Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72242482b824bcdca1f05e3d1d8f3cbfe9d8f1339454688c13bdab9f685c964a
+oid sha256:bf6e2f34a437cc812d80116db6b3f6e3dc9249735fccac25dbd833e0efd52047
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a3562f466114e028e0729dda48969f0a0a670bc33fc2f42cf2dc56d8879a82
+oid sha256:9563cf1303015f1e47633400eae256015b83d96252d08ebcc19ef3cda9b40f61
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90d9f0dcae7eb5ce87a182da0a575715ff4041fc8ddb1a069df406d2e9bcd6ed
+oid sha256:0de426bbc15c4be72c228cb80b9966550032ee81fc5c4e878ea4f3eb899834a5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cfe6796d5075727a90ba1381a912c320008c4a75cf7e5e7d94bf36ba4afa0b
+oid sha256:b3d8e68d636d47c3f5773c1481f02bce82a8857eb226987ac68f9c7a6f67f325
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:666d77a624b162688d909792e389bb2bc847b8e6590c677ae903379833dd52d0
+oid sha256:dee9c227f27343b1cf7e8f5f80fa67616152e754a3450fbcc9e0304b2966329c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2cc91e2446161fb9b74ee57e288c7f0c165de126559b0a66afdbd77e9053422
+oid sha256:bff30627bbe4a5a58431dc59129643ab4793b7f03955eaf533bbb2f129b58445
 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": 0.7424139976501465,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.07923930269413629,
+  "best_metric": 0.7020787596702576,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.11885895404120443,
   "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": 15.234,
       "eval_steps_per_second": 3.961,
       "step": 50
+    },
+    {
+      "epoch": 0.08082408874801902,
+      "grad_norm": 0.706727921962738,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 0.9714,
+      "step": 51
+    },
+    {
+      "epoch": 0.08240887480190175,
+      "grad_norm": 0.6248128414154053,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 0.7904,
+      "step": 52
+    },
+    {
+      "epoch": 0.08399366085578447,
+      "grad_norm": 0.6073558330535889,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 0.7816,
+      "step": 53
+    },
+    {
+      "epoch": 0.08557844690966719,
+      "grad_norm": 0.5754700899124146,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 0.7652,
+      "step": 54
+    },
+    {
+      "epoch": 0.08716323296354993,
+      "grad_norm": 0.5993666052818298,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 0.7248,
+      "step": 55
+    },
+    {
+      "epoch": 0.08874801901743265,
+      "grad_norm": 0.645228922367096,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 0.8138,
+      "step": 56
+    },
+    {
+      "epoch": 0.09033280507131537,
+      "grad_norm": 0.825614869594574,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 0.5822,
+      "step": 57
+    },
+    {
+      "epoch": 0.0919175911251981,
+      "grad_norm": 0.6977015733718872,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 0.6557,
+      "step": 58
+    },
+    {
+      "epoch": 0.09350237717908082,
+      "grad_norm": 0.8051120638847351,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 0.6739,
+      "step": 59
+    },
+    {
+      "epoch": 0.09508716323296355,
+      "grad_norm": 0.9124981164932251,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 0.6184,
+      "step": 60
+    },
+    {
+      "epoch": 0.09667194928684628,
+      "grad_norm": 1.1939939260482788,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 0.6686,
+      "step": 61
+    },
+    {
+      "epoch": 0.098256735340729,
+      "grad_norm": 1.1615188121795654,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 0.5636,
+      "step": 62
+    },
+    {
+      "epoch": 0.09984152139461172,
+      "grad_norm": 0.9352508187294006,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 0.6433,
+      "step": 63
+    },
+    {
+      "epoch": 0.10142630744849446,
+      "grad_norm": 0.5545775890350342,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 0.8057,
+      "step": 64
+    },
+    {
+      "epoch": 0.10301109350237718,
+      "grad_norm": 0.6947957873344421,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 0.7252,
+      "step": 65
+    },
+    {
+      "epoch": 0.1045958795562599,
+      "grad_norm": 0.5455904603004456,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 0.6677,
+      "step": 66
+    },
+    {
+      "epoch": 0.10618066561014262,
+      "grad_norm": 0.6412747502326965,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 0.7173,
+      "step": 67
+    },
+    {
+      "epoch": 0.10776545166402536,
+      "grad_norm": 0.5318034887313843,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 0.5931,
+      "step": 68
+    },
+    {
+      "epoch": 0.10935023771790808,
+      "grad_norm": 0.6276905536651611,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 0.7394,
+      "step": 69
+    },
+    {
+      "epoch": 0.1109350237717908,
+      "grad_norm": 0.6510589122772217,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 0.6478,
+      "step": 70
+    },
+    {
+      "epoch": 0.11251980982567353,
+      "grad_norm": 0.6245140433311462,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 0.5465,
+      "step": 71
+    },
+    {
+      "epoch": 0.11410459587955626,
+      "grad_norm": 0.7210938334465027,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5694,
+      "step": 72
+    },
+    {
+      "epoch": 0.11568938193343899,
+      "grad_norm": 0.6950007677078247,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 0.5108,
+      "step": 73
+    },
+    {
+      "epoch": 0.11727416798732171,
+      "grad_norm": 0.887366771697998,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 0.4886,
+      "step": 74
+    },
+    {
+      "epoch": 0.11885895404120443,
+      "grad_norm": 1.3450919389724731,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 0.5812,
+      "step": 75
+    },
+    {
+      "epoch": 0.11885895404120443,
+      "eval_loss": 0.7020787596702576,
+      "eval_runtime": 3.311,
+      "eval_samples_per_second": 15.101,
+      "eval_steps_per_second": 3.926,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.32019209568256e+17,
+  "total_flos": 7.98028814352384e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null