Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc4489d70caa047c9a554ce661c2555d55edb1c9b3e6a451adc02de8da8d839
+oid sha256:2c2947addefa03503377e78af6e3a7c56cc29b7a2459f6f929a1018c8eeeee10
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bd5e8b4fd6bd1a078d3c81c8d38606014927eb33db5b87c26e74f53785ab609
+oid sha256:6df24dc4990af01f4e2532bea5ce0de0ffc3e945e702958a74ab609adcc04a3b
 size 436251442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:385f3cca5392baf05f38a00a029a89cf2c5e04bc2a58b30ee408aad9f02060a3
+oid sha256:62e73e6ad19948579779ff6a1c72ee669ed031d5b3a303d2977d967d47ff1e3c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.814056396484375,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004708097928436911,
+  "best_metric": 3.4954330921173096,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.009416195856873822,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 4.255,
       "eval_steps_per_second": 2.13,
       "step": 10
+    },
+    {
+      "epoch": 0.005649717514124294,
+      "grad_norm": 1.583258867263794,
+      "learning_rate": 0.000163742398974869,
+      "loss": 3.4178,
+      "step": 12
+    },
+    {
+      "epoch": 0.007062146892655367,
+      "grad_norm": 1.6109554767608643,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.2549,
+      "step": 15
+    },
+    {
+      "epoch": 0.007062146892655367,
+      "eval_loss": 3.5871899127960205,
+      "eval_runtime": 209.6126,
+      "eval_samples_per_second": 4.27,
+      "eval_steps_per_second": 2.137,
+      "step": 15
+    },
+    {
+      "epoch": 0.00847457627118644,
+      "grad_norm": 1.8463785648345947,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 3.4706,
+      "step": 18
+    },
+    {
+      "epoch": 0.009416195856873822,
+      "eval_loss": 3.4954330921173096,
+      "eval_runtime": 208.9877,
+      "eval_samples_per_second": 4.283,
+      "eval_steps_per_second": 2.144,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4343693347651584.0,
+  "total_flos": 8581442955116544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null