Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd47d86e881fb12ad9ffde31595433fd7654602dd58f3fe783f727104b6088b
+oid sha256:671678d7dba30b87bcd3079e44864b61aed7cbf0eea9ac3e6ab102f9de913f6f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a15678ba41a8f6beb531b290dd308019a858fc1a2e01adbf2d471899b48ea49
+oid sha256:ebe3d2b023a8215f6a320e605916cba8ea44497d7bbe104b7acff0d799771c8f
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125190fa6b1731624b1f21747b3f0e6a0438fcc92470cacdee3800364f95b184
+oid sha256:0ea2a312f1b8c04a72fd99088711bbbc598702a183b1e975bfad4d3e09d41f45
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1784987449645996,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0013667270304438446,
+  "best_metric": 0.9468892216682434,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.002733454060887689,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 4.74,
       "eval_steps_per_second": 2.371,
       "step": 10
+    },
+    {
+      "epoch": 0.001503399733488229,
+      "grad_norm": 0.6936522126197815,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 1.0377,
+      "step": 11
+    },
+    {
+      "epoch": 0.0016400724365326135,
+      "grad_norm": 0.6066957116127014,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 1.1414,
+      "step": 12
+    },
+    {
+      "epoch": 0.001776745139576998,
+      "grad_norm": 1.024498701095581,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.9257,
+      "step": 13
+    },
+    {
+      "epoch": 0.0019134178426213825,
+      "grad_norm": 0.39579325914382935,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.7189,
+      "step": 14
+    },
+    {
+      "epoch": 0.002050090545665767,
+      "grad_norm": 0.5156039595603943,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.0717,
+      "step": 15
+    },
+    {
+      "epoch": 0.002050090545665767,
+      "eval_loss": 1.0189374685287476,
+      "eval_runtime": 651.4577,
+      "eval_samples_per_second": 4.729,
+      "eval_steps_per_second": 2.365,
+      "step": 15
+    },
+    {
+      "epoch": 0.0021867632487101514,
+      "grad_norm": 0.4737545847892761,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.9375,
+      "step": 16
+    },
+    {
+      "epoch": 0.002323435951754536,
+      "grad_norm": 0.37397414445877075,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.794,
+      "step": 17
+    },
+    {
+      "epoch": 0.0024601086547989203,
+      "grad_norm": 2.7903082370758057,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.8632,
+      "step": 18
+    },
+    {
+      "epoch": 0.0025967813578433047,
+      "grad_norm": 0.5934101343154907,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.7099,
+      "step": 19
+    },
+    {
+      "epoch": 0.002733454060887689,
+      "grad_norm": 0.43005478382110596,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.9802,
+      "step": 20
+    },
+    {
+      "epoch": 0.002733454060887689,
+      "eval_loss": 0.9468892216682434,
+      "eval_runtime": 652.2901,
+      "eval_samples_per_second": 4.723,
+      "eval_steps_per_second": 2.362,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3007276835143680.0,
+  "total_flos": 6138140389539840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null