Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f73d2c85fb7a949ade3389c6e227c97a6c97c460bd098400a54f838c988c99
+oid sha256:ea4d2ae17a4923ca7476bf79d7aa0742fad4969cb144279f3f15d4706e444e73
 size 997533656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d731aa3795bb408893cbbe1141fa6a90b727eb9c6530d2f29d741487c46b121
+oid sha256:d4875fb30a62843cc2edef5ad39db2ed35079ad397e13069707800640da9a461
 size 507180756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b899ebf179e478d77f43a1e1be04df80ba5ed7ff912f18bb90d45a71fb9a36f9
+oid sha256:b97bec063427a5bc68520a7c278fee734536758732f2c4113bcc45a9d87c355c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aefa5c0989fb1076f44dee5ec81119730caab480902e567590e4c3defecd81d
+oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4000242948532104,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.12874747103181902,
+  "best_metric": 1.3680524826049805,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.14713996689350745,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 10.683,
       "eval_steps_per_second": 2.678,
       "step": 350
+    },
+    {
+      "epoch": 0.1324259702041567,
+      "grad_norm": 0.5911391973495483,
+      "learning_rate": 4.804797352168861e-05,
+      "loss": 1.4978,
+      "step": 360
+    },
+    {
+      "epoch": 0.1361044693764944,
+      "grad_norm": 0.6037421226501465,
+      "learning_rate": 4.189289918950325e-05,
+      "loss": 1.4423,
+      "step": 370
+    },
+    {
+      "epoch": 0.13978296854883207,
+      "grad_norm": 0.5900255441665649,
+      "learning_rate": 3.606476390688449e-05,
+      "loss": 1.3197,
+      "step": 380
+    },
+    {
+      "epoch": 0.14346146772116977,
+      "grad_norm": 0.6815835237503052,
+      "learning_rate": 3.0591961763087043e-05,
+      "loss": 1.3703,
+      "step": 390
+    },
+    {
+      "epoch": 0.14713996689350745,
+      "grad_norm": 0.7701212167739868,
+      "learning_rate": 2.550115570003141e-05,
+      "loss": 1.2902,
+      "step": 400
+    },
+    {
+      "epoch": 0.14713996689350745,
+      "eval_loss": 1.3680524826049805,
+      "eval_runtime": 107.1594,
+      "eval_samples_per_second": 10.685,
+      "eval_steps_per_second": 2.678,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.17309374988288e+17,
+  "total_flos": 1.34067857129472e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null