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:dc4334b869811fe02e72806997caf2965c6515b94afe9fc88bb32759efa5e092
+oid sha256:08a1b623030be3f84515c8d31cbea9febd0d3163256609a84a3edc07a84f527d
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390e30ae50e39c9f218d126c25e349a51bdf12fe637c55b0f8d68ca93ddb98ac
+oid sha256:60a443becf3d37f60bce92f9eee07d6335fda3291d2de63cfe8dad41932d10f6
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be70d832a1bbff101f33c955af2006518b5495f9530a45087a280e66288a93d
+oid sha256:23ba6f4e1ddd9457b39425bc60bf390070addbb761f15a038321aac470417dab
 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": 1.903188705444336,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.019985011241568824,
+  "best_metric": 1.8866443634033203,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.02498126405196103,
   "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": 1.289,
       "eval_steps_per_second": 0.645,
       "step": 20
+    },
+    {
+      "epoch": 0.020984261803647264,
+      "grad_norm": 6.02990198135376,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 7.7003,
+      "step": 21
+    },
+    {
+      "epoch": 0.021983512365725707,
+      "grad_norm": 6.189011096954346,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 8.5614,
+      "step": 22
+    },
+    {
+      "epoch": 0.022982762927804146,
+      "grad_norm": 7.53192663192749,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 8.2399,
+      "step": 23
+    },
+    {
+      "epoch": 0.02398201348988259,
+      "grad_norm": 11.395584106445312,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 5.7759,
+      "step": 24
+    },
+    {
+      "epoch": 0.02498126405196103,
+      "grad_norm": 7.061837673187256,
+      "learning_rate": 0.0,
+      "loss": 6.8975,
+      "step": 25
+    },
+    {
+      "epoch": 0.02498126405196103,
+      "eval_loss": 1.8866443634033203,
+      "eval_runtime": 315.3013,
+      "eval_samples_per_second": 1.338,
+      "eval_steps_per_second": 0.669,
+      "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": 6332448610713600.0,
+  "total_flos": 7915560763392000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null