Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e003598caa526fb5635c4952935f8fd70bf457219d4a16646bcb452f2219d1b
+oid sha256:8238920631a86e097faa82c4096f3d72fb3c5efe2ed8e80f2225e8749836e755
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f38db2c0cccaceb489e9e4407d62163d6c42990b1297f80e35a46a181e722f59
+oid sha256:bc3bd533702ae9fc0c83a81b56a0a74f6e2254ba7f2e06d0767ae732cdc1f63c
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88089b75d6b623f34c98becff8927336b43ddcda017bf8dd6cdbc2ddbbe5dcbc
+oid sha256:3f04944917c15f265951392f0ad036c49b2e1d3572ae924179abc0eb1dc0ce1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9086689949035645,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.007217610970768676,
+  "best_metric": 0.8924118876457214,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.009022013713460845,
   "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": 4.188,
       "eval_steps_per_second": 2.096,
       "step": 20
+    },
+    {
+      "epoch": 0.007578491519307109,
+      "grad_norm": 2.8713228702545166,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 3.5997,
+      "step": 21
+    },
+    {
+      "epoch": 0.007939372067845544,
+      "grad_norm": 3.4211626052856445,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.1135,
+      "step": 22
+    },
+    {
+      "epoch": 0.008300252616383976,
+      "grad_norm": 4.066512584686279,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.6769,
+      "step": 23
+    },
+    {
+      "epoch": 0.00866113316492241,
+      "grad_norm": 3.9022419452667236,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 3.4745,
+      "step": 24
+    },
+    {
+      "epoch": 0.009022013713460845,
+      "grad_norm": 3.832505464553833,
+      "learning_rate": 0.0,
+      "loss": 3.1977,
+      "step": 25
+    },
+    {
+      "epoch": 0.009022013713460845,
+      "eval_loss": 0.8924118876457214,
+      "eval_runtime": 278.3819,
+      "eval_samples_per_second": 4.192,
+      "eval_steps_per_second": 2.098,
+      "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": 1.14112214335488e+16,
+  "total_flos": 1.4264026791936e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null