Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336349cdda9e552594efc596c1c8c81093535034cd5326ae7a1e5db7112ab287
+oid sha256:e428201636aa64c11c144521a9430fecbd72e6a371424359c31fe1b9f2a972f8
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05004a8fd6e5f98efaa8a79a7d4622594f30d45b1bf1d3f70017f28510d85e83
+oid sha256:c49d4c5c48d6c419ff5e0303478d2eed2704dc19a6fb2f98b31a70d9f9f8eeb6
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efca72e85f47c3412b8269c01893c0997c89bff5c55003771da72332cf48b74
+oid sha256:c8febc93c8fcf92d491ea7cbc1fc6a662583d43b0a72fdca3a550c194df77e11
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4841180974da24cb0c9ce1a2ad169bfb90c37460517a3ce06052b09a0edd78d
+oid sha256:1546f084086715834389ed44b67b814f6f5bab89ca6b7f34d2f9fff371fec01b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce7d20276c64c4aa56a5506733daad4cee09902505287ad9bd79e8ed7cdde7e
+oid sha256:5fb36110fbb4ceab5aed585179b989c3dfa9b30e9f9a16515cb89a59206f2c24
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05f5852112f6eb3a1deba045635ca49b48da54b7aada39a0e15ad89cbccd9bfb
+oid sha256:00fd78cb62810535d698a7649d511e7eb62caa553a8425ace6d6360f50039393
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd8b969ce6a3f06e5c06504065f43d471f4f8e360f2eb91a5068e5fed0b0d9dc
+oid sha256:344fc18df9c84f214bc47e69d1bbde70d66cf3ec6caeac9cd529dfb5814c4b9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5405478477478027,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.16059419853457793,
+  "best_metric": 0.3565179407596588,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.2408912978018669,
   "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": 99.187,
       "eval_steps_per_second": 25.789,
       "step": 50
+    },
+    {
+      "epoch": 0.16380608250526948,
+      "grad_norm": 4.038471698760986,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 0.8339,
+      "step": 51
+    },
+    {
+      "epoch": 0.16701796647596107,
+      "grad_norm": 2.3349921703338623,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 0.4534,
+      "step": 52
+    },
+    {
+      "epoch": 0.17022985044665262,
+      "grad_norm": 1.8736135959625244,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 0.4491,
+      "step": 53
+    },
+    {
+      "epoch": 0.17344173441734417,
+      "grad_norm": 2.2482573986053467,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 0.403,
+      "step": 54
+    },
+    {
+      "epoch": 0.17665361838803573,
+      "grad_norm": 1.4259393215179443,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 0.3789,
+      "step": 55
+    },
+    {
+      "epoch": 0.17986550235872728,
+      "grad_norm": 1.762160301208496,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 0.4335,
+      "step": 56
+    },
+    {
+      "epoch": 0.18307738632941886,
+      "grad_norm": 1.4867217540740967,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 0.42,
+      "step": 57
+    },
+    {
+      "epoch": 0.18628927030011042,
+      "grad_norm": 1.774482250213623,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 0.7633,
+      "step": 58
+    },
+    {
+      "epoch": 0.18950115427080197,
+      "grad_norm": 1.6524527072906494,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 0.3312,
+      "step": 59
+    },
+    {
+      "epoch": 0.19271303824149352,
+      "grad_norm": 1.7809213399887085,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 0.3048,
+      "step": 60
+    },
+    {
+      "epoch": 0.19592492221218508,
+      "grad_norm": 0.9493484497070312,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 0.2782,
+      "step": 61
+    },
+    {
+      "epoch": 0.19913680618287663,
+      "grad_norm": 1.6046050786972046,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.2086,
+      "step": 62
+    },
+    {
+      "epoch": 0.2023486901535682,
+      "grad_norm": 4.323451042175293,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 0.5269,
+      "step": 63
+    },
+    {
+      "epoch": 0.20556057412425977,
+      "grad_norm": 3.2167468070983887,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 0.5914,
+      "step": 64
+    },
+    {
+      "epoch": 0.20877245809495132,
+      "grad_norm": 2.5836000442504883,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 0.3979,
+      "step": 65
+    },
+    {
+      "epoch": 0.21198434206564287,
+      "grad_norm": 1.6577327251434326,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 0.2982,
+      "step": 66
+    },
+    {
+      "epoch": 0.21519622603633443,
+      "grad_norm": 1.7948780059814453,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 0.353,
+      "step": 67
+    },
+    {
+      "epoch": 0.218408110007026,
+      "grad_norm": 2.2538440227508545,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 0.4393,
+      "step": 68
+    },
+    {
+      "epoch": 0.22161999397771756,
+      "grad_norm": 1.4487870931625366,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 0.3644,
+      "step": 69
+    },
+    {
+      "epoch": 0.22483187794840911,
+      "grad_norm": 1.4857341051101685,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 0.5984,
+      "step": 70
+    },
+    {
+      "epoch": 0.22804376191910067,
+      "grad_norm": 1.458071231842041,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 0.4983,
+      "step": 71
+    },
+    {
+      "epoch": 0.23125564588979222,
+      "grad_norm": 1.4762952327728271,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 0.247,
+      "step": 72
+    },
+    {
+      "epoch": 0.2344675298604838,
+      "grad_norm": 1.1881077289581299,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 0.2679,
+      "step": 73
+    },
+    {
+      "epoch": 0.23767941383117536,
+      "grad_norm": 0.9410943984985352,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 0.1891,
+      "step": 74
+    },
+    {
+      "epoch": 0.2408912978018669,
+      "grad_norm": 1.873358964920044,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 0.2224,
+      "step": 75
+    },
+    {
+      "epoch": 0.2408912978018669,
+      "eval_loss": 0.3565179407596588,
+      "eval_runtime": 0.503,
+      "eval_samples_per_second": 99.395,
+      "eval_steps_per_second": 25.843,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.33416392081408e+16,
+  "total_flos": 1.250124588122112e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null