbf0693376a9eb8d16bcc14ed8290fd4db9869728a9c5a9199c29f155ffd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6154ddd0ca82c24f83293db4e50ce4b13738adc9f0a115358ad04b394b61de18
+oid sha256:d8d14560e223fc030c6157f29852e84e03adf39cfc748d9f10ae1c6786c80abc
 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": 0.9369022250175476,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.33030553261767137,
+  "best_metric": 0.9118998050689697,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6606110652353427,
   "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": 34.83,
       "eval_steps_per_second": 4.371,
       "step": 25
+    },
+    {
+      "epoch": 0.3435177539223782,
+      "grad_norm": 0.4335106909275055,
+      "learning_rate": 5e-05,
+      "loss": 0.9927,
+      "step": 26
+    },
+    {
+      "epoch": 0.35672997522708505,
+      "grad_norm": 0.4817415177822113,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.9772,
+      "step": 27
+    },
+    {
+      "epoch": 0.3699421965317919,
+      "grad_norm": 0.4249557852745056,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.9824,
+      "step": 28
+    },
+    {
+      "epoch": 0.3831544178364988,
+      "grad_norm": 0.37584105134010315,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9446,
+      "step": 29
+    },
+    {
+      "epoch": 0.3963666391412056,
+      "grad_norm": 0.3376809060573578,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9574,
+      "step": 30
+    },
+    {
+      "epoch": 0.40957886044591246,
+      "grad_norm": 0.274263858795166,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.915,
+      "step": 31
+    },
+    {
+      "epoch": 0.4227910817506193,
+      "grad_norm": 0.2863050103187561,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.9271,
+      "step": 32
+    },
+    {
+      "epoch": 0.4360033030553262,
+      "grad_norm": 0.2439480870962143,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9205,
+      "step": 33
+    },
+    {
+      "epoch": 0.44921552436003304,
+      "grad_norm": 0.327269583940506,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8951,
+      "step": 34
+    },
+    {
+      "epoch": 0.4624277456647399,
+      "grad_norm": 0.33922868967056274,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9512,
+      "step": 35
+    },
+    {
+      "epoch": 0.4756399669694467,
+      "grad_norm": 0.3129810392856598,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9269,
+      "step": 36
+    },
+    {
+      "epoch": 0.4888521882741536,
+      "grad_norm": 0.505581259727478,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8302,
+      "step": 37
+    },
+    {
+      "epoch": 0.5020644095788604,
+      "grad_norm": 0.36821824312210083,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9218,
+      "step": 38
+    },
+    {
+      "epoch": 0.5152766308835673,
+      "grad_norm": 0.4120348393917084,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.9595,
+      "step": 39
+    },
+    {
+      "epoch": 0.5284888521882741,
+      "grad_norm": 0.38509809970855713,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9533,
+      "step": 40
+    },
+    {
+      "epoch": 0.541701073492981,
+      "grad_norm": 0.32172009348869324,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9401,
+      "step": 41
+    },
+    {
+      "epoch": 0.5549132947976878,
+      "grad_norm": 0.2821166515350342,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.9336,
+      "step": 42
+    },
+    {
+      "epoch": 0.5681255161023947,
+      "grad_norm": 0.20851825177669525,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9049,
+      "step": 43
+    },
+    {
+      "epoch": 0.5813377374071016,
+      "grad_norm": 0.23832282423973083,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.931,
+      "step": 44
+    },
+    {
+      "epoch": 0.5945499587118084,
+      "grad_norm": 0.23053020238876343,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.919,
+      "step": 45
+    },
+    {
+      "epoch": 0.6077621800165153,
+      "grad_norm": 0.32718178629875183,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9049,
+      "step": 46
+    },
+    {
+      "epoch": 0.6209744013212222,
+      "grad_norm": 0.3872445821762085,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9391,
+      "step": 47
+    },
+    {
+      "epoch": 0.634186622625929,
+      "grad_norm": 0.34386420249938965,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9179,
+      "step": 48
+    },
+    {
+      "epoch": 0.6473988439306358,
+      "grad_norm": 0.3821120262145996,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9039,
+      "step": 49
+    },
+    {
+      "epoch": 0.6606110652353427,
+      "grad_norm": 0.6619767546653748,
+      "learning_rate": 0.0,
+      "loss": 0.8356,
+      "step": 50
+    },
+    {
+      "epoch": 0.6606110652353427,
+      "eval_loss": 0.9118998050689697,
+      "eval_runtime": 14.644,
+      "eval_samples_per_second": 34.826,
+      "eval_steps_per_second": 4.37,
+      "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": 2.629552387915776e+17,
+  "total_flos": 5.259104775831552e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null