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:fbce135ef032e75c643ba14186dcf72a8481911f4ffe5e45e0676ffeacd227cc
+oid sha256:e25a34169bf69f684ab29af2083c0b0d3394199dbd3d4f8742a76bee13624092
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49fdcd936d4881d2ed8a7883609a3f112b3c50e04e0de8b368af654487da1768
+oid sha256:ffdb2007df072481443c9b669f6145cb9673a5da7b023032498921ab48c5d0ec
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c5eb4e32661bb720c3ed60226062cb92e22990153a3844a5d2bd718b78a2c9
+oid sha256:832c2c442cbf71daf394540d727b118ab5b6db1652a2abe4106d73ca87deac6e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1123dd497c9b8910fe9a2e80a4ab323c0694a06c711a817decbfc0ad393e20a4
+oid sha256:913ab8b0d366eeaae4f2a144c807ce2c591297e394af2372dd426dd4c3850119
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9906885623931885,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.5079825834542816,
+  "best_metric": 1.9605308771133423,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.5805515239477503,
   "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": 11.907,
       "eval_steps_per_second": 2.997,
       "step": 350
+    },
+    {
+      "epoch": 0.5224963715529753,
+      "grad_norm": 0.9822912812232971,
+      "learning_rate": 4.5623534490777714e-05,
+      "loss": 2.0033,
+      "step": 360
+    },
+    {
+      "epoch": 0.5370101596516691,
+      "grad_norm": 0.9240527153015137,
+      "learning_rate": 3.9779037303794365e-05,
+      "loss": 1.933,
+      "step": 370
+    },
+    {
+      "epoch": 0.5515239477503628,
+      "grad_norm": 1.1260921955108643,
+      "learning_rate": 3.42449822418582e-05,
+      "loss": 1.9529,
+      "step": 380
+    },
+    {
+      "epoch": 0.5660377358490566,
+      "grad_norm": 1.302894949913025,
+      "learning_rate": 2.9048330664949622e-05,
+      "loss": 1.9263,
+      "step": 390
+    },
+    {
+      "epoch": 0.5805515239477503,
+      "grad_norm": 2.6783480644226074,
+      "learning_rate": 2.4214400137185785e-05,
+      "loss": 1.8083,
+      "step": 400
+    },
+    {
+      "epoch": 0.5805515239477503,
+      "eval_loss": 1.9605308771133423,
+      "eval_runtime": 24.3765,
+      "eval_samples_per_second": 11.897,
+      "eval_steps_per_second": 2.995,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.041653262607974e+16,
+  "total_flos": 1.0333318014409114e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null