Training in progress, step 309, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a518a594168876a8907e142a5ec101420b772f7d4a4d1033df583177b4e92cd3
+oid sha256:0b1bd90d6e372f45800ceac53c536142c3ee30347ead05d2e23a2b902be42689
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dffda1d4ace02ebb6c8b05443e8e249ede4e48325ec8a300481437db3ac4314c
+oid sha256:d0ad20e2f09232e22dff7b31a82c489a47c66c3f569e80a704ef610687fd1984
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51cf95d40bcc1d1c9a2583de6235211d4a201114723d69666b6435f8fbdee579
+oid sha256:aa0d68e5dd2d58bdc87345576f2f74dc9651c98d7b5f3d0e037c2696583bab96
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1661baebacd5f03a5441403c0632d52750084c359c58314f3911ce2808755a25
+oid sha256:979dde1f0d281eb2dc3958f83b783edeadae178d67f76589e69c962081c16466
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4889930784702301,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.9732360097323601,
+  "epoch": 1.002433090024331,
   "eval_steps": 100,
-  "global_step": 300,
+  "global_step": 309,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2139,6 +2139,69 @@
       "eval_samples_per_second": 7.196,
       "eval_steps_per_second": 1.803,
       "step": 300
+    },
+    {
+      "epoch": 0.9764801297648013,
+      "grad_norm": 1.423581600189209,
+      "learning_rate": 1.889514885109689e-07,
+      "loss": 0.5293,
+      "step": 301
+    },
+    {
+      "epoch": 0.9797242497972425,
+      "grad_norm": 0.757242739200592,
+      "learning_rate": 1.4468735616587904e-07,
+      "loss": 0.4023,
+      "step": 302
+    },
+    {
+      "epoch": 0.9829683698296837,
+      "grad_norm": 1.0456199645996094,
+      "learning_rate": 1.0631452502237737e-07,
+      "loss": 0.7101,
+      "step": 303
+    },
+    {
+      "epoch": 0.986212489862125,
+      "grad_norm": 0.8465937376022339,
+      "learning_rate": 7.383752952010992e-08,
+      "loss": 0.333,
+      "step": 304
+    },
+    {
+      "epoch": 0.9894566098945661,
+      "grad_norm": 0.9582859873771667,
+      "learning_rate": 4.7260207399774105e-08,
+      "loss": 0.5266,
+      "step": 305
+    },
+    {
+      "epoch": 0.9927007299270073,
+      "grad_norm": 0.9226927757263184,
+      "learning_rate": 2.6585699249642716e-08,
+      "loss": 0.3913,
+      "step": 306
+    },
+    {
+      "epoch": 0.9959448499594485,
+      "grad_norm": 0.7818783521652222,
+      "learning_rate": 1.181644813441074e-08,
+      "loss": 0.4817,
+      "step": 307
+    },
+    {
+      "epoch": 0.9991889699918897,
+      "grad_norm": 0.7689955234527588,
+      "learning_rate": 2.9541993065373976e-09,
+      "loss": 0.3477,
+      "step": 308
+    },
+    {
+      "epoch": 1.002433090024331,
+      "grad_norm": 1.9308133125305176,
+      "learning_rate": 0.0,
+      "loss": 1.2261,
+      "step": 309
     }
   ],
   "logging_steps": 1,
@@ -2162,12 +2225,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.011444759397663e+17,
+  "total_flos": 4.133268278728458e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null