Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48173c29d0a53283a5158e2c6ab9797bbafebc851d778afbcb059be419f05f2b
+oid sha256:b2bb40be6ef37d52c7142510f189c88b37f8b1b56786b5d2aec7683a25ab42f0
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3861dea34353a92f4697d99937718b7610b9f966fb41c666c48b2577eb4d4917
+oid sha256:68f53f39e1aca6c59aa7c903b32158fc5824f7bbe694cd69a6447a94bea6e67f
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46addfbda18ff9b9d337346f94fecc408cd80c4f43db25ec1e2a3edb89fa2812
+oid sha256:ca49ab65bc1f6b6e07a97baa271a253688e0cd7d7efd3a4371213104279c9d5b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13db002787eac5a3b1c72fd53ac7834264c174ccf89cfc8a2c85e4a987ea8b10
+oid sha256:6354288372ec961a9b0cc33d2b16655aaac558d6208ab9ccac75884d564931be
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08781b30a125ec9b2724f5e03ab0bc7c81ae341b2bbd45f22c85b375ddc24121
+oid sha256:efef25ea44167287ea83f901a104708084b2ee418ef06071a5130357832811a4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab9f9902a18b8b1bd915728ddbcce202e1e9dcab3162ea192d8d302398b4addc
+oid sha256:da7a9ebb8478fa6f89c015f2effdf33c84b179de45b0282ba1809736c74f1a8c
 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": 0.5248658061027527,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.7881773399014779,
+  "best_metric": 0.3735887110233307,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 1.1822660098522166,
   "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": 71.202,
       "eval_steps_per_second": 18.513,
       "step": 50
+    },
+    {
+      "epoch": 0.8039408866995074,
+      "grad_norm": 7.980965614318848,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 0.5778,
+      "step": 51
+    },
+    {
+      "epoch": 0.819704433497537,
+      "grad_norm": 4.428957462310791,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 0.5315,
+      "step": 52
+    },
+    {
+      "epoch": 0.8354679802955665,
+      "grad_norm": 4.525695323944092,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 0.4983,
+      "step": 53
+    },
+    {
+      "epoch": 0.8512315270935961,
+      "grad_norm": 1.8734763860702515,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 0.4634,
+      "step": 54
+    },
+    {
+      "epoch": 0.8669950738916257,
+      "grad_norm": 3.463655948638916,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 0.4803,
+      "step": 55
+    },
+    {
+      "epoch": 0.8827586206896552,
+      "grad_norm": 3.0169169902801514,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 0.4406,
+      "step": 56
+    },
+    {
+      "epoch": 0.8985221674876848,
+      "grad_norm": 3.7181005477905273,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 0.5167,
+      "step": 57
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 2.4602622985839844,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 0.4639,
+      "step": 58
+    },
+    {
+      "epoch": 0.9300492610837439,
+      "grad_norm": 3.199212074279785,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 0.4315,
+      "step": 59
+    },
+    {
+      "epoch": 0.9458128078817734,
+      "grad_norm": 4.430737495422363,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 0.5223,
+      "step": 60
+    },
+    {
+      "epoch": 0.961576354679803,
+      "grad_norm": 7.746757507324219,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 0.4648,
+      "step": 61
+    },
+    {
+      "epoch": 0.9773399014778326,
+      "grad_norm": 7.860967636108398,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.4422,
+      "step": 62
+    },
+    {
+      "epoch": 0.993103448275862,
+      "grad_norm": 1.5262166261672974,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 0.4396,
+      "step": 63
+    },
+    {
+      "epoch": 1.0088669950738915,
+      "grad_norm": 12.424480438232422,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 0.7924,
+      "step": 64
+    },
+    {
+      "epoch": 1.0246305418719213,
+      "grad_norm": 7.300468444824219,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 0.5098,
+      "step": 65
+    },
+    {
+      "epoch": 1.0403940886699508,
+      "grad_norm": 6.1646599769592285,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 0.4455,
+      "step": 66
+    },
+    {
+      "epoch": 1.0561576354679802,
+      "grad_norm": 3.547170639038086,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 0.4332,
+      "step": 67
+    },
+    {
+      "epoch": 1.07192118226601,
+      "grad_norm": 2.7341320514678955,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 0.3857,
+      "step": 68
+    },
+    {
+      "epoch": 1.0876847290640395,
+      "grad_norm": 2.705845355987549,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 0.4454,
+      "step": 69
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 5.191798210144043,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 0.4356,
+      "step": 70
+    },
+    {
+      "epoch": 1.1192118226600984,
+      "grad_norm": 1.7099392414093018,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 0.4155,
+      "step": 71
+    },
+    {
+      "epoch": 1.1349753694581282,
+      "grad_norm": 4.040687561035156,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 0.4195,
+      "step": 72
+    },
+    {
+      "epoch": 1.1507389162561577,
+      "grad_norm": 5.240128517150879,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 0.4251,
+      "step": 73
+    },
+    {
+      "epoch": 1.1665024630541871,
+      "grad_norm": 4.154675483703613,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 0.4514,
+      "step": 74
+    },
+    {
+      "epoch": 1.1822660098522166,
+      "grad_norm": 2.458857536315918,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 0.3418,
+      "step": 75
+    },
+    {
+      "epoch": 1.1822660098522166,
+      "eval_loss": 0.3735887110233307,
+      "eval_runtime": 0.7016,
+      "eval_samples_per_second": 71.267,
+      "eval_steps_per_second": 18.53,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.589463780163584e+17,
+  "total_flos": 2.384195670245376e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null