Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8240f519392129a19102ff04c9add810864f445ee1f8dac2ff3faf28b901893c
+oid sha256:d707b8a24c3c9434d33a3fd7ab5eec62bf9b56ce96fc618ea811971432b221e4
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a53e70c0226d912e793c6d94377401d17b136c90cb79e805e5fe0316b3f444e
+oid sha256:f845052071d557b8c2b7535318c71846ebbbed85f3906d3e8c2ed9e52cb12613
 size 445835066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e31a45a8095a57ba97d7f9515c49fa268d5f648d3f99241bdc55f4bf0e98b1
+oid sha256:7491a1e803c9763a09bd346725e94118d07e2415eb07d8a04698304a2d1ec050
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2484335899353027,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0034278858514011482,
+  "best_metric": 1.2236804962158203,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.005141828777101723,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 4.184,
       "eval_steps_per_second": 2.093,
       "step": 20
+    },
+    {
+      "epoch": 0.003599280143971206,
+      "grad_norm": 1.8467648029327393,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 4.9633,
+      "step": 21
+    },
+    {
+      "epoch": 0.004113463021681378,
+      "grad_norm": 1.0094811916351318,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 4.9854,
+      "step": 24
+    },
+    {
+      "epoch": 0.004284857314251435,
+      "eval_loss": 1.2274752855300903,
+      "eval_runtime": 589.1454,
+      "eval_samples_per_second": 4.17,
+      "eval_steps_per_second": 2.086,
+      "step": 25
+    },
+    {
+      "epoch": 0.0046276458993915505,
+      "grad_norm": 1.3172191381454468,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 4.8362,
+      "step": 27
+    },
+    {
+      "epoch": 0.005141828777101723,
+      "grad_norm": 5.663494110107422,
+      "learning_rate": 0.0,
+      "loss": 4.8685,
+      "step": 30
+    },
+    {
+      "epoch": 0.005141828777101723,
+      "eval_loss": 1.2236804962158203,
+      "eval_runtime": 587.2261,
+      "eval_samples_per_second": 4.184,
+      "eval_steps_per_second": 2.093,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.361684987904e+16,
+  "total_flos": 2.0935906689024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null