Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccee6e143cf262f18ad9d0f53f76c4b3725cb37be70c6f036923d4c306407703
+oid sha256:3a4a227c79a756f4041b4193fe029400c768e4fb220bda1690a44a40497f15ca
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d51af386786f9f5724a0dd3104c9b311e2a6675e051731d163ccb924ee0f7bb4
+oid sha256:9fa9ea107ed355e1702a55bfaf275d662d9e18bee8ba93874900a4dc29805547
 size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ecd1455bb3fc32a98fe70b8fb37696d4823754f4032a53a3810faccac9b739
+oid sha256:858ffaf5420905109f055dc370b50c9f0db5d0f1b10c2f4496d7349612d81ec4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c8f35d62ab0308ea4f3d434e6ddceeb2288fdcf54813dbe06805202a497865
+oid sha256:67ea7fdc27d3a55e20051ff7c0b0952cd04b9d78f6edb951d9b6865b402accbc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.35801100730896,
   "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.10922247252372176,
+  "epoch": 0.12287528158918698,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -191,6 +191,28 @@
       "eval_samples_per_second": 34.979,
       "eval_steps_per_second": 8.745,
       "step": 800
+    },
+    {
+      "epoch": 0.11604887705645436,
+      "grad_norm": 100.18714141845703,
+      "learning_rate": 0.00025,
+      "loss": 9.0877,
+      "step": 850
+    },
+    {
+      "epoch": 0.12287528158918698,
+      "grad_norm": 110.27277374267578,
+      "learning_rate": 0.00025,
+      "loss": 9.0612,
+      "step": 900
+    },
+    {
+      "epoch": 0.12287528158918698,
+      "eval_loss": 2.5282108783721924,
+      "eval_runtime": 176.2988,
+      "eval_samples_per_second": 34.986,
+      "eval_steps_per_second": 8.747,
+      "step": 900
     }
   ],
   "logging_steps": 50,
@@ -210,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.829010669142016e+17,
+  "total_flos": 3.182637002784768e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null