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:f41b79576a924dea42734236c3ad3fbadbe766043fdcbf546edea80f0d24f9cb
+oid sha256:d047bdcd4e973979beb6bd1e0b8a08c5a82b6b55f524050ee0ab9a60671eb254
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12f338547a48853ecc92ed4cbce78a6d9ba85cee28343fb970d5b3844d268b2d
+oid sha256:0daaa5dc480cbeaa1e04d16fbd2827afb06bcbee0cec2285177f64ad911738d8
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa05a865aff45e989a8c6b25c4a2375bbb87080e72ed92377dda8accc63a9b2c
+oid sha256:2c8c3bcc1577294a1d17d4dc319e9d343488285f5ba413a33529b72bd2653e7e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd24fe94724b17203c7081de1e070175b9825c462fb93d99ebdbbffcf3da541c
+oid sha256:24954f9790e39a05d7defe3874594aced0a221c61c8d4c0aaadc1ba3bcf1ee54
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eaa4dd20c4eb365ee032fa8568e139121865fb698ec4bcd2efc0b1e7574654ec
+oid sha256:89eaff9506ffc49b05424a096a6dd6c74ea777a1e3ed9f58b9e8e08f7ad01962
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8725dba6e1356bb51c97670b13704d5da43cf52a426c4b6eac362052912be488
+oid sha256:29bc162805ff0773b8fe86952b91cb5290d0799fe122320197030b4b1f5f9edc
 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": 0.3386324644088745,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.07814026176987693,
+  "best_metric": 0.28741422295570374,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.15628052353975386,
   "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": 37.87,
       "eval_steps_per_second": 4.743,
       "step": 25
+    },
+    {
+      "epoch": 0.08126587224067201,
+      "grad_norm": 2.45245623588562,
+      "learning_rate": 5e-05,
+      "loss": 0.3774,
+      "step": 26
+    },
+    {
+      "epoch": 0.08439148271146708,
+      "grad_norm": 1.5845011472702026,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3466,
+      "step": 27
+    },
+    {
+      "epoch": 0.08751709318226215,
+      "grad_norm": 0.8654233813285828,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2892,
+      "step": 28
+    },
+    {
+      "epoch": 0.09064270365305724,
+      "grad_norm": 1.2370487451553345,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3171,
+      "step": 29
+    },
+    {
+      "epoch": 0.09376831412385231,
+      "grad_norm": 1.3261559009552002,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.3282,
+      "step": 30
+    },
+    {
+      "epoch": 0.0968939245946474,
+      "grad_norm": 1.2208430767059326,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2933,
+      "step": 31
+    },
+    {
+      "epoch": 0.10001953506544246,
+      "grad_norm": 1.0844453573226929,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3098,
+      "step": 32
+    },
+    {
+      "epoch": 0.10314514553623755,
+      "grad_norm": 0.9611645936965942,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2733,
+      "step": 33
+    },
+    {
+      "epoch": 0.10627075600703262,
+      "grad_norm": 1.1155072450637817,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3004,
+      "step": 34
+    },
+    {
+      "epoch": 0.1093963664778277,
+      "grad_norm": 1.0913764238357544,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3093,
+      "step": 35
+    },
+    {
+      "epoch": 0.11252197694862277,
+      "grad_norm": 0.7945312261581421,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2808,
+      "step": 36
+    },
+    {
+      "epoch": 0.11564758741941786,
+      "grad_norm": 1.0648337602615356,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2536,
+      "step": 37
+    },
+    {
+      "epoch": 0.11877319789021293,
+      "grad_norm": 0.7629750967025757,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3224,
+      "step": 38
+    },
+    {
+      "epoch": 0.12189880836100801,
+      "grad_norm": 1.1458991765975952,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2724,
+      "step": 39
+    },
+    {
+      "epoch": 0.1250244188318031,
+      "grad_norm": 2.066157579421997,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3444,
+      "step": 40
+    },
+    {
+      "epoch": 0.12815002930259817,
+      "grad_norm": 2.434628963470459,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3555,
+      "step": 41
+    },
+    {
+      "epoch": 0.13127563977339324,
+      "grad_norm": 1.6599045991897583,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.3035,
+      "step": 42
+    },
+    {
+      "epoch": 0.1344012502441883,
+      "grad_norm": 1.7663042545318604,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3589,
+      "step": 43
+    },
+    {
+      "epoch": 0.1375268607149834,
+      "grad_norm": 1.3124494552612305,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3243,
+      "step": 44
+    },
+    {
+      "epoch": 0.14065247118577848,
+      "grad_norm": 0.9794068336486816,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2703,
+      "step": 45
+    },
+    {
+      "epoch": 0.14377808165657355,
+      "grad_norm": 1.0024210214614868,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2816,
+      "step": 46
+    },
+    {
+      "epoch": 0.14690369212736862,
+      "grad_norm": 1.1213816404342651,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2952,
+      "step": 47
+    },
+    {
+      "epoch": 0.15002930259816372,
+      "grad_norm": 1.1528414487838745,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2853,
+      "step": 48
+    },
+    {
+      "epoch": 0.1531549130689588,
+      "grad_norm": 0.7072805762290955,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2796,
+      "step": 49
+    },
+    {
+      "epoch": 0.15628052353975386,
+      "grad_norm": 0.8989966511726379,
+      "learning_rate": 0.0,
+      "loss": 0.2968,
+      "step": 50
+    },
+    {
+      "epoch": 0.15628052353975386,
+      "eval_loss": 0.28741422295570374,
+      "eval_runtime": 56.9261,
+      "eval_samples_per_second": 37.874,
+      "eval_steps_per_second": 4.743,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null