Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41013d67c2894365b1744d3213536ab9f340e0dd6210e2adb0c7f32b73160d37
+oid sha256:7aaa39214ca050f54ac1bc3faa35b4e17f32d60fdfd1448d3fa427972caeab53
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77c813b8ebeac5d9bb131be6ba2116acd5558040a69c763b3f56d09ef6ede2c
+oid sha256:408fc7e1cfcccbd01a534e8797503f14942d3b639b37e0e778195ae8124318fe
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c8cc9090b5cc5d4b4246c49707d356f87bdf6b8f409039134d01740469d1b72
+oid sha256:e224c14664601a8f0eb60590a28a54e325cd887941e1d119e02e8c408128fff3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4c15c93e093cba090b2f3583592294b602741c9988a1980b16636e603079f25
+oid sha256:2c0c9560ea4ec378bff0927b20fa3ef4645adc76e93a49024ae06865cbf33e40
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.359244704246521,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.12874747103181902,
+  "best_metric": 1.332943081855774,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.14713996689350745,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 17.547,
       "eval_steps_per_second": 4.398,
       "step": 350
+    },
+    {
+      "epoch": 0.1324259702041567,
+      "grad_norm": 0.766905665397644,
+      "learning_rate": 4.430111320118996e-05,
+      "loss": 1.451,
+      "step": 360
+    },
+    {
+      "epoch": 0.1361044693764944,
+      "grad_norm": 0.7716265916824341,
+      "learning_rate": 3.862602172977134e-05,
+      "loss": 1.4025,
+      "step": 370
+    },
+    {
+      "epoch": 0.13978296854883207,
+      "grad_norm": 0.7445082664489746,
+      "learning_rate": 3.325237406093478e-05,
+      "loss": 1.2896,
+      "step": 380
+    },
+    {
+      "epoch": 0.14346146772116977,
+      "grad_norm": 0.8825977444648743,
+      "learning_rate": 2.820635006596558e-05,
+      "loss": 1.3365,
+      "step": 390
+    },
+    {
+      "epoch": 0.14713996689350745,
+      "grad_norm": 1.0006340742111206,
+      "learning_rate": 2.351253346654272e-05,
+      "loss": 1.2482,
+      "step": 400
+    },
+    {
+      "epoch": 0.14713996689350745,
+      "eval_loss": 1.332943081855774,
+      "eval_runtime": 65.309,
+      "eval_samples_per_second": 17.532,
+      "eval_steps_per_second": 4.394,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.2207629983744e+16,
+  "total_flos": 7.1094434267136e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null