Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b165c57288b3a1cb87c459ca9217ab265550f0d9a0be4b03e47aea610cfe11da
+oid sha256:349b92fc771467ba19f4a4375705b0be18ee0a70d66dd5e9a3218efead140655
 size 891333320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8b527d3eca9fefe98f40ef8916f8d843e468b9d5861e46cd138601924c8cc76
+oid sha256:25b655e6762cc1be326580ea77e8423738abff3ab79f8450863570718360a4d6
 size 452984596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6c31fdd8582b45a066dc89e3f99ddd96bde609925f8b3ac71fe97a5f9c5e25
+oid sha256:100d6b5df23f5f5fd45227dfa104aadadc2938f6706932b75edbcb0c200c13d0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152cf5e1f9adf3dc2c608dbb3e394e09940ab42688cdb5a07d89f1cccb7f89a5
+oid sha256:d4d0f57336dd58c2282a758b1873df2644647c71e8296b0dab58cb3a9f5f7c78
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3859279751777649,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.04088307440719542,
+  "best_metric": 0.32411646842956543,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.08176614881439084,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 4.128,
       "eval_steps_per_second": 1.034,
       "step": 50
+    },
+    {
+      "epoch": 0.04905968928863451,
+      "grad_norm": 0.28594130277633667,
+      "learning_rate": 6.992307692307692e-06,
+      "loss": 0.4319,
+      "step": 60
+    },
+    {
+      "epoch": 0.05723630417007359,
+      "grad_norm": 0.6387773156166077,
+      "learning_rate": 6.215384615384615e-06,
+      "loss": 0.4787,
+      "step": 70
+    },
+    {
+      "epoch": 0.06541291905151267,
+      "grad_norm": 0.30498838424682617,
+      "learning_rate": 5.438461538461538e-06,
+      "loss": 0.5047,
+      "step": 80
+    },
+    {
+      "epoch": 0.07358953393295176,
+      "grad_norm": 0.15410414338111877,
+      "learning_rate": 4.661538461538462e-06,
+      "loss": 0.1164,
+      "step": 90
+    },
+    {
+      "epoch": 0.08176614881439084,
+      "grad_norm": 0.12575368583202362,
+      "learning_rate": 3.884615384615385e-06,
+      "loss": 0.0136,
+      "step": 100
+    },
+    {
+      "epoch": 0.08176614881439084,
+      "eval_loss": 0.32411646842956543,
+      "eval_runtime": 124.5506,
+      "eval_samples_per_second": 4.135,
+      "eval_steps_per_second": 1.036,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.27041523204096e+16,
+  "total_flos": 1.247192480219136e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null