Training in progress, step 71, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff38f002f2db583c531754273140ac4ffabf37c1df997d72fce2d8cab1c7f19
+oid sha256:d7a21385b35c4511150bddb0e2d338d4e4b0b3813d84d97990112c207a87b76c
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b23075af815920f28ae0b6d3a1c49653f774f432145bdeed595d35340f69806
+oid sha256:ad3fc8934b65cf36b8373430c1e34013c102f1f5871ffb4bbe461bdc23c36ea5
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:526c8ff5efce5a7fe336790db72c3c954df147ad4b0421de13e76d2581d6940d
+oid sha256:abc2af392d268d328bbc945d816ff696059cf2b8006d58eff5988da1fe010300
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c172182220dc75650474ed86f6e1ac686e1b6507660963f478a7ac1072fd6b50
+oid sha256:64db0aa3eeaf835cfc5bd6629b2b7ef4ada209e4e02cd0a3010490e80b328790
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58ac13f1a05864cc78f8c83a52173dae350c18b3f68568e5713ff77494c676c
+oid sha256:e84f9d007bfdd0fe81039600a4c7f0dfe4b20872078f48677037d3e5b040f0ae
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:729086655f90749854673979167b19494ece6995e04928bca1b7af7cd390d65c
+oid sha256:8417b8dfb741dd3cbcef43cd2f4dbb0ada76e1cebf3966f04b3494d8982b5273
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09c886ce689c5dc6f9fb4f7bfd869ed47d5f69d07d5be044cdd6480e5367062
+oid sha256:544f6ccb4622164946a8bd8e21374fc5cfa8e8262c8720a1374851949c7e26c1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 6.85532283782959,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 1.016260162601626,
+  "epoch": 1.443089430894309,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 71,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,153 @@
       "eval_samples_per_second": 620.406,
       "eval_steps_per_second": 37.224,
       "step": 50
+    },
+    {
+      "epoch": 1.0365853658536586,
+      "grad_norm": 0.0706627145409584,
+      "learning_rate": 8.220898871169827e-05,
+      "loss": 6.7974,
+      "step": 51
+    },
+    {
+      "epoch": 1.056910569105691,
+      "grad_norm": 0.06643562018871307,
+      "learning_rate": 7.744141792252794e-05,
+      "loss": 6.8372,
+      "step": 52
+    },
+    {
+      "epoch": 1.0772357723577235,
+      "grad_norm": 0.06472016870975494,
+      "learning_rate": 7.285532566548172e-05,
+      "loss": 6.8331,
+      "step": 53
+    },
+    {
+      "epoch": 1.0975609756097562,
+      "grad_norm": 0.06576112657785416,
+      "learning_rate": 6.846021731708856e-05,
+      "loss": 6.8458,
+      "step": 54
+    },
+    {
+      "epoch": 1.1178861788617886,
+      "grad_norm": 0.06294548511505127,
+      "learning_rate": 6.426520241056245e-05,
+      "loss": 6.8476,
+      "step": 55
+    },
+    {
+      "epoch": 1.1382113821138211,
+      "grad_norm": 0.06356498599052429,
+      "learning_rate": 6.0278975754903317e-05,
+      "loss": 6.846,
+      "step": 56
+    },
+    {
+      "epoch": 1.1585365853658536,
+      "grad_norm": 0.06702162325382233,
+      "learning_rate": 5.6509799413577934e-05,
+      "loss": 6.8533,
+      "step": 57
+    },
+    {
+      "epoch": 1.1788617886178863,
+      "grad_norm": 0.06253218650817871,
+      "learning_rate": 5.296548558013161e-05,
+      "loss": 6.8537,
+      "step": 58
+    },
+    {
+      "epoch": 1.1991869918699187,
+      "grad_norm": 0.06217321753501892,
+      "learning_rate": 4.9653380386224046e-05,
+      "loss": 6.8631,
+      "step": 59
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 0.06489800661802292,
+      "learning_rate": 4.658034867564977e-05,
+      "loss": 6.9336,
+      "step": 60
+    },
+    {
+      "epoch": 1.2398373983739837,
+      "grad_norm": 0.07119685411453247,
+      "learning_rate": 4.375275977590104e-05,
+      "loss": 6.8487,
+      "step": 61
+    },
+    {
+      "epoch": 1.2601626016260163,
+      "grad_norm": 0.06628692150115967,
+      "learning_rate": 4.117647429676387e-05,
+      "loss": 6.5646,
+      "step": 62
+    },
+    {
+      "epoch": 1.2804878048780488,
+      "grad_norm": 0.07155509293079376,
+      "learning_rate": 3.885683198330941e-05,
+      "loss": 7.0993,
+      "step": 63
+    },
+    {
+      "epoch": 1.3008130081300813,
+      "grad_norm": 0.06444606184959412,
+      "learning_rate": 3.679864064845691e-05,
+      "loss": 6.8313,
+      "step": 64
+    },
+    {
+      "epoch": 1.321138211382114,
+      "grad_norm": 0.061461322009563446,
+      "learning_rate": 3.500616620804712e-05,
+      "loss": 6.8289,
+      "step": 65
+    },
+    {
+      "epoch": 1.3414634146341464,
+      "grad_norm": 0.06256741285324097,
+      "learning_rate": 3.348312383908033e-05,
+      "loss": 6.8465,
+      "step": 66
+    },
+    {
+      "epoch": 1.3617886178861789,
+      "grad_norm": 0.06616440415382385,
+      "learning_rate": 3.223267027944483e-05,
+      "loss": 6.8441,
+      "step": 67
+    },
+    {
+      "epoch": 1.3821138211382114,
+      "grad_norm": 0.06352795660495758,
+      "learning_rate": 3.125739728509535e-05,
+      "loss": 6.8487,
+      "step": 68
+    },
+    {
+      "epoch": 1.4024390243902438,
+      "grad_norm": 0.0632796511054039,
+      "learning_rate": 3.055932625824328e-05,
+      "loss": 6.8438,
+      "step": 69
+    },
+    {
+      "epoch": 1.4227642276422765,
+      "grad_norm": 0.06695584207773209,
+      "learning_rate": 3.0139904057691777e-05,
+      "loss": 6.8565,
+      "step": 70
+    },
+    {
+      "epoch": 1.443089430894309,
+      "grad_norm": 0.06280119717121124,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 6.8591,
+      "step": 71
     }
   ],
   "logging_steps": 1,
@@ -404,12 +551,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 10698670080000.0,
+  "total_flos": 15192111513600.0,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null