Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8c2981a6d0acdb6a9f33e868656d33c8edd890e867aa80d9e050b74bda57fea
+oid sha256:9d95f3292d011bfa0f6f200c33ec0fe694b4a3504faa2a05b0745f4b0959cefe
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3456bcd455a85f05fadbf036f85295fa55ba86c65213ca7be2e765aa44abf73a
+oid sha256:d85610e015c5273f9b34bc3223ff08ffa85f188b61e98e4436f3de18aa9fc119
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5346b2fcacfcede118e119a7779fe56a80aab626d410d6ea41dc163d233048cc
+oid sha256:b9aad5b8a7ed3399ba42be1b623e0f94bb5b63064670587d5808d6a7b1a5604a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8280d2baacb3a3f336bc60e0922d43f23fc81e348d244bce634231d74609d8ba
+oid sha256:f85dfacbbcc9678049350859c3eda9f18fb349dd16bb5cbd235b5f14e3c6f7d7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d23bec2d2ec5294458693d914b3a162540a67da732cf0758bd3173ce17cb14e
+oid sha256:73f9b6a40e7893c555ab93b2a2e1fff1d41c9a6b10cdedbfb5c601f543915721
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31fd7fafd1cb9bc086b5bda24049ea808651f18ec7472122ad94e9e6818baed2
+oid sha256:b4d1816811d028604e42d7e52a923daa2d44f7ba661542acb2bd12b01c0cd513
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
+oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6258954405784607,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.40434672731867577,
+  "best_metric": 0.6152855753898621,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.6065200909780136,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 14.231,
       "eval_steps_per_second": 3.7,
       "step": 50
+    },
+    {
+      "epoch": 0.41243366186504926,
+      "grad_norm": 0.4838196933269501,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 0.7284,
+      "step": 51
+    },
+    {
+      "epoch": 0.4205205964114228,
+      "grad_norm": 0.49653565883636475,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 0.6909,
+      "step": 52
+    },
+    {
+      "epoch": 0.4286075309577963,
+      "grad_norm": 0.5994144678115845,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 0.7597,
+      "step": 53
+    },
+    {
+      "epoch": 0.43669446550416985,
+      "grad_norm": 0.5351035594940186,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 0.7537,
+      "step": 54
+    },
+    {
+      "epoch": 0.44478140005054334,
+      "grad_norm": 0.4333861470222473,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 0.6553,
+      "step": 55
+    },
+    {
+      "epoch": 0.45286833459691683,
+      "grad_norm": 0.39463362097740173,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 0.7712,
+      "step": 56
+    },
+    {
+      "epoch": 0.4609552691432904,
+      "grad_norm": 0.36598527431488037,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 0.6333,
+      "step": 57
+    },
+    {
+      "epoch": 0.4690422036896639,
+      "grad_norm": 0.3563452661037445,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 0.6562,
+      "step": 58
+    },
+    {
+      "epoch": 0.4771291382360374,
+      "grad_norm": 0.451840341091156,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 0.711,
+      "step": 59
+    },
+    {
+      "epoch": 0.4852160727824109,
+      "grad_norm": 0.37084537744522095,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 0.6075,
+      "step": 60
+    },
+    {
+      "epoch": 0.49330300732878446,
+      "grad_norm": 0.47421273589134216,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 0.7213,
+      "step": 61
+    },
+    {
+      "epoch": 0.501389941875158,
+      "grad_norm": 0.5006868243217468,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 0.5814,
+      "step": 62
+    },
+    {
+      "epoch": 0.5094768764215315,
+      "grad_norm": 0.38857290148735046,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 0.6031,
+      "step": 63
+    },
+    {
+      "epoch": 0.5175638109679049,
+      "grad_norm": 0.3656562268733978,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 0.7153,
+      "step": 64
+    },
+    {
+      "epoch": 0.5256507455142785,
+      "grad_norm": 0.3729749023914337,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 0.7616,
+      "step": 65
+    },
+    {
+      "epoch": 0.533737680060652,
+      "grad_norm": 0.3745996654033661,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 0.7703,
+      "step": 66
+    },
+    {
+      "epoch": 0.5418246146070256,
+      "grad_norm": 0.3874468505382538,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 0.7703,
+      "step": 67
+    },
+    {
+      "epoch": 0.549911549153399,
+      "grad_norm": 0.40286222100257874,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 0.7155,
+      "step": 68
+    },
+    {
+      "epoch": 0.5579984836997726,
+      "grad_norm": 0.3780246078968048,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 0.6842,
+      "step": 69
+    },
+    {
+      "epoch": 0.5660854182461461,
+      "grad_norm": 0.34932300448417664,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 0.6526,
+      "step": 70
+    },
+    {
+      "epoch": 0.5741723527925195,
+      "grad_norm": 0.37983378767967224,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 0.6156,
+      "step": 71
+    },
+    {
+      "epoch": 0.5822592873388931,
+      "grad_norm": 0.3535488545894623,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5966,
+      "step": 72
+    },
+    {
+      "epoch": 0.5903462218852666,
+      "grad_norm": 0.5434425473213196,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 0.7458,
+      "step": 73
+    },
+    {
+      "epoch": 0.5984331564316401,
+      "grad_norm": 0.37971338629722595,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 0.6074,
+      "step": 74
+    },
+    {
+      "epoch": 0.6065200909780136,
+      "grad_norm": 0.4319310188293457,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 0.5151,
+      "step": 75
+    },
+    {
+      "epoch": 0.6065200909780136,
+      "eval_loss": 0.6152855753898621,
+      "eval_runtime": 3.512,
+      "eval_samples_per_second": 14.237,
+      "eval_steps_per_second": 3.702,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.968083617316864e+17,
+  "total_flos": 8.952125425975296e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null