Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48b849b0639072c81c28e60615d399aeacc871913e47ff0af164d9e8d66f3ac7
+oid sha256:babc82995071bc41aade3454d15ec9bb729d608997415d35bcd2c165bc782f33
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4a8e4dce1af080bd39e003d9c564cc0189ea7a06901e0d0cfd20b471d2653db
+oid sha256:0c51a1e2578eaad67acf69af76baea1d98fcce883b9129ee2d3fbcd75663d482
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b21235d7310c76611cd027b6ec2a9e84982a6979284dabfd4e28eebadef009e
+oid sha256:3ffba558654506832b5597bf972aa095b36602aaa1cc09e0d0d147c3a782cc8c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5063db6ae05109d54988422d72cb5a96bf60d9778931bb7bdcaf6c5e2d3c4ce
+oid sha256:79307bdfd3764f9f34027dd539012be032a8f7b79e1df2fd5965658a362e8053
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ae14563717027916e574c2bdef6015cd3dcbb1f7627833735476aaedba7400a
+oid sha256:52e3013cf1b9904d72d3b0a6acc6c9fb854b016b052426d7fd2097ca2a412319
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3a0b0f8a3d4cb27d35aae35f7edf8934375bfcc7db432466bd5819f249b82b
+oid sha256:21b9829c96e37ea15bd3e98d1f613a9ab5cc5cdeb64c689d1051eca410e52456
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f5c305e4a92be904895c02f0f0a1da666e6e7555f6043a8f089990c87f4ce88
+oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.142909526824951,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6546644844517185,
+  "best_metric": 3.856473922729492,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.3093289689034369,
   "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": 173.488,
       "eval_steps_per_second": 45.107,
       "step": 25
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.4640260636806488,
+      "learning_rate": 8.681980515339464e-05,
+      "loss": 4.2203,
+      "step": 26
+    },
+    {
+      "epoch": 0.707037643207856,
+      "grad_norm": 0.5100923776626587,
+      "learning_rate": 8.571489144483944e-05,
+      "loss": 4.181,
+      "step": 27
+    },
+    {
+      "epoch": 0.7332242225859247,
+      "grad_norm": 0.6287262439727783,
+      "learning_rate": 8.457416554680877e-05,
+      "loss": 4.3732,
+      "step": 28
+    },
+    {
+      "epoch": 0.7594108019639935,
+      "grad_norm": 0.5281463265419006,
+      "learning_rate": 8.339895749467238e-05,
+      "loss": 3.7263,
+      "step": 29
+    },
+    {
+      "epoch": 0.7855973813420621,
+      "grad_norm": 0.41669386625289917,
+      "learning_rate": 8.219063752844926e-05,
+      "loss": 3.7891,
+      "step": 30
+    },
+    {
+      "epoch": 0.8117839607201309,
+      "grad_norm": 0.39933446049690247,
+      "learning_rate": 8.095061449516903e-05,
+      "loss": 3.8458,
+      "step": 31
+    },
+    {
+      "epoch": 0.8379705400981997,
+      "grad_norm": 0.42396020889282227,
+      "learning_rate": 7.968033420621935e-05,
+      "loss": 3.8991,
+      "step": 32
+    },
+    {
+      "epoch": 0.8641571194762684,
+      "grad_norm": 0.45608440041542053,
+      "learning_rate": 7.838127775159452e-05,
+      "loss": 3.9113,
+      "step": 33
+    },
+    {
+      "epoch": 0.8903436988543372,
+      "grad_norm": 0.5071250200271606,
+      "learning_rate": 7.705495977301078e-05,
+      "loss": 3.9696,
+      "step": 34
+    },
+    {
+      "epoch": 0.9165302782324058,
+      "grad_norm": 0.408988356590271,
+      "learning_rate": 7.570292669790186e-05,
+      "loss": 4.0264,
+      "step": 35
+    },
+    {
+      "epoch": 0.9427168576104746,
+      "grad_norm": 0.41267451643943787,
+      "learning_rate": 7.43267549363537e-05,
+      "loss": 4.0024,
+      "step": 36
+    },
+    {
+      "epoch": 0.9689034369885434,
+      "grad_norm": 0.6320325136184692,
+      "learning_rate": 7.292804904308087e-05,
+      "loss": 4.0503,
+      "step": 37
+    },
+    {
+      "epoch": 0.9950900163666121,
+      "grad_norm": 0.7328307628631592,
+      "learning_rate": 7.150843984658754e-05,
+      "loss": 4.1336,
+      "step": 38
+    },
+    {
+      "epoch": 1.0212765957446808,
+      "grad_norm": 1.987341284751892,
+      "learning_rate": 7.006958254769438e-05,
+      "loss": 6.7162,
+      "step": 39
+    },
+    {
+      "epoch": 1.0474631751227497,
+      "grad_norm": 1.042544960975647,
+      "learning_rate": 6.861315478964841e-05,
+      "loss": 3.6702,
+      "step": 40
+    },
+    {
+      "epoch": 1.0736497545008183,
+      "grad_norm": 0.6465303301811218,
+      "learning_rate": 6.714085470206609e-05,
+      "loss": 3.8179,
+      "step": 41
+    },
+    {
+      "epoch": 1.099836333878887,
+      "grad_norm": 0.3951312005519867,
+      "learning_rate": 6.56543989209901e-05,
+      "loss": 3.7864,
+      "step": 42
+    },
+    {
+      "epoch": 1.1260229132569557,
+      "grad_norm": 0.41512835025787354,
+      "learning_rate": 6.415552058736854e-05,
+      "loss": 3.7806,
+      "step": 43
+    },
+    {
+      "epoch": 1.1522094926350246,
+      "grad_norm": 0.534665584564209,
+      "learning_rate": 6.264596732629e-05,
+      "loss": 3.8374,
+      "step": 44
+    },
+    {
+      "epoch": 1.1783960720130933,
+      "grad_norm": 0.5684964060783386,
+      "learning_rate": 6.112749920933111e-05,
+      "loss": 3.9551,
+      "step": 45
+    },
+    {
+      "epoch": 1.204582651391162,
+      "grad_norm": 0.6400809288024902,
+      "learning_rate": 5.960188670239154e-05,
+      "loss": 4.0032,
+      "step": 46
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 0.7185765504837036,
+      "learning_rate": 5.80709086014102e-05,
+      "loss": 3.9989,
+      "step": 47
+    },
+    {
+      "epoch": 1.2569558101472995,
+      "grad_norm": 0.5369796752929688,
+      "learning_rate": 5.653634995836856e-05,
+      "loss": 3.3087,
+      "step": 48
+    },
+    {
+      "epoch": 1.2831423895253682,
+      "grad_norm": 0.3849294185638428,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.8981,
+      "step": 49
+    },
+    {
+      "epoch": 1.3093289689034369,
+      "grad_norm": 0.34771353006362915,
+      "learning_rate": 5.346365004163145e-05,
+      "loss": 3.6507,
+      "step": 50
+    },
+    {
+      "epoch": 1.3093289689034369,
+      "eval_loss": 3.856473922729492,
+      "eval_runtime": 0.2803,
+      "eval_samples_per_second": 178.389,
+      "eval_steps_per_second": 46.381,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5686862177894400.0,
+  "total_flos": 1.13737243557888e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null