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:adb312be6206f60dd28261fd0f5b769f34530c6224e72d716e40c0e519253a6f
+oid sha256:58c7afebbfcd2272fe3ced345d78d01f67b098c7dd2d5e2ec111a0d4e8093d45
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:831f189361f8088ed0efbbc3f1b8e2581eced35dc9eae9feb52aeae19d3dc4bc
+oid sha256:344af2874827af47304d72154c92ad1fa8b3f690630a48729dc1fb804dff828f
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81a6fb9fbf6fb764770b1d55886ab375d8f18ad58d8f9099209dec1696d8d473
+oid sha256:87bd120fd086c25fbfec9308dc91d25a3b4d47ca2917fa43a04ce165b330b5c6
 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": 1.6313807964324951,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.007739938080495356,
+  "best_metric": 1.5969746112823486,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.015479876160990712,
   "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": 4.396,
       "eval_steps_per_second": 2.202,
       "step": 10
+    },
+    {
+      "epoch": 0.008513931888544891,
+      "grad_norm": 0.5993853807449341,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 4.7124,
+      "step": 11
+    },
+    {
+      "epoch": 0.009287925696594427,
+      "grad_norm": 0.98615562915802,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 9.0319,
+      "step": 12
+    },
+    {
+      "epoch": 0.010061919504643963,
+      "grad_norm": 0.7699627876281738,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 8.72,
+      "step": 13
+    },
+    {
+      "epoch": 0.010835913312693499,
+      "grad_norm": 0.905797004699707,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 6.5687,
+      "step": 14
+    },
+    {
+      "epoch": 0.011609907120743035,
+      "grad_norm": 0.6917111873626709,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 7.6529,
+      "step": 15
+    },
+    {
+      "epoch": 0.011609907120743035,
+      "eval_loss": 1.6112371683120728,
+      "eval_runtime": 124.5295,
+      "eval_samples_per_second": 4.376,
+      "eval_steps_per_second": 2.192,
+      "step": 15
+    },
+    {
+      "epoch": 0.01238390092879257,
+      "grad_norm": 0.8985219597816467,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 8.5202,
+      "step": 16
+    },
+    {
+      "epoch": 0.013157894736842105,
+      "grad_norm": 0.7589756846427917,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 6.8425,
+      "step": 17
+    },
+    {
+      "epoch": 0.01393188854489164,
+      "grad_norm": 0.8652344346046448,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 7.2533,
+      "step": 18
+    },
+    {
+      "epoch": 0.014705882352941176,
+      "grad_norm": 1.1718361377716064,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 7.3282,
+      "step": 19
+    },
+    {
+      "epoch": 0.015479876160990712,
+      "grad_norm": 1.478440761566162,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 6.26,
+      "step": 20
+    },
+    {
+      "epoch": 0.015479876160990712,
+      "eval_loss": 1.5969746112823486,
+      "eval_runtime": 125.3564,
+      "eval_samples_per_second": 4.348,
+      "eval_steps_per_second": 2.178,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2931748635672576.0,
+  "total_flos": 5904216002396160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null