Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3156371f18912efe9870f8d597cf8bf2f37de2339a0d2f009df115d47ceedbc1
+oid sha256:3fb066f837feb309a9345b4330875b8f60d476b689ddc09d909f541ee0dd0ecd
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:530d376e951a9d7026ba0125c54fcd3d684dabfc39e53e82b04a9a031d4d83ef
+oid sha256:b18ec58fa0effd8f5242ba815e317d2a9e6195e6e7a5c4a56bf8ee8a8f70c292
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c15e094d65a2a04ddf2ebcfc5ab4b15c91e3bbc100ae81a10baa00a1c5a4f71
+oid sha256:5158c5dcc45e6f02a0349d4271d805a52895514480d8e78ac07d853e7dff1486
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28db7b94298edfbbdbc29b237ba07b0fdc1211300bc39385315854d1fbbaee49
+oid sha256:c1eee0fd2d2974b84b078b434bb0036fd3078ec186a77bdb87082f41870f64ce
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587da782b6c5f0e8b2fa4d8896a929f45313deb0b7da2c24c2393a205fef0714
+oid sha256:cf30240cb2cc292bee74e6a12d06bdb9a4ffaf9f8edfd69df4b993469e6d0965
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c43dbd13f8f0564355267a63b86c95dffdc4512d80a63ba57b940fa2854a463
+oid sha256:c391c69d79ba0aee3d534303170439a8026fed6aa993973ec32d292fa38bf783
 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": 0.22515492141246796,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.30337504740235116,
+  "best_metric": 0.21727269887924194,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.4550625711035267,
   "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": 12.409,
       "eval_steps_per_second": 3.226,
       "step": 50
+    },
+    {
+      "epoch": 0.3094425483503982,
+      "grad_norm": 0.46408069133758545,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 0.2074,
+      "step": 51
+    },
+    {
+      "epoch": 0.3155100492984452,
+      "grad_norm": 0.3362777531147003,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 0.2881,
+      "step": 52
+    },
+    {
+      "epoch": 0.3215775502464922,
+      "grad_norm": 0.33510658144950867,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 0.2266,
+      "step": 53
+    },
+    {
+      "epoch": 0.32764505119453924,
+      "grad_norm": 0.5662570595741272,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 0.2653,
+      "step": 54
+    },
+    {
+      "epoch": 0.33371255214258627,
+      "grad_norm": 0.7332994937896729,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 0.3039,
+      "step": 55
+    },
+    {
+      "epoch": 0.3397800530906333,
+      "grad_norm": 0.45034223794937134,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 0.2767,
+      "step": 56
+    },
+    {
+      "epoch": 0.34584755403868034,
+      "grad_norm": 0.36071422696113586,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 0.2616,
+      "step": 57
+    },
+    {
+      "epoch": 0.3519150549867273,
+      "grad_norm": 0.38735389709472656,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 0.2729,
+      "step": 58
+    },
+    {
+      "epoch": 0.35798255593477435,
+      "grad_norm": 0.3561176657676697,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 0.2106,
+      "step": 59
+    },
+    {
+      "epoch": 0.3640500568828214,
+      "grad_norm": 0.430941104888916,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 0.285,
+      "step": 60
+    },
+    {
+      "epoch": 0.3701175578308684,
+      "grad_norm": 0.622871994972229,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 0.3367,
+      "step": 61
+    },
+    {
+      "epoch": 0.37618505877891545,
+      "grad_norm": 1.2697404623031616,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 0.3697,
+      "step": 62
+    },
+    {
+      "epoch": 0.3822525597269625,
+      "grad_norm": 0.40310418605804443,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 0.1306,
+      "step": 63
+    },
+    {
+      "epoch": 0.38832006067500946,
+      "grad_norm": 0.2851163148880005,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 0.2808,
+      "step": 64
+    },
+    {
+      "epoch": 0.3943875616230565,
+      "grad_norm": 0.2384623885154724,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 0.2313,
+      "step": 65
+    },
+    {
+      "epoch": 0.4004550625711035,
+      "grad_norm": 0.24203841388225555,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 0.2467,
+      "step": 66
+    },
+    {
+      "epoch": 0.40652256351915056,
+      "grad_norm": 0.2760860323905945,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 0.2661,
+      "step": 67
+    },
+    {
+      "epoch": 0.4125900644671976,
+      "grad_norm": 0.3492850959300995,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 0.2071,
+      "step": 68
+    },
+    {
+      "epoch": 0.41865756541524457,
+      "grad_norm": 0.463875412940979,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 0.2345,
+      "step": 69
+    },
+    {
+      "epoch": 0.4247250663632916,
+      "grad_norm": 0.34055763483047485,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 0.2777,
+      "step": 70
+    },
+    {
+      "epoch": 0.43079256731133864,
+      "grad_norm": 0.3323991894721985,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 0.2575,
+      "step": 71
+    },
+    {
+      "epoch": 0.43686006825938567,
+      "grad_norm": 0.43374085426330566,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.2336,
+      "step": 72
+    },
+    {
+      "epoch": 0.4429275692074327,
+      "grad_norm": 0.45842763781547546,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 0.2808,
+      "step": 73
+    },
+    {
+      "epoch": 0.44899507015547974,
+      "grad_norm": 0.5284908413887024,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 0.3155,
+      "step": 74
+    },
+    {
+      "epoch": 0.4550625711035267,
+      "grad_norm": 0.6865499019622803,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 0.237,
+      "step": 75
+    },
+    {
+      "epoch": 0.4550625711035267,
+      "eval_loss": 0.21727269887924194,
+      "eval_runtime": 4.0624,
+      "eval_samples_per_second": 12.308,
+      "eval_steps_per_second": 3.2,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.174479344467968e+17,
+  "total_flos": 9.261719016701952e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null