Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2947addefa03503377e78af6e3a7c56cc29b7a2459f6f929a1018c8eeeee10
+oid sha256:7094d3d35c8ca23585deea11e4aa1f2ca60b6d007a7a663b93596d075b57a062
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6df24dc4990af01f4e2532bea5ce0de0ffc3e945e702958a74ab609adcc04a3b
+oid sha256:9734fa4dcf0a57560f0298168e55201edf7508aaca64180275d8a93ac628bf00
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62e73e6ad19948579779ff6a1c72ee669ed031d5b3a303d2977d967d47ff1e3c
+oid sha256:d6dcbdad252c7f7c65f0d0f167ff9a58b5a6d000a3ecfd1729496cbbff340bde
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.4954330921173096,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.009416195856873822,
+  "best_metric": 3.461520195007324,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.014124293785310734,
   "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": 4.283,
       "eval_steps_per_second": 2.144,
       "step": 20
+    },
+    {
+      "epoch": 0.009887005649717515,
+      "grad_norm": 2.2122228145599365,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 3.4689,
+      "step": 21
+    },
+    {
+      "epoch": 0.011299435028248588,
+      "grad_norm": 2.0522589683532715,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 3.3605,
+      "step": 24
+    },
+    {
+      "epoch": 0.011770244821092278,
+      "eval_loss": 3.4695844650268555,
+      "eval_runtime": 209.3727,
+      "eval_samples_per_second": 4.275,
+      "eval_steps_per_second": 2.14,
+      "step": 25
+    },
+    {
+      "epoch": 0.012711864406779662,
+      "grad_norm": 2.119175910949707,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 3.6951,
+      "step": 27
+    },
+    {
+      "epoch": 0.014124293785310734,
+      "grad_norm": 2.415921211242676,
+      "learning_rate": 0.0,
+      "loss": 3.4002,
+      "step": 30
+    },
+    {
+      "epoch": 0.014124293785310734,
+      "eval_loss": 3.461520195007324,
+      "eval_runtime": 209.0434,
+      "eval_samples_per_second": 4.281,
+      "eval_steps_per_second": 2.143,
+      "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": 8581442955116544.0,
+  "total_flos": 1.2819192562581504e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null