Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ecef8fa7e14960edc3ccb347ce6703af38091d30de79023cbc40dcabb86b7ca
+oid sha256:50a9a1961f89ddbedc70c9eff06d96f67678d565f0f72c76444947e2e4b408d7
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a651078ad4ebf9db7dc0293881eb3b6c0fb0723fd137ffbf36a7b8cca221f2
+oid sha256:a6670ebf325f46c81236dd642610d06369f20d729c78c5658309b82ab0f3d62a
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1889983b1ecda80870c997c8619834b2bf57d34e140454ca55a974593ecf251f
+oid sha256:96bcc9f2208627343efb282c69f858dfa3339a1ca3e40f4ad215b8dc03deb055
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb7fb5f22874147e56941b0c2b0e6e106f9317ff78b343462a5df511f2b8d1e2
+oid sha256:6d3338a58e0bfbbf42753b4e3cd5016702f7cda5f6424a907d04dafd472f305e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1186692714691162,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.20949720670391062,
+  "best_metric": 1.097469449043274,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.24441340782122906,
   "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": 11.54,
       "eval_steps_per_second": 2.89,
       "step": 300
+    },
+    {
+      "epoch": 0.2164804469273743,
+      "grad_norm": 0.42285749316215515,
+      "learning_rate": 7.997724001423507e-05,
+      "loss": 0.9125,
+      "step": 310
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.4134489595890045,
+      "learning_rate": 7.289870709344306e-05,
+      "loss": 0.8194,
+      "step": 320
+    },
+    {
+      "epoch": 0.23044692737430167,
+      "grad_norm": 0.463888943195343,
+      "learning_rate": 6.597900439462128e-05,
+      "loss": 0.8107,
+      "step": 330
+    },
+    {
+      "epoch": 0.23743016759776536,
+      "grad_norm": 0.48735177516937256,
+      "learning_rate": 5.9251844013752326e-05,
+      "loss": 0.802,
+      "step": 340
+    },
+    {
+      "epoch": 0.24441340782122906,
+      "grad_norm": 1.3572193384170532,
+      "learning_rate": 5.275000000000002e-05,
+      "loss": 2.2902,
+      "step": 350
+    },
+    {
+      "epoch": 0.24441340782122906,
+      "eval_loss": 1.097469449043274,
+      "eval_runtime": 52.3157,
+      "eval_samples_per_second": 11.526,
+      "eval_steps_per_second": 2.886,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.48689809063936e+16,
+  "total_flos": 9.882126363131904e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null