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:cce3698b1698d2675f201d99ddfc8709dd905b069bc4b57ee4672ffd3556da98
+oid sha256:b6225dc799a76be598ad28ce9afa31d9b6748dad5eeeff5c1c08ad9c1711c64d
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26d976e7695ac034bf556af6a417f6fb1fe8848cdcb28452151a5416589cebba
+oid sha256:35401082f973e4c60f1cf4d8786abc44507ca4c3d22dd8eb11730417f58d310f
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d3798fbe92977c468df560249beeff8821943517ad2ad372e6b561125ab1220
+oid sha256:8971b951096638d89ca3314b1b857d64afa2e02898d5bd4f6079b16275749f89
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf9f827bbbd87064f54e8e51c81eda7802024d14ca0c8f8b05964fa882514f46
+oid sha256:d7ecb99b9ca9b181a5886f6bbd0d91816d6889d67a924c746cc036309d85083c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29ce7e9ad135f121df842132ad66c1da0f30206c8bca5984417694c3493aa2c1
+oid sha256:88e8e04479811b5c791c9660a23e7b19233d68289a1ba798dc8f6164bc720deb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb7e361ff3c0780c7d3bfd4c18a532ec73e832d3793ce6b41f25f79a8eabc0dc
+oid sha256:d311b3bdfc5071cd48b2d92a565ec2e4d09d38ca9e2cd7546c71522b96776f3b
 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": 3.4557735919952393,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9501187648456056,
+  "best_metric": 3.357673168182373,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9026128266033253,
   "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": 71.79,
       "eval_steps_per_second": 9.276,
       "step": 25
+    },
+    {
+      "epoch": 0.9881235154394299,
+      "grad_norm": 0.6033377051353455,
+      "learning_rate": 5e-05,
+      "loss": 3.8401,
+      "step": 26
+    },
+    {
+      "epoch": 1.0285035629453683,
+      "grad_norm": 0.6220775246620178,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 6.2136,
+      "step": 27
+    },
+    {
+      "epoch": 1.0665083135391924,
+      "grad_norm": 0.3605939447879791,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.0169,
+      "step": 28
+    },
+    {
+      "epoch": 1.1045130641330165,
+      "grad_norm": 0.4560985863208771,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.3652,
+      "step": 29
+    },
+    {
+      "epoch": 1.1425178147268409,
+      "grad_norm": 0.5514870285987854,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.1878,
+      "step": 30
+    },
+    {
+      "epoch": 1.180522565320665,
+      "grad_norm": 0.5774045586585999,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.0743,
+      "step": 31
+    },
+    {
+      "epoch": 1.2185273159144894,
+      "grad_norm": 0.7691540122032166,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.6026,
+      "step": 32
+    },
+    {
+      "epoch": 1.2565320665083135,
+      "grad_norm": 0.38054758310317993,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.9451,
+      "step": 33
+    },
+    {
+      "epoch": 1.2945368171021379,
+      "grad_norm": 0.44550177454948425,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.8813,
+      "step": 34
+    },
+    {
+      "epoch": 1.332541567695962,
+      "grad_norm": 0.5434937477111816,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.1944,
+      "step": 35
+    },
+    {
+      "epoch": 1.3705463182897861,
+      "grad_norm": 0.47107967734336853,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.3142,
+      "step": 36
+    },
+    {
+      "epoch": 1.4085510688836105,
+      "grad_norm": 0.55793297290802,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.24,
+      "step": 37
+    },
+    {
+      "epoch": 1.4465558194774346,
+      "grad_norm": 0.7050827741622925,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.4012,
+      "step": 38
+    },
+    {
+      "epoch": 1.484560570071259,
+      "grad_norm": 0.976097583770752,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.7907,
+      "step": 39
+    },
+    {
+      "epoch": 1.522565320665083,
+      "grad_norm": 0.37063631415367126,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.5599,
+      "step": 40
+    },
+    {
+      "epoch": 1.5605700712589075,
+      "grad_norm": 0.39631596207618713,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.1048,
+      "step": 41
+    },
+    {
+      "epoch": 1.5985748218527316,
+      "grad_norm": 0.4788654148578644,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.2364,
+      "step": 42
+    },
+    {
+      "epoch": 1.6365795724465557,
+      "grad_norm": 0.5167055130004883,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.1073,
+      "step": 43
+    },
+    {
+      "epoch": 1.67458432304038,
+      "grad_norm": 0.6170525550842285,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.2586,
+      "step": 44
+    },
+    {
+      "epoch": 1.7125890736342044,
+      "grad_norm": 0.700023889541626,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.5919,
+      "step": 45
+    },
+    {
+      "epoch": 1.7505938242280283,
+      "grad_norm": 0.3638046085834503,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.8131,
+      "step": 46
+    },
+    {
+      "epoch": 1.7885985748218527,
+      "grad_norm": 0.4485277235507965,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.6761,
+      "step": 47
+    },
+    {
+      "epoch": 1.826603325415677,
+      "grad_norm": 0.4701801538467407,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.2881,
+      "step": 48
+    },
+    {
+      "epoch": 1.8646080760095012,
+      "grad_norm": 0.46767908334732056,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.3644,
+      "step": 49
+    },
+    {
+      "epoch": 1.9026128266033253,
+      "grad_norm": 0.5206577181816101,
+      "learning_rate": 0.0,
+      "loss": 3.0493,
+      "step": 50
+    },
+    {
+      "epoch": 1.9026128266033253,
+      "eval_loss": 3.357673168182373,
+      "eval_runtime": 2.3659,
+      "eval_samples_per_second": 75.237,
+      "eval_steps_per_second": 9.722,
+      "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": 5.337414377668608e+16,
+  "total_flos": 1.0671517724783411e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null