Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c016719c49be4ca5558ed86f62d48ff6511503d71d15734669ea899a7d5a07
+oid sha256:a5f3717e398c9632e2a4e967562ba686bdef014a83f6bb3a4ce1a4f447179e25
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d008f322fef9cbeb7f253b9b0010ac1539ec3c214ce9cf2b7e45cb201581d9
+oid sha256:ca2d5368cd159fb827b59a4953a980f645d9e7f2cca6fd0a6230ba3c5279be17
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34709fca1d7c4f31268ebac24fa0fec894fb794996213a9a74e5d79229a2caac
+oid sha256:9ed345d46c22829856d6e59bb67a296b6d7eaa3f14aacf9ecf2ef695d776ea15
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41439765e4324bfba55c134066121dc462eb56b67b27f6e7308aecd489d52c0e
+oid sha256:d4724a4322486cf07c6f137f6430836b1a2cb9ae0cd696f1604a47814630e3ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.572946310043335,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.04610065309258548,
+  "best_metric": 2.400266170501709,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.05378409527468306,
   "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": 15.595,
       "eval_steps_per_second": 3.899,
       "step": 300
+    },
+    {
+      "epoch": 0.04763734152900499,
+      "grad_norm": 4.437800407409668,
+      "learning_rate": 7.884012285763457e-05,
+      "loss": 4.644,
+      "step": 310
+    },
+    {
+      "epoch": 0.04917402996542451,
+      "grad_norm": 4.734920024871826,
+      "learning_rate": 7.186223258500548e-05,
+      "loss": 4.554,
+      "step": 320
+    },
+    {
+      "epoch": 0.050710718401844025,
+      "grad_norm": 7.473479747772217,
+      "learning_rate": 6.504091428474514e-05,
+      "loss": 4.4863,
+      "step": 330
+    },
+    {
+      "epoch": 0.052247406838263545,
+      "grad_norm": 8.95118236541748,
+      "learning_rate": 5.840940073393593e-05,
+      "loss": 5.0514,
+      "step": 340
+    },
+    {
+      "epoch": 0.05378409527468306,
+      "grad_norm": 15.974135398864746,
+      "learning_rate": 5.200000000000002e-05,
+      "loss": 5.0546,
+      "step": 350
+    },
+    {
+      "epoch": 0.05378409527468306,
+      "eval_loss": 2.400266170501709,
+      "eval_runtime": 178.4074,
+      "eval_samples_per_second": 15.358,
+      "eval_steps_per_second": 3.84,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.902866787074048e+16,
+  "total_flos": 6.886677918253056e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null