Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea1ce74696715d3659691f09607f581c981e2329ce5d44ba831b86338ddee39
+oid sha256:5609fc529a27d9029b91cbc1b6497a9f6481f3a1c180872608d28578468175b1
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6111af2dee0c909afe23aa3744430dadbeb084b03b9ff0ed9be45180cbbfa54a
+oid sha256:797695502e8e2360d028bb82c1f225c0abe7e4cb6deeb4f5e1c5dda05381c7a6
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:831b31121461f31f6507a3380cef073065ad0314f424afcbb9b85f91f34e8a9b
+oid sha256:03c1430c9d12a1d23e8e302b7d18d4a4a9c4a6d9b8a704442e85759e1c8af6c1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:289bb2feec78b3b33d6a6af2ac25f50a92dd602450a71eea31ef9baebba690fd
+oid sha256:8947b26818f2b48cdab60ac49e6850ac5a45983ddbc2e966334b654b665b5c81
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9136b3040d324d70638327d708b67ffa7e9431087c41b33fcfb4e1be3f4b951
+oid sha256:c02a3b615456816eafc7b2eae64c142b795e81886f3f5a6ae469c9925735b4b2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d402f15b66702a076df33d9aa00ac4344db6eba87375083d9fa39a4e6c490f2
+oid sha256:5086913c80ff6b019645ad90ab852cd887c7fcab5d8728794f65402e55991b67
 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": 1.9504194259643555,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.6099885627144491,
+  "best_metric": 1.6713114976882935,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.9149828440716736,
   "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": 35.151,
       "eval_steps_per_second": 9.139,
       "step": 50
+    },
+    {
+      "epoch": 0.6221883339687381,
+      "grad_norm": 0.9663915634155273,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 2.1974,
+      "step": 51
+    },
+    {
+      "epoch": 0.634388105223027,
+      "grad_norm": 0.9641888737678528,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 2.1838,
+      "step": 52
+    },
+    {
+      "epoch": 0.6465878764773161,
+      "grad_norm": 0.9429617524147034,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 2.0881,
+      "step": 53
+    },
+    {
+      "epoch": 0.658787647731605,
+      "grad_norm": 1.0586568117141724,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 2.0872,
+      "step": 54
+    },
+    {
+      "epoch": 0.670987418985894,
+      "grad_norm": 1.1340885162353516,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 1.8281,
+      "step": 55
+    },
+    {
+      "epoch": 0.683187190240183,
+      "grad_norm": 1.0865514278411865,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 1.7659,
+      "step": 56
+    },
+    {
+      "epoch": 0.695386961494472,
+      "grad_norm": 1.1755565404891968,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 1.8385,
+      "step": 57
+    },
+    {
+      "epoch": 0.7075867327487609,
+      "grad_norm": 1.297876238822937,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 1.9225,
+      "step": 58
+    },
+    {
+      "epoch": 0.7197865040030499,
+      "grad_norm": 1.1662304401397705,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 1.6643,
+      "step": 59
+    },
+    {
+      "epoch": 0.731986275257339,
+      "grad_norm": 1.3199200630187988,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 1.5546,
+      "step": 60
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 1.5923489332199097,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 1.3895,
+      "step": 61
+    },
+    {
+      "epoch": 0.7563858177659168,
+      "grad_norm": 2.492323398590088,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 1.2338,
+      "step": 62
+    },
+    {
+      "epoch": 0.7685855890202059,
+      "grad_norm": 1.8413420915603638,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 2.0796,
+      "step": 63
+    },
+    {
+      "epoch": 0.7807853602744949,
+      "grad_norm": 0.9823299050331116,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 1.9643,
+      "step": 64
+    },
+    {
+      "epoch": 0.7929851315287838,
+      "grad_norm": 1.094659686088562,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 1.9729,
+      "step": 65
+    },
+    {
+      "epoch": 0.8051849027830729,
+      "grad_norm": 1.1028552055358887,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 1.9267,
+      "step": 66
+    },
+    {
+      "epoch": 0.8173846740373618,
+      "grad_norm": 1.0977410078048706,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 1.7912,
+      "step": 67
+    },
+    {
+      "epoch": 0.8295844452916508,
+      "grad_norm": 1.102168083190918,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 1.7725,
+      "step": 68
+    },
+    {
+      "epoch": 0.8417842165459397,
+      "grad_norm": 1.1367805004119873,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 1.8996,
+      "step": 69
+    },
+    {
+      "epoch": 0.8539839878002288,
+      "grad_norm": 1.1765918731689453,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 1.6463,
+      "step": 70
+    },
+    {
+      "epoch": 0.8661837590545177,
+      "grad_norm": 1.2325594425201416,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 1.572,
+      "step": 71
+    },
+    {
+      "epoch": 0.8783835303088067,
+      "grad_norm": 1.403302550315857,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 1.6589,
+      "step": 72
+    },
+    {
+      "epoch": 0.8905833015630957,
+      "grad_norm": 1.3870701789855957,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 1.5272,
+      "step": 73
+    },
+    {
+      "epoch": 0.9027830728173847,
+      "grad_norm": 1.7309116125106812,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 1.2688,
+      "step": 74
+    },
+    {
+      "epoch": 0.9149828440716736,
+      "grad_norm": 3.672463893890381,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 0.656,
+      "step": 75
+    },
+    {
+      "epoch": 0.9149828440716736,
+      "eval_loss": 1.6713114976882935,
+      "eval_runtime": 1.4237,
+      "eval_samples_per_second": 35.12,
+      "eval_steps_per_second": 9.131,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.624057810649088e+17,
+  "total_flos": 8.436086715973632e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null