Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:233e09ee5bc8d8105a266c3d939128182b160b7b40bb4b811a2cdea197c2fcca
+oid sha256:41fcd0c26e77ca64dc4c931a0bb512b8291dcb30e2f73a5c6beae64862e5da1c
 size 138995824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd428976deb912c8264d432082401465d7f00eb13ce7463c12cc8445cbf3f499
+oid sha256:2c6f126d97a69a4fea24d075862c914bf51b76bb888427f5a3e8768fa5d6933b
 size 71077780

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04423fbeb4d1095a270fff1825b61570a5ec93ec9d9f3bfa477470ad330fa58a
+oid sha256:a8a4a0024556e1b863a457f3632c7a699f1e182e747c1be3fc9aaf54cae8b54d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ae405ee21cfcf580074817030af494e013eac0b98711bc28cd3bcfa236dcc4b
+oid sha256:d9821b687b0301a05cac9bd37b28a5cb1ef278a0580c58589f7a45a55534bddb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6733328104019165,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.43383947939262474,
+  "best_metric": 1.5498733520507812,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.6507592190889371,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 41.402,
       "eval_steps_per_second": 10.562,
       "step": 100
+    },
+    {
+      "epoch": 0.4772234273318872,
+      "grad_norm": 0.4030924141407013,
+      "learning_rate": 0.00015501521621725395,
+      "loss": 1.5976,
+      "step": 110
+    },
+    {
+      "epoch": 0.5206073752711496,
+      "grad_norm": 0.4995245337486267,
+      "learning_rate": 0.00013888057814525847,
+      "loss": 1.5292,
+      "step": 120
+    },
+    {
+      "epoch": 0.5639913232104121,
+      "grad_norm": 0.6390402913093567,
+      "learning_rate": 0.00012166770996473358,
+      "loss": 1.5418,
+      "step": 130
+    },
+    {
+      "epoch": 0.6073752711496746,
+      "grad_norm": 0.6645438075065613,
+      "learning_rate": 0.0001038938673523089,
+      "loss": 1.6084,
+      "step": 140
+    },
+    {
+      "epoch": 0.6507592190889371,
+      "grad_norm": 2.0902185440063477,
+      "learning_rate": 8.609316355920905e-05,
+      "loss": 1.7155,
+      "step": 150
+    },
+    {
+      "epoch": 0.6507592190889371,
+      "eval_loss": 1.5498733520507812,
+      "eval_runtime": 2.3415,
+      "eval_samples_per_second": 41.853,
+      "eval_steps_per_second": 10.677,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 927298737930240.0,
+  "total_flos": 1395241156608000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null