Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359696a13c42066066590d817694b458e25e21c470d45d032fd0ec8eea14290b
+oid sha256:fbce135ef032e75c643ba14186dcf72a8481911f4ffe5e45e0676ffeacd227cc
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e449c02bae727997cf08fa1c0e54bf170591c31381c2033d81436862d01d3e08
+oid sha256:49fdcd936d4881d2ed8a7883609a3f112b3c50e04e0de8b368af654487da1768
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f072f97456ea81d819fde3e33fd5989f0b76463ed7ed0d88b79ae6ab014c50f
+oid sha256:b4c5eb4e32661bb720c3ed60226062cb92e22990153a3844a5d2bd718b78a2c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9ba82c4660fefa9fbbf06a718c7a06114d84fa536c01a280f55e7524e533da3
+oid sha256:1123dd497c9b8910fe9a2e80a4ab323c0694a06c711a817decbfc0ad393e20a4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.034973382949829,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.43541364296081275,
+  "best_metric": 1.9906885623931885,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.5079825834542816,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 11.807,
       "eval_steps_per_second": 2.972,
       "step": 300
+    },
+    {
+      "epoch": 0.44992743105950656,
+      "grad_norm": 0.9694491624832153,
+      "learning_rate": 7.84610838054344e-05,
+      "loss": 2.0345,
+      "step": 310
+    },
+    {
+      "epoch": 0.4644412191582003,
+      "grad_norm": 1.099524736404419,
+      "learning_rate": 7.151674108219295e-05,
+      "loss": 1.991,
+      "step": 320
+    },
+    {
+      "epoch": 0.47895500725689405,
+      "grad_norm": 1.2441976070404053,
+      "learning_rate": 6.472821758145309e-05,
+      "loss": 2.0073,
+      "step": 330
+    },
+    {
+      "epoch": 0.4934687953555878,
+      "grad_norm": 1.3850934505462646,
+      "learning_rate": 5.8128586307330475e-05,
+      "loss": 2.0145,
+      "step": 340
+    },
+    {
+      "epoch": 0.5079825834542816,
+      "grad_norm": 3.0692977905273438,
+      "learning_rate": 5.175000000000002e-05,
+      "loss": 1.9566,
+      "step": 350
+    },
+    {
+      "epoch": 0.5079825834542816,
+      "eval_loss": 1.9906885623931885,
+      "eval_runtime": 24.3553,
+      "eval_samples_per_second": 11.907,
+      "eval_steps_per_second": 2.997,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.749988510806835e+16,
+  "total_flos": 9.041653262607974e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null