Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07d4669abcafa1e4ffd4094fd4dead1c5f5b255ef58535f18838a912a8520a35
+oid sha256:4157169bed0655deb96ca2b5ab37a8844007e96c7ad45e6e9c1a015803ceca5e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c7cbee7f44d5ac14bf7714106f89fce09244334f6ea9f68f24fcb21e4ef3d7c
+oid sha256:e6ef6cd70848fb738757e5d7c9f5b15c8017d42ef9a9cb54e5a2f3f86dcf8ef2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc3e5265caade9b4765ce3bea88afed07b875a6b1b6dbe83b1b96d505d55d4b
+oid sha256:c70a576494e56c909be11c04fa488ebbe191aee3195b0dd47c32f36094b31b77
 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": 1.7598896026611328,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.015958507879513265,
+  "best_metric": 1.7297241687774658,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.01994813484939158,
   "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": 6.835,
       "eval_steps_per_second": 3.418,
       "step": 20
+    },
+    {
+      "epoch": 0.016756433273488927,
+      "grad_norm": 3.4833950996398926,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 1.9758,
+      "step": 21
+    },
+    {
+      "epoch": 0.017554358667464593,
+      "grad_norm": 3.8444583415985107,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.025,
+      "step": 22
+    },
+    {
+      "epoch": 0.018352284061440256,
+      "grad_norm": 2.9565610885620117,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.6026,
+      "step": 23
+    },
+    {
+      "epoch": 0.019150209455415918,
+      "grad_norm": 3.334594964981079,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.9002,
+      "step": 24
+    },
+    {
+      "epoch": 0.01994813484939158,
+      "grad_norm": 2.8627727031707764,
+      "learning_rate": 0.0,
+      "loss": 1.4609,
+      "step": 25
+    },
+    {
+      "epoch": 0.01994813484939158,
+      "eval_loss": 1.7297241687774658,
+      "eval_runtime": 77.1994,
+      "eval_samples_per_second": 6.839,
+      "eval_steps_per_second": 3.42,
+      "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