Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a78c89ebd00d2b02f78b4c471e7c58b2f5cc503da44e7eb02d059d1372f9ad
+oid sha256:2942c604c402be0dd61661c70ff00f6d333c0f80999397e145dc919fba246f3b
 size 15156512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61340f3376726c4c48530c01086a662962794976294c22923589a83767792d0c
+oid sha256:773329a6306179af91c9bf8f1757dca5a5717f7e9dd3203e2bfb3c0cd8446d95
 size 7826042

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b995deefe39b4f8fe8d268aa6faadc741cee3f1be7a5cf6ea4d944a35ecd2f1
+oid sha256:e905d36ab2885c18b6bfd546ddde99117f7f4dab0bbce5a4c6de17d257b0dc5b
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f9b617dc7e03f15241e601f231fe18c1003fedf46d1ce0dba8cd328f9b4a80
+oid sha256:10f7347a2afb1e470f457ae657ace2e239323389d3fe2906c06dcd2436150868
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 8.469345092773438,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.7662835249042146,
+  "best_metric": 8.457124710083008,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.8939974457215837,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 109.646,
       "eval_steps_per_second": 27.91,
       "step": 300
+    },
+    {
+      "epoch": 0.7918263090676884,
+      "grad_norm": 0.7007551193237305,
+      "learning_rate": 2.908181510249828e-05,
+      "loss": 8.474,
+      "step": 310
+    },
+    {
+      "epoch": 0.8173690932311622,
+      "grad_norm": 0.7329103350639343,
+      "learning_rate": 2.2667395239887702e-05,
+      "loss": 8.5448,
+      "step": 320
+    },
+    {
+      "epoch": 0.842911877394636,
+      "grad_norm": 0.5645519495010376,
+      "learning_rate": 1.69683028863367e-05,
+      "loss": 8.4645,
+      "step": 330
+    },
+    {
+      "epoch": 0.8684546615581098,
+      "grad_norm": 0.7888035774230957,
+      "learning_rate": 1.2032594064039719e-05,
+      "loss": 8.4487,
+      "step": 340
+    },
+    {
+      "epoch": 0.8939974457215837,
+      "grad_norm": 2.03556489944458,
+      "learning_rate": 7.90188777440881e-06,
+      "loss": 8.3678,
+      "step": 350
+    },
+    {
+      "epoch": 0.8939974457215837,
+      "eval_loss": 8.457124710083008,
+      "eval_runtime": 1.5108,
+      "eval_samples_per_second": 109.217,
+      "eval_steps_per_second": 27.801,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2951723574362112.0,
+  "total_flos": 3436534796648448.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null