Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5caf7dfcf8ed893ff77a660f14d9d600e2fb93aa38c91403c9e2b1fe492e7e81
+oid sha256:5e47bb561a5feb7bcf864c61e2c66c357882bbe63ac7161d08cf966801d2139b
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a41275b1205e8fa27e5c01f2ad55cb4c073ce412ea7b704ba9b5118aef07daee
-size 325339796
+oid sha256:c5ec0fdbb629efacaf51b19eba3e8b6fa5fcc9c77d6c9ac859163dbef4b8cfee
+size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee6c65374969079a97d587c57ff4dfef3f5f9263484451a1467b8321bafb06c3
+oid sha256:ec3a794838ad98cb24e90db23231e689208506f9fde5fabc681bc616ecb6cb47
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5245962b37abe5debb29d3c0771306ab720257c32ca897672f6c78751ec6642f
+oid sha256:4e3407292f65425c0593f095883f5f3c050baccb28fc15b3c1ad88090d6c23ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9553887248039246,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.023611635814129204,
+  "best_metric": 0.9112545847892761,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.028333962976955042,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 17.355,
       "eval_steps_per_second": 4.341,
       "step": 250
+    },
+    {
+      "epoch": 0.02455610124669437,
+      "grad_norm": 0.6607593894004822,
+      "learning_rate": 0.00012039360249617425,
+      "loss": 0.9588,
+      "step": 260
+    },
+    {
+      "epoch": 0.02550056667925954,
+      "grad_norm": 1.0234694480895996,
+      "learning_rate": 0.00011280404514057264,
+      "loss": 0.9644,
+      "step": 270
+    },
+    {
+      "epoch": 0.026445032111824706,
+      "grad_norm": 1.1011518239974976,
+      "learning_rate": 0.00010519595485942743,
+      "loss": 0.8414,
+      "step": 280
+    },
+    {
+      "epoch": 0.027389497544389876,
+      "grad_norm": 1.0725549459457397,
+      "learning_rate": 9.76063975038258e-05,
+      "loss": 0.9655,
+      "step": 290
+    },
+    {
+      "epoch": 0.028333962976955042,
+      "grad_norm": 2.3623476028442383,
+      "learning_rate": 9.00723486343046e-05,
+      "loss": 0.7658,
+      "step": 300
+    },
+    {
+      "epoch": 0.028333962976955042,
+      "eval_loss": 0.9112545847892761,
+      "eval_runtime": 256.7605,
+      "eval_samples_per_second": 17.362,
+      "eval_steps_per_second": 4.343,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.2139348107264e+16,
+  "total_flos": 5.0550395633664e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null