Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43ab0107df543e535c4293e0be8a9acf7f28451b2be4fd430922587acd84a2a7
+oid sha256:7d9cc9defeb61e377a87bce7bb056c8e061f32996d64729a91a1156053beea7e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9770be047cb804cb2bf5436de8c99a17024ddd77f060bf17b0e85793c09efaaa
+oid sha256:c046d3abcebed63fa5e418102c9755ef524e801ba31f70bb4691ca1ad1c94e13
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eff7fd73f973e46014ca0cba260ef1bf771431578dfc80d8fcdb5d9fe1ecc859
+oid sha256:315f214c6e0b8fd03acec16280ddc948e89968dbe8e150005ce6867f765b6871
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d5f342d4229a407b143249c0b0919abc73174c3fbf690cf4dd4451580b8e09
+oid sha256:41e83f307180ac8f488ffa5d12e6485869ba276842bbc2776b54d5f280df42a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4073567390441895,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.004402135035492214,
+  "best_metric": 1.3910977840423584,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.005502668794365267,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 8.031,
       "eval_steps_per_second": 4.017,
       "step": 20
+    },
+    {
+      "epoch": 0.004622241787266825,
+      "grad_norm": 1.278303623199463,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 1.3414,
+      "step": 21
+    },
+    {
+      "epoch": 0.004842348539041435,
+      "grad_norm": 1.280018925666809,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 1.3812,
+      "step": 22
+    },
+    {
+      "epoch": 0.005062455290816046,
+      "grad_norm": 1.2225253582000732,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 1.2927,
+      "step": 23
+    },
+    {
+      "epoch": 0.005282562042590657,
+      "grad_norm": 1.431139588356018,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 1.2481,
+      "step": 24
+    },
+    {
+      "epoch": 0.005502668794365267,
+      "grad_norm": 1.0689414739608765,
+      "learning_rate": 0.0,
+      "loss": 1.1105,
+      "step": 25
+    },
+    {
+      "epoch": 0.005502668794365267,
+      "eval_loss": 1.3910977840423584,
+      "eval_runtime": 238.3074,
+      "eval_samples_per_second": 8.027,
+      "eval_steps_per_second": 4.016,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3699128496291840.0,
+  "total_flos": 4623910620364800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null