Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:176db8445e7b869f7566dd4c569cddc8d87e95a350d4422d8048ffaac41b0a35
+oid sha256:233e09ee5bc8d8105a266c3d939128182b160b7b40bb4b811a2cdea197c2fcca
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ec59cc0b4c01c5e22771418fc8522213747fa8178a559e9d1b414c18352637
+oid sha256:cd428976deb912c8264d432082401465d7f00eb13ce7463c12cc8445cbf3f499
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad3d1cd644e605f7de2c8884e4d9fa1d1cb1535310037473210f01262be6c57
+oid sha256:04423fbeb4d1095a270fff1825b61570a5ec93ec9d9f3bfa477470ad330fa58a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f05a07b776abc173978a0e887e7c70d773d3b63ce9e1342d6d78880c1684ac0
+oid sha256:5ae405ee21cfcf580074817030af494e013eac0b98711bc28cd3bcfa236dcc4b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.9748687744140625,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.21691973969631237,
+  "best_metric": 1.6733328104019165,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.43383947939262474,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 41.85,
       "eval_steps_per_second": 10.676,
       "step": 50
+    },
+    {
+      "epoch": 0.2603036876355748,
+      "grad_norm": 0.42307645082473755,
+      "learning_rate": 0.00020445239810895846,
+      "loss": 1.7835,
+      "step": 60
+    },
+    {
+      "epoch": 0.3036876355748373,
+      "grad_norm": 0.465277761220932,
+      "learning_rate": 0.00019985609868074957,
+      "loss": 1.7309,
+      "step": 70
+    },
+    {
+      "epoch": 0.3470715835140998,
+      "grad_norm": 0.6410661935806274,
+      "learning_rate": 0.0001923492229131769,
+      "loss": 1.6651,
+      "step": 80
+    },
+    {
+      "epoch": 0.39045553145336226,
+      "grad_norm": 0.6676890850067139,
+      "learning_rate": 0.0001821573563428174,
+      "loss": 1.7176,
+      "step": 90
+    },
+    {
+      "epoch": 0.43383947939262474,
+      "grad_norm": 2.6857898235321045,
+      "learning_rate": 0.00016958676988185618,
+      "loss": 1.8401,
+      "step": 100
+    },
+    {
+      "epoch": 0.43383947939262474,
+      "eval_loss": 1.6733328104019165,
+      "eval_runtime": 2.3671,
+      "eval_samples_per_second": 41.402,
+      "eval_steps_per_second": 10.562,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 463649368965120.0,
+  "total_flos": 927298737930240.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null