Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:125932c92fc22df2bfcd46a4b76aa1f1e12d210b210eee2efb48f7d85e2d56ce
+oid sha256:9d11579181d90a0e6f1885d461c094afb68e4ba391255616514dfcc4290f8be0
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676bda05c986598dc668b1a660178110bc3425f61918073aa0222ce2f226cd6c
+oid sha256:d3c5709d6685652583fb7baf9875f6da4e195efe4f10e74ef1c2c772d8536906
 size 4830970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bafac06a8e43bd1cc523e3d92e7a3dc4709aa044e054b6663bbc1a3cf6859d1b
+oid sha256:4c011f1beda4c8f05170094c5cb762c77f7cb8a18a37fb29a3e4306d25bd7d99
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fa0f7e2faaa98aa485e5dc42922e1b1819381507fa6961c3be50a0b49af04c0
+oid sha256:b617d9f149fb11f5d9825dc6193f0b55aa7bf4899d1811982c0c93a389d7300b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.4847993850708,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.017502236396872935,
+  "best_metric": 11.484682083129883,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.019446929329858816,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 72.608,
       "eval_steps_per_second": 18.155,
       "step": 450
+    },
+    {
+      "epoch": 0.01789117498347011,
+      "grad_norm": 0.16383996605873108,
+      "learning_rate": 4.106260230538197e-06,
+      "loss": 11.4228,
+      "step": 460
+    },
+    {
+      "epoch": 0.018280113570067286,
+      "grad_norm": 0.19095608592033386,
+      "learning_rate": 2.316354322216597e-06,
+      "loss": 11.4225,
+      "step": 470
+    },
+    {
+      "epoch": 0.01866905215666446,
+      "grad_norm": 0.478286474943161,
+      "learning_rate": 1.0315847133935416e-06,
+      "loss": 11.4453,
+      "step": 480
+    },
+    {
+      "epoch": 0.01905799074326164,
+      "grad_norm": 0.3949192464351654,
+      "learning_rate": 2.582106724586351e-07,
+      "loss": 11.5443,
+      "step": 490
+    },
+    {
+      "epoch": 0.019446929329858816,
+      "grad_norm": 1.270707607269287,
+      "learning_rate": 0.0,
+      "loss": 11.5995,
+      "step": 500
+    },
+    {
+      "epoch": 0.019446929329858816,
+      "eval_loss": 11.484682083129883,
+      "eval_runtime": 149.1447,
+      "eval_samples_per_second": 72.587,
+      "eval_steps_per_second": 18.15,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 61975756800000.0,
+  "total_flos": 68861952000000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null